WO2019242222A1 - 用于生成信息的方法和装置 - Google Patents

用于生成信息的方法和装置 Download PDF

Info

Publication number
WO2019242222A1
WO2019242222A1 PCT/CN2018/116184 CN2018116184W WO2019242222A1 WO 2019242222 A1 WO2019242222 A1 WO 2019242222A1 CN 2018116184 W CN2018116184 W CN 2018116184W WO 2019242222 A1 WO2019242222 A1 WO 2019242222A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
recognition
sample
model
training
Prior art date
Application number
PCT/CN2018/116184
Other languages
English (en)
French (fr)
Inventor
李伟健
李映虹
王长虎
Original Assignee
北京字节跳动网络技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京字节跳动网络技术有限公司 filed Critical 北京字节跳动网络技术有限公司
Publication of WO2019242222A1 publication Critical patent/WO2019242222A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/19—Recognition using electronic means
    • G06V30/192—Recognition using electronic means using simultaneous comparisons or correlations of the image signals with a plurality of references
    • G06V30/194—References adjustable by an adaptive method, e.g. learning

Definitions

  • Embodiments of the present application relate to the field of computer technology, and in particular, to a method and an apparatus for generating information.
  • Video usually includes foreground and background.
  • the foreground may include the shooting content (such as people, animals, behaviors, etc.) corresponding to the captured video;
  • the background may include the shooting scene (such as the sky, stadium, forest, etc.) corresponding to the captured video.
  • video recognition usually only identifies the foreground of a video.
  • the embodiments of the present application provide a method and device for generating information.
  • an embodiment of the present application provides a method for generating information.
  • the method includes: obtaining a target video; inputting the target video into a pre-trained video recognition model to obtain a pair of recognition results corresponding to the target video, wherein, The video recognition model is used to characterize the correspondence between the video and the recognition result pair.
  • the recognition result pair includes a first recognition result and a second recognition result.
  • the first recognition result is used to characterize the foreground included in the video
  • the second recognition result is used to characterize the video. Included background.
  • the video recognition model includes a first video recognition sub-model, a second video recognition sub-model, and a feature extraction network; and inputting a target video into a pre-trained video recognition model to obtain a pair of recognition results corresponding to the target video,
  • the method includes: extracting a target video from a feature extraction network to obtain video features of the target video; and inputting the obtained video features to a first video recognition sub-model and a second video recognition sub-model, respectively, to obtain a target video corresponding to the first video recognition The result is a pair of recognition results with the second recognition result.
  • the video recognition model is obtained by training as follows: obtaining a training sample set, wherein the training sample includes a sample video and a pair of sample recognition results pre-labeled for the sample video; and using the sample video of the training sample in the training sample set as As input, the pair of sample recognition results corresponding to the input sample video is taken as the desired output, and a video recognition model is obtained by training using a machine learning method.
  • the sample video of the training samples in the training sample set is used as an input
  • the sample recognition result pair corresponding to the input sample video is used as an output
  • a video recognition model is trained by using a machine learning method, including: training samples The set is divided into a preset number of training sample groups; a training sample group is selected as a candidate training sample group from the preset number of training sample groups, and based on the candidate training sample group and a predetermined initial model, the following training steps are performed: for the candidate
  • the training sample group takes the sample video of the training sample as an input, and uses the pair of sample recognition results corresponding to the input sample video as an output.
  • the initial model is trained using the machine learning method to obtain the initial video recognition model.
  • Determining whether the completion condition of the training is satisfied in response to determining that the completion condition is satisfied, generating a video recognition model based on the obtained initial video recognition model; in response to determining that the completion condition is not satisfied, selecting a training from a group of training samples that have not been selected Sample group as new Selected training sample set, and the initial video recognition model is obtained most recently as a new initial model, continuing its training procedures.
  • the completion condition includes, but is not limited to, at least one of the following: the preset number of training sample groups does not include unselected training sample groups; and inputting a sample video of training samples in candidate training sample groups into the initial model A loss value of the obtained actual recognition result pair with respect to the sample recognition result pair corresponding to the input sample video is less than a preset loss threshold.
  • an embodiment of the present application provides an apparatus for generating information.
  • the apparatus includes: an acquiring unit configured to acquire a target video; an input unit configured to input the target video into a pre-trained video recognition model, Obtain a pair of recognition results corresponding to the target video, where the video recognition model is used to characterize the correspondence between the video and the pair of recognition results, the pair of recognition results includes a first recognition result and a second recognition result, and the first recognition result is used to represent the The included foreground and the second recognition result are used to characterize the background included in the video.
  • the video recognition model includes a first video recognition sub-model, a second video recognition sub-model, and a feature extraction network; and the input unit includes: a first input module configured to input a target video into the feature extraction network to obtain Video features of the target video; a second input module configured to input the obtained video features into the first video recognition sub-model and the second video recognition sub-model, respectively, to obtain the corresponding target video including the first recognition result and the first video recognition sub-model.
  • the recognition result pairs of the two recognition results are examples of the two recognition results.
  • the video recognition model is obtained by training as follows: obtaining a training sample set, wherein the training sample includes a sample video and a pair of sample recognition results pre-labeled for the sample video; and using the sample video of the training sample in the training sample set as As input, the pair of sample recognition results corresponding to the input sample video is taken as the desired output, and a video recognition model is obtained by training using a machine learning method.
  • the sample video of the training samples in the training sample set is used as an input
  • the sample recognition result pair corresponding to the input sample video is used as an output
  • a video recognition model is trained by using a machine learning method, including: training samples The set is divided into a preset number of training sample groups; a training sample group is selected as a candidate training sample group from the preset number of training sample groups, and based on the candidate training sample group and a predetermined initial model, the following training steps are performed: for the candidate
  • the training sample group takes the sample video of the training sample as an input, and uses the pair of sample recognition results corresponding to the input sample video as an output.
  • the initial model is trained using the machine learning method to obtain the initial video recognition model.
  • Determining whether the completion condition of the training is satisfied in response to determining that the completion condition is satisfied, generating a video recognition model based on the obtained initial video recognition model; in response to determining that the completion condition is not satisfied, selecting a training from a group of training samples that have not been selected Sample group as new Selected training sample set, and the initial video recognition model is obtained most recently as a new initial model, continuing its training procedures.
  • the completion condition includes, but is not limited to, at least one of the following: the preset number of training sample groups does not include unselected training sample groups; and inputting a sample video of training samples in candidate training sample groups into the initial model A loss value of the obtained actual recognition result pair with respect to the sample recognition result pair corresponding to the input sample video is less than a preset loss threshold.
  • an embodiment of the present application provides an electronic device, including: one or more processors; a storage device storing one or more programs thereon; when one or more programs are processed by one or more processors Execution causes one or more processors to implement the method of any one of the foregoing methods for generating information.
  • an embodiment of the present application provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the method of any one of the foregoing methods for generating information is implemented.
  • the method and device for generating information obtained by the embodiments of the present application obtain a target video corresponding to the target video by acquiring the target video and then inputting the target video into a pre-trained video recognition model, where the video recognition model is used for characterization Correspondence between the video and the recognition result pair.
  • the recognition result pair includes a first recognition result and a second recognition result.
  • the first recognition result is used to characterize the foreground included in the video
  • the second recognition result is used to characterize the background included in the video.
  • the pre-trained video recognition model can be used to identify the foreground and background of the target video at the same time, which improves the diversity of information generation.
  • FIG. 1 is an exemplary system architecture diagram to which an embodiment of the present application can be applied;
  • FIG. 1 is an exemplary system architecture diagram to which an embodiment of the present application can be applied;
  • FIG. 2 is a flowchart of an embodiment of a method for generating information according to the present application
  • FIG. 3 is a schematic diagram of an application scenario of a method for generating information according to the present application.
  • FIG. 4 is a flowchart of another embodiment of a method for generating information according to the present application.
  • FIG. 5 is a schematic structural diagram of an embodiment of an apparatus for generating information according to the present application.
  • FIG. 6 is a schematic structural diagram of a computer system suitable for implementing an electronic device according to an embodiment of the present application.
  • FIG. 1 illustrates an exemplary system architecture 100 of an embodiment of a method for generating information or an apparatus for generating information to which the present application can be applied.
  • the system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105.
  • the network 104 is a medium for providing a communication link between the terminal devices 101, 102, 103 and the server 105.
  • the network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
  • the user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages and the like.
  • Various communication client applications such as model training applications, video recognition applications, web browser applications, social platform software, and the like can be installed on the terminal devices 101, 102, and 103.
  • the terminal devices 101, 102, and 103 may be hardware or software.
  • the terminal devices 101, 102, and 103 can be various electronic devices with a display screen, including but not limited to smartphones, tablets, e-book readers, MP3 players (Moving Pictures Experts Group Audio Audio Layer III, Motion picture expert compression standard audio layer 3), MP4 (Moving Picture Experts Group Audio Layer 4), player, laptop portable computer and desktop computer, etc.
  • MP3 players Motion Picture Experts Group Audio Layer III, Motion picture expert compression standard audio layer 3
  • MP4 Motion Picture Experts Group Audio Layer 4
  • player laptop portable computer and desktop computer, etc.
  • laptop portable computer and desktop computer etc.
  • the terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules (for example, multiple software or software modules used to provide distributed services), or it can be implemented as a single software or software module. It is not specifically limited here.
  • a video capture device may also be installed on the terminals.
  • the video capture device can be a variety of devices that can capture video, such as cameras, sensors, and so on. Users can use the video capture devices on the terminals 101, 102, 103 to capture video.
  • the server 105 may be a server that provides various services, such as a background server that processes videos displayed on the terminal devices 101, 102, and 103.
  • the background server can perform analysis and other processing on the received target video and other data, and can feed back the processing results (such as the recognition result pair) to the terminal device.
  • the server may be hardware or software.
  • the server can be implemented as a distributed server cluster consisting of multiple servers or as a single server.
  • the server can be implemented as multiple software or software modules (for example, multiple software or software modules used to provide distributed services), or it can be implemented as a single software or software module. It is not specifically limited here.
  • terminal devices, networks, and servers in FIG. 1 are merely exemplary. Depending on the implementation needs, there can be any number of terminal devices, networks, and servers.
  • the above-mentioned system architecture may not include a network but only a terminal device or a server.
  • a flowchart 200 of one embodiment of a method for generating information according to the present application is shown.
  • the method for generating information includes the following steps:
  • Step 201 Obtain a target video.
  • an execution subject for example, a server shown in FIG. 1
  • the target video may be a video to be identified.
  • the above-mentioned execution subject may obtain the target video sent by the electronic device (for example, the terminal device shown in FIG. 1) in communication connection therewith, or may obtain the target video stored in the local area in advance.
  • Step 202 Input a target video into a pre-trained video recognition model to obtain a pair of recognition results corresponding to the target video.
  • the execution subject may input the target video into a pre-trained video recognition model to obtain a pair of recognition results corresponding to the target video.
  • the video recognition model can be used to characterize the correspondence between the video and the recognition result pair.
  • the recognition result pair includes a first recognition result and a second recognition result.
  • the first recognition result may be used to characterize the foreground included in the video.
  • the second recognition result can be used to characterize the background included in the video.
  • the recognition results (the first recognition result and the second recognition result) in the recognition result pair may include, but are not limited to, at least one of the following: text, numbers, symbols, images, videos.
  • the foreground included in the video usually refers to the shooting content (such as people, animals, behaviors, etc.) corresponding to the video
  • the background included in the video usually refers to the shooting scene (such as Sky, stadium, forest, etc.).
  • the video recognition model may be obtained by training as follows: First, a training sample set is obtained, where the training sample includes a sample video and a sample recognition result pair that is pre-labeled for the sample video. Then, the sample video of the training samples in the training sample set is used as an input, and the pair of sample recognition results corresponding to the input sample video is used as the desired output, and a video recognition model is obtained by training using a machine learning method.
  • training samples can be selected from the training sample set and the following steps are performed: the sample video of the selected training samples is input to an initial model (such as a Convolutional Neural Network (CNN), a residual network ( ResNet), etc.) to obtain the recognition result pair; use the sample recognition result pair corresponding to the input sample video as the expected output of the initial model, and adjust the parameters of the initial model based on the obtained recognition result pair and sample recognition result pair; determine Whether there are unselected training samples in the training sample set; and in response to the absence of unselected training samples, the adjusted initial model is determined as a video recognition model.
  • an initial model such as a Convolutional Neural Network (CNN), a residual network ( ResNet), etc.
  • CNN Convolutional Neural Network
  • ResNet residual network
  • the video recognition model described above may also be obtained by training as follows:
  • the training sample set can be divided into a preset number of training sample groups in various ways.
  • the training sample set can be divided into a preset number of training sample groups in an equal division manner, or the training sample set can be divided such that the training included in each training sample group in the preset number of training sample groups
  • the number of samples is greater than or equal to a preset threshold. It should be noted that the preset number can be set in advance by a technician.
  • a training sample group can be selected as a candidate training sample group from a preset number of training sample groups, and based on the candidate training sample group and a predetermined initial model, the following training steps are performed:
  • For the candidate training sample group The sample video is used as an input, and the sample recognition result pair corresponding to the input sample video is used as an output.
  • the initial model is trained by using a machine learning method to obtain an initial video recognition model. It is determined whether a preset completion condition is used to indicate the completion of training. Yes; in response to determining that the completion conditions are met, a video recognition model is generated based on the obtained initial video recognition model.
  • an initial video recognition model may be selected from the obtained initial video recognition models as a video recognition model, or the obtained initial video recognition model may be processed (fused) to obtain a video recognition model.
  • the selection method of the training sample group is not limited in this application. For example, it may be randomly selected, or a training sample group with more training samples may be preferentially selected.
  • a training sample group is selected from the unselected training sample group as a new candidate training sample group, and the newly obtained initial video recognition model is used as a new initial model, and the process continues. Perform the training steps described above.
  • the execution subject of the steps for obtaining the video recognition model may be the same as or different from the execution subject of the method for generating information. If they are the same, the executing subject of the step for obtaining the video recognition model may store the trained video recognition model locally after training to obtain the video recognition model. If they are different, the execution subject of the step for obtaining the video recognition model may send the trained video recognition model to the execution subject of the method for generating information after training to obtain the video recognition model.
  • the above completion conditions may include, but are not limited to, at least one of the following: a preset number of training sample groups does not include an unselected training sample group; and a candidate training sample group The loss value of the actual recognition result pair obtained from the input of the initial model of the training sample of the training sample relative to the sample recognition result pair corresponding to the input sample video is less than the preset loss threshold.
  • FIG. 3 is a schematic diagram of an application scenario of the method for generating information according to this embodiment.
  • the terminal 301 first sends a target video (video obtained by shooting a kite) 302 to the server 303.
  • the server 303 obtains the target video 302, and inputs the target video 302 into a pre-trained video recognition model 304 to obtain a recognition result pair 305 corresponding to the target video 302.
  • the video recognition model can be used to characterize the correspondence between the video and the recognition result pair.
  • the recognition result pair 305 includes a first recognition result (kite) 3051 and a second recognition result (sky) 3052.
  • the first recognition result 3051 can be used to characterize the foreground included in the video
  • the second recognition result 3052 can be used to characterize the video. Background.
  • the method provided by the above embodiments of the present application obtains a target video and then inputs the target video into a pre-trained video recognition model to obtain a pair of recognition results corresponding to the target video.
  • the video recognition model is used to characterize the relationship between the video and the recognition result pair.
  • the recognition result pair includes a first recognition result and a second recognition result.
  • the first recognition result is used to characterize the foreground included in the video
  • the second recognition result is used to characterize the background included in the video, so that a pre-trained video can be used.
  • Recognition model while identifying the foreground and background of the target video, improves the diversity of information generation.
  • a flowchart 400 of still another embodiment of a method for generating information is shown.
  • the process 400 of the method for generating information includes the following steps:
  • Step 401 Obtain a target video.
  • an execution subject for example, a server shown in FIG. 1
  • a server shown in FIG. 1
  • an execution subject of the method for generating information may obtain a target video by using a wired connection method or a wireless connection method.
  • step 401 may be implemented in a manner similar to step 201 in the foregoing embodiment. Accordingly, the above description of step 201 is also applicable to step 401 of this embodiment, and details are not described herein again.
  • Step 402 Input the target video into a feature extraction network of a pre-trained video recognition model to obtain video features of the target video.
  • the video recognition model may include a feature extraction network. Further, based on the target video obtained in step 401, the execution subject may input the target video into the feature extraction network of the video recognition model to obtain the video features of the target video.
  • the target video is essentially a target image sequence arranged in chronological order. Therefore, the video characteristics of the target video can be reflected by the image characteristics of the target image in the target image sequence.
  • the feature extraction network may be used to extract the image features of the target image corresponding to the target video, and based on the image features, generate the video features and output corresponding to the target video.
  • the execution subject may directly determine the obtained image feature as the video feature corresponding to the target video, or may process the obtained image feature and determine the processed image feature as the video corresponding to the target video. feature.
  • the above-mentioned execution subject may fuse the obtained image features to obtain the fused features, and then determine the fused features as the video features corresponding to the target video.
  • the feature extraction network may include a structure (such as a convolution layer) for extracting image features, and of course, may also include other structures (such as a pooling layer), which is not limited herein.
  • a structure such as a convolution layer
  • other structures such as a pooling layer
  • Step 403 Input the obtained video features into the first video recognition sub-model and the second video recognition sub-model of the video recognition model, and obtain the recognition result pair corresponding to the target video including the first recognition result and the second recognition result.
  • the video recognition model may further include a first video recognition sub-model and a second video recognition sub-model.
  • the above-mentioned execution body may input the obtained video features into the first video recognition sub-model of the video recognition model, respectively.
  • the second video recognition sub-model to obtain a pair of recognition results corresponding to the target video and including the first recognition result and the second recognition result.
  • the first recognition result may be used to characterize the foreground included in the video.
  • the second recognition result can be used to characterize the background included in the video.
  • the recognition results (the first recognition result and the second recognition result) in the recognition result pair may include, but are not limited to, at least one of the following: text, numbers, symbols, images, videos.
  • the first video recognition sub-model is connected to a feature extraction network for generating a first recognition result based on the input video features.
  • the second video sub-model is connected to a feature extraction network, and is configured to generate a second recognition result based on the input video features.
  • the first video recognition sub-model and the second video sub-model may include a structure for generating results (for example, a classifier, a fully connected layer), and of course, other structures (for example, an output layer) may be included, which is not limited here. .
  • the process 400 of the method for generating information in this embodiment highlights the target video input feature extraction network, obtains the video features of the target video, and And using the obtained video features as shared features to input a first video recognition sub-model and a second video recognition sub-model, respectively, and then obtain a pair of recognition results. Therefore, the solution described in this embodiment can use the overall features (including foreground features and background features) of the target video to generate a first recognition result and a second recognition result. For the first recognition result, the background feature is added. For reference data, for the second recognition result, reference data of foreground features is added, which can realize more accurate video recognition and improve the accuracy of information generation.
  • this application provides an embodiment of an apparatus for generating information.
  • the apparatus embodiment corresponds to the method embodiment shown in FIG. 2.
  • the device can be specifically applied to various electronic devices.
  • the apparatus 500 for generating information in this embodiment includes: an obtaining unit 501 and an input unit 502.
  • the obtaining unit 501 is configured to obtain the target video;
  • the input unit 502 is configured to input the target video into a pre-trained video recognition model to obtain a pair of recognition results corresponding to the target video, wherein the video recognition model is used to characterize the video and recognition Correspondence between result pairs.
  • the recognition result pair includes a first recognition result and a second recognition result.
  • the first recognition result is used to characterize the foreground included in the video
  • the second recognition result is used to characterize the background included in the video.
  • the obtaining unit 501 of the apparatus 500 for generating information may obtain a target video by using a wired connection method or a wireless connection method.
  • the target video may be a video to be identified.
  • the obtaining unit 501 may obtain a target video sent by an electronic device (such as the terminal device shown in FIG. 1) that is communicatively connected to the target unit, and may also obtain a target video stored in advance locally.
  • an electronic device such as the terminal device shown in FIG. 1
  • the input unit 502 may input the target video into a pre-trained video recognition model to obtain a pair of recognition results corresponding to the target video.
  • the video recognition model can be used to characterize the correspondence between the video and the recognition result pair.
  • the recognition result pair includes a first recognition result and a second recognition result.
  • the first recognition result may be used to characterize the foreground included in the video.
  • the second recognition result can be used to characterize the background included in the video.
  • the recognition results (the first recognition result and the second recognition result) in the recognition result pair may include, but are not limited to, at least one of the following: text, numbers, symbols, images, videos.
  • the foreground included in the video usually refers to the shooting content (such as people, animals, behaviors, etc.) corresponding to the video
  • the background included in the video usually refers to the shooting scene (such as Sky, stadium, forest, etc.).
  • the video recognition model may include a first video recognition sub-model, a second video recognition sub-model, and a feature extraction network; and the input unit 502 may include: a first input module (in the figure) (Not shown), configured to extract a target video into a feature extraction network to obtain video features of the target video; a second input module (not shown in the figure), configured to input the obtained video features into a first video recognition, respectively
  • the sub-model and the second video recognition sub-model obtain a recognition result pair corresponding to the target video and including the first recognition result and the second recognition result.
  • the video recognition model may be obtained by training as follows: obtaining a training sample set, where the training sample includes a sample video and a pair of sample recognition results pre-labeled for the sample video; and training samples The sample video of the concentrated training samples is used as input, and the pair of sample recognition results corresponding to the input sample video is used as the desired output, and a video recognition model is obtained by training using a machine learning method.
  • a sample video of training samples in a training sample set is used as an input, and a pair of sample recognition results corresponding to the input sample video is used as an output.
  • Video recognition is obtained by training using a machine learning method.
  • the model includes: dividing a training sample set into a preset number of training sample groups; selecting a training sample group as a candidate training sample group from the preset number of training sample groups, and based on the candidate training sample group and a predetermined initial model, The following training steps are performed: for the candidate training sample group, the sample video of the training sample is used as an input, and the sample recognition result pair corresponding to the input sample video is used as an output, and the initial model is trained using the machine learning method to obtain the initial video recognition Model; determine whether the pre-set completion conditions used to indicate the completion of training are met; in response to determining that the completion conditions are met, generate a video recognition model based on the obtained initial video recognition model; in response to determining that the completion conditions are not met, never selected From the training sample group
  • the completion condition may include, but is not limited to, at least one of the following: a preset number of training sample groups does not include an unselected training sample group; The loss value of the actual recognition result pair obtained by inputting the sample video of the training sample into the initial model with respect to the sample recognition result pair corresponding to the input sample video is less than a preset loss threshold.
  • the apparatus 500 obtained by the foregoing embodiment of the present application obtains a target video through the obtaining unit 501, and then the input unit 502 inputs the target video into a pre-trained video recognition model to obtain a pair of recognition result corresponding to the target video, where the video recognition model is used for Characterizing the correspondence between the video and the recognition result pair, the recognition result pair includes a first recognition result and a second recognition result, the first recognition result is used to characterize the foreground included in the video, and the second recognition result is used to characterize the background included in the video, Therefore, the pre-trained video recognition model can be used to identify the foreground and background of the target video at the same time, which improves the diversity of information generation.
  • FIG. 6 illustrates a schematic structural diagram of a computer system 600 suitable for implementing an electronic device according to an embodiment of the present application.
  • the electronic device shown in FIG. 6 is only an example, and should not impose any limitation on the functions and scope of use of the embodiments of the present application.
  • the computer system 600 includes a central processing unit (CPU) 601, which can be loaded into a random access memory (RAM) 603 from a program stored in a read-only memory (ROM) 602 or from a storage portion 608. Instead, perform various appropriate actions and processes.
  • RAM random access memory
  • ROM read-only memory
  • various programs and data required for the operation of the system 600 are also stored.
  • the CPU 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604.
  • An input / output (I / O) interface 605 is also connected to the bus 604.
  • the following components are connected to the I / O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage portion 608 including a hard disk and the like; a communication section 609 including a network interface card such as a LAN card, a modem, and the like.
  • the communication section 609 performs communication processing via a network such as the Internet.
  • the driver 610 is also connected to the I / O interface 605 as necessary.
  • a removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.
  • the process described above with reference to the flowchart may be implemented as a computer software program.
  • embodiments of the present disclosure include a computer program product including a computer program carried on a computer-readable medium, the computer program containing program code for performing a method shown in a flowchart.
  • the computer program may be downloaded and installed from a network through the communication section 609, and / or installed from a removable medium 611.
  • CPU central processing unit
  • the computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two.
  • the computer-readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programming read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in combination with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal that is included in baseband or propagated as part of a carrier wave, and which carries computer-readable program code. Such a propagated data signal may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable medium may send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. .
  • the program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
  • each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, which contains one or more functions to implement a specified logical function Executable instructions.
  • the functions labeled in the blocks may also occur in a different order than those labeled in the drawings. For example, two blocks represented one after the other may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts can be implemented by a dedicated hardware-based system that performs the specified function or operation , Or it can be implemented with a combination of dedicated hardware and computer instructions.
  • the units described in the embodiments of the present application may be implemented by software or hardware.
  • the described unit may also be provided in a processor, for example, it may be described as: a processor includes an obtaining unit and an input unit. Among them, the names of these units do not constitute a limitation on the unit itself in some cases.
  • the obtaining unit may also be described as a “unit obtaining a target video”.
  • the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device in.
  • the computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device: obtains a target video; inputs the target video into a pre-trained video recognition model to obtain the target video Corresponding recognition result pair, where the video recognition model is used to characterize the correspondence between the video and the recognition result pair, the recognition result pair includes the first recognition result and the second recognition result, and the first recognition result is used to represent the foreground included in the video The second recognition result is used to characterize the background included in the video.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Databases & Information Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Image Analysis (AREA)

Abstract

本申请实施例公开了用于生成信息的方法和装置。该方法的一具体实施方式包括：获取目标视频；将目标视频输入预先训练的视频识别模型，获得目标视频所对应的识别结果对，其中，视频识别模型用于表征视频与识别结果对的对应关系，识别结果对包括第一识别结果和第二识别结果，第一识别结果用于表征视频所包括的前景，第二识别结果用于表征视频所包括的背景。该实施方式提高了信息生成的多样性。

Description

用于生成信息的方法和装置
本专利申请要求于2018年6月21日提交的、申请号为201810644175.4、申请人为北京字节跳动网络技术有限公司、发明名称为“用于生成信息的方法和装置”的中国专利申请的优先权，该申请的全文以引用的方式并入本申请中。
技术领域
本申请实施例涉及计算机技术领域，尤其涉及用于生成信息的方法和装置。
背景技术
视频通常包括前景和背景。前景可以包括拍摄获得的视频所对应的拍摄内容(例如人物、动物、行为等)；背景可以包括拍摄获得的视频所对应的拍摄场景(例如天空、球场、森林等)。
目前，视频识别通常只对视频的前景进行识别。
发明内容
本申请实施例提出了用于生成信息的方法和装置。
第一方面，本申请实施例提供了一种用于生成信息的方法，该方法包括：获取目标视频；将目标视频输入预先训练的视频识别模型，获得目标视频所对应的识别结果对，其中，视频识别模型用于表征视频与识别结果对的对应关系，识别结果对包括第一识别结果和第二识别结果，第一识别结果用于表征视频所包括的前景，第二识别结果用于表征视频所包括的背景。
在一些实施例中，视频识别模型包括第一视频识别子模型、第二视频识别子模型和特征提取网络；以及将目标视频输入预先训练的视频识别模型，获得目标视频所对应的识别结果对，包括：将目标视频 输入特征提取网络，获得目标视频的视频特征；将所获得的视频特征分别输入第一视频识别子模型和第二视频识别子模型，获得目标视频所对应的、包括第一识别结果和第二识别结果的识别结果对。
在一些实施例中，视频识别模型通过如下步骤训练得到：获取训练样本集，其中，训练样本包括样本视频和针对样本视频预先标注的样本识别结果对；将训练样本集中的训练样本的样本视频作为输入，将所输入的样本视频所对应的样本识别结果对作为期望输出，利用机器学习方法训练得到视频识别模型。
在一些实施例中，将训练样本集中的训练样本的样本视频作为输入，将所输入的样本视频所对应的样本识别结果对作为输出，利用机器学习方法训练得到视频识别模型，包括：将训练样本集划分成预设数量个训练样本组；从预设数量个训练样本组中选取训练样本组作为候选训练样本组，以及基于候选训练样本组和预先确定的初始模型，执行以下训练步骤：对于候选训练样本组，将训练样本的样本视频作为输入，将所输入的样本视频所对应的样本识别结果对作为输出，利用机器学习方法对初始模型进行训练，获得初始视频识别模型；确定预先设置的用于指示训练完成的完成条件是否满足；响应于确定完成条件满足，基于所获得的初始视频识别模型，生成视频识别模型；响应于确定完成条件不满足，从未被选取的训练样本组中选取训练样本组作为新的候选训练样本组，以及将最近一次获得的初始视频识别模型作为新的初始模型，继续执行训练步骤。
在一些实施例中，完成条件包括但不限于以下至少一项：预设数量个训练样本组中不包括未被选取的训练样本组；将候选训练样本组中的训练样本的样本视频输入初始模型所得到的实际识别结果对相对于所输入的样本视频所对应的样本识别结果对的损失值小于预设损失阈值。
第二方面，本申请实施例提供了一种用于生成信息的装置，该装置包括：获取单元，被配置成获取目标视频；输入单元，被配置成将目标视频输入预先训练的视频识别模型，获得目标视频所对应的识别结果对，其中，视频识别模型用于表征视频与识别结果对的对应关系， 识别结果对包括第一识别结果和第二识别结果，第一识别结果用于表征视频所包括的前景，第二识别结果用于表征视频所包括的背景。
在一些实施例中，视频识别模型包括第一视频识别子模型、第二视频识别子模型和特征提取网络；以及输入单元包括：第一输入模块，被配置成将目标视频输入特征提取网络，获得目标视频的视频特征；第二输入模块，被配置成将所获得的视频特征分别输入第一视频识别子模型和第二视频识别子模型，获得目标视频所对应的、包括第一识别结果和第二识别结果的识别结果对。
在一些实施例中，视频识别模型通过如下步骤训练得到：获取训练样本集，其中，训练样本包括样本视频和针对样本视频预先标注的样本识别结果对；将训练样本集中的训练样本的样本视频作为输入，将所输入的样本视频所对应的样本识别结果对作为期望输出，利用机器学习方法训练得到视频识别模型。
在一些实施例中，将训练样本集中的训练样本的样本视频作为输入，将所输入的样本视频所对应的样本识别结果对作为输出，利用机器学习方法训练得到视频识别模型，包括：将训练样本集划分成预设数量个训练样本组；从预设数量个训练样本组中选取训练样本组作为候选训练样本组，以及基于候选训练样本组和预先确定的初始模型，执行以下训练步骤：对于候选训练样本组，将训练样本的样本视频作为输入，将所输入的样本视频所对应的样本识别结果对作为输出，利用机器学习方法对初始模型进行训练，获得初始视频识别模型；确定预先设置的用于指示训练完成的完成条件是否满足；响应于确定完成条件满足，基于所获得的初始视频识别模型，生成视频识别模型；响应于确定完成条件不满足，从未被选取的训练样本组中选取训练样本组作为新的候选训练样本组，以及将最近一次获得的初始视频识别模型作为新的初始模型，继续执行训练步骤。
在一些实施例中，完成条件包括但不限于以下至少一项：预设数量个训练样本组中不包括未被选取的训练样本组；将候选训练样本组中的训练样本的样本视频输入初始模型所得到的实际识别结果对相对于所输入的样本视频所对应的样本识别结果对的损失值小于预设损失 阈值。
第三方面，本申请实施例提供了一种电子设备，包括：一个或多个处理器；存储装置，其上存储有一个或多个程序，当一个或多个程序被一个或多个处理器执行，使得一个或多个处理器实现上述用于生成信息的方法中任一实施例的方法。
第四方面，本申请实施例提供了一种计算机可读介质，其上存储有计算机程序，该程序被处理器执行时实现上述用于生成信息的方法中任一实施例的方法。
本申请实施例提供的用于生成信息的方法和装置，通过获取目标视频，然后将目标视频输入预先训练的视频识别模型，获得目标视频所对应的识别结果对，其中，视频识别模型用于表征视频与识别结果对的对应关系，识别结果对包括第一识别结果和第二识别结果，第一识别结果用于表征视频所包括的前景，第二识别结果用于表征视频所包括的背景，从而可以利用预先训练的视频识别模型，同时对目标视频的前景和背景进行识别，提高了信息生成的多样性。
附图说明
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本申请的其它特征、目的和优点将会变得更明显：
图1是本申请的一个实施例可以应用于其中的示例性***架构图；
图2是根据本申请的用于生成信息的方法的一个实施例的流程图；
图3是根据本申请的用于生成信息的方法的一个应用场景的示意图；
图4是根据本申请的用于生成信息的方法的又一个实施例的流程图；
图5是根据本申请的用于生成信息的装置的一个实施例的结构示意图；
图6是适于用来实现本申请实施例的电子设备的计算机***的结 构示意图。
具体实施方式
下面结合附图和实施例对本申请作进一步的详细说明。可以理解的是，此处所描述的具体实施例仅仅用于解释相关发明，而非对该发明的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与有关发明相关的部分。
需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请。
图1示出了可以应用本申请的用于生成信息的方法或用于生成信息的装置的实施例的示例性***架构100。
如图1所示，***架构100可以包括终端设备101、102、103，网络104和服务器105。网络104用以在终端设备101、102、103和服务器105之间提供通信链路的介质。网络104可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。
用户可以使用终端设备101、102、103通过网络104与服务器105交互，以接收或发送消息等。终端设备101、102、103上可以安装有各种通讯客户端应用，例如模型训练类应用、视频识别类应用、网页浏览器应用、社交平台软件等。
终端设备101、102、103可以是硬件，也可以是软件。当终端设备101、102、103为硬件时，可以是具有显示屏的各种电子设备，包括但不限于智能手机、平板电脑、电子书阅读器、MP3播放器(Moving Picture Experts Group Audio Layer III，动态影像专家压缩标准音频层面3)、MP4(Moving Picture Experts Group Audio Layer IV，动态影像专家压缩标准音频层面4)播放器、膝上型便携计算机和台式计算机等等。当终端设备101、102、103为软件时，可以安装在上述所列举的电子设备中。其可以实现成多个软件或软件模块(例如用来提供分布式服务的多个软件或软件模块)，也可以实现成单个软件或软件模块。在此不做具体限定。
当终端101、102、103为硬件时，其上还可以安装有视频采集设备。视频采集设备可以是各种能实现采集视频功能的设备，如摄像头、传感器等等。用户可以利用终端101、102、103上的视频采集设备来采集视频。
服务器105可以是提供各种服务的服务器，例如对终端设备101、102、103上显示的视频进行处理的后台服务器。后台服务器可以对接收到的目标视频等数据进行分析等处理，并可以将处理结果(例如识别结果对)反馈给终端设备。
需要说明的是，服务器可以是硬件，也可以是软件。当服务器为硬件时，可以实现成多个服务器组成的分布式服务器集群，也可以实现成单个服务器。当服务器为软件时，可以实现成多个软件或软件模块(例如用来提供分布式服务的多个软件或软件模块)，也可以实现成单个软件或软件模块。在此不做具体限定。
应该理解，图1中的终端设备、网络和服务器的数目仅仅是示意性的。根据实现需要，可以具有任意数目的终端设备、网络和服务器。特别地，在目标人脸视频或者生成识别结果的过程中所使用的数据不需要从远程获取的情况下，上述***架构可以不包括网络，而只包括终端设备或服务器。
继续参考图2，示出了根据本申请的用于生成信息的方法的一个实施例的流程200。该用于生成信息的方法，包括以下步骤：
步骤201，获取目标视频。
在本实施例中，用于生成信息的方法的执行主体(例如图1所示的服务器)可以通过有线连接方式或者无线连接方式获取目标视频。其中，目标视频可以为待对其进行识别的视频。
需要说明的是，上述执行主体可以获取与之通信连接的电子设备(例如图1所示的终端设备)发送的目标视频，也可以获取预先存储于本地的目标视频。
步骤202，将目标视频输入预先训练的视频识别模型，获得目标视频所对应的识别结果对。
在本实施例中，基于步骤201中得到的目标视频，上述执行主体可以将目标视频输入预先训练的视频识别模型，获得目标视频所对应的识别结果对。其中，视频识别模型可以用于表征视频与识别结果对的对应关系。识别结果对包括第一识别结果和第二识别结果。第一识别结果可以用于表征视频所包括的前景。第二识别结果可以用于表征视频所包括的背景。识别结果对中的识别结果(第一识别结果和第二识别结果)可以包括但不限于以下至少一项：文字、数字、符号、图像、视频。
在这里，可以理解的是，视频所包括的前景通常是指视频所对应的拍摄内容(例如人物、动物、行为等)，视频所包括的背景通常是指上述拍摄内容所属于的拍摄场景(例如天空、球场、森林等)。
在本实施例的一些可选的实现方式中，视频识别模型可以通过如下步骤训练得到：首先，获取训练样本集，其中，训练样本包括样本视频和针对样本视频预先标注的样本识别结果对。然后，将训练样本集中的训练样本的样本视频作为输入，将所输入的样本视频所对应的样本识别结果对作为期望输出，利用机器学习方法训练得到视频识别模型。
具体的，作为示例，可以从训练样本集中选取训练样本，并执行以下步骤：将所选取的训练样本的样本视频输入初始模型(例如卷积神经网络(Convolutional Neural Network，CNN)、残差网络(ResNet)等)，获得识别结果对；将所输入的样本视频所对应的样本识别结果对作为初始模型的期望输出，基于所获得的识别结果对和样本识别结果对，调整初始模型的参数；确定训练样本集中是否存在未被选取的训练样本；响应于不存在未被选取的训练样本，将调整后的初始模型确定为视频识别模型。需要说明的是，训练样本的选取方式在本申请中并不限制。例如可以是随机选取，也可以是优先选取样本视频的清晰度较好的训练样本。
在本实施例的一些可选的实现方式中，上述视频识别模型也可以通过如下步骤训练得到：
首先，获取训练样本集，以及将训练样本集划分成预设数量个训 练样本组。
在这里，可以采用各种方式将训练样本集划分成预设数量个训练样本组。例如，可以采用等分的方式将训练样本集划分成预设数量个训练样本组，也可以对训练样本集进行划分，使得预设数量个训练样本组中的每个训练样本组所包括的训练样本的数量值大于等于预设阈值。需要说明的是，上述预设数量可以由技术人员预先设置。
然后，可以从预设数量个训练样本组中选取训练样本组作为候选训练样本组，以及基于候选训练样本组和预先确定的初始模型，执行以下训练步骤：对于候选训练样本组，将训练样本的样本视频作为输入，将所输入的样本视频所对应的样本识别结果对作为输出，利用机器学习方法对初始模型进行训练，获得初始视频识别模型；确定预先设置的用于指示训练完成的完成条件是否满足；响应于确定完成条件满足，基于所获得的初始视频识别模型，生成视频识别模型。
在这里，可以从所得到的初始视频识别模型中选取一个初始视频识别模型作为视频识别模型，或者对所得到的初始视频识别模型进行处理(融合)，获得视频识别模型。
需要说明的是，训练样本组的选取方式在本申请中并不限制。例如可以是随机选取，也可以是优先选取训练样本较多的训练样本组。
另外，还可以响应于确定完成条件不满足，从未被选取的训练样本组中选取训练样本组作为新的候选训练样本组，以及将最近一次获得的初始视频识别模型作为新的初始模型，继续执行上述训练步骤。
需要说明的是，上述用于获得视频识别模型的步骤的执行主体可以与用于生成信息的方法的执行主体相同或者不同。如果相同，则用于获得视频识别模型的步骤的执行主体可以在训练得到视频识别模型后将训练好的视频识别模型存储在本地。如果不同，则用于获得视频识别模型的步骤的执行主体可以在训练得到视频识别模型后将训练好的视频识别模型发送给用于生成信息的方法的执行主体。
在本实施例的一些可选的实现方式中，上述完成条件可以包括但不限于以下至少一项：预设数量个训练样本组中不包括未被选取的训练样本组；将候选训练样本组中的训练样本的样本视频输入初始模型 所得到的实际识别结果对相对于所输入的样本视频所对应的样本识别结果对的损失值小于预设损失阈值。
继续参见图3，图3是根据本实施例的用于生成信息的方法的应用场景的一个示意图。在图3的应用场景中，终端301首先将目标视频(拍摄风筝所获得的视频)302发送给服务器303。然后，服务器303获取到目标视频302，以及将目标视频302输入预先训练的视频识别模型304，获得目标视频302所对应的识别结果对305。其中，视频识别模型可以用于表征视频与识别结果对的对应关系。识别结果对305包括第一识别结果(风筝)3051和第二识别结果(天空)3052，第一识别结果3051可以用于表征视频所包括的前景，第二识别结果3052可以用于表征视频所包括的背景。
本申请的上述实施例提供的方法通过获取目标视频，然后将目标视频输入预先训练的视频识别模型，获得目标视频所对应的识别结果对，其中，视频识别模型用于表征视频与识别结果对的对应关系，识别结果对包括第一识别结果和第二识别结果，第一识别结果用于表征视频所包括的前景，第二识别结果用于表征视频所包括的背景，从而可以利用预先训练的视频识别模型，同时对目标视频的前景和背景进行识别，提高了信息生成的多样性。
进一步参考图4，其示出了用于生成信息的方法的又一个实施例的流程400。该用于生成信息的方法的流程400，包括以下步骤：
步骤401，获取目标视频。
在本实施例中，用于生成信息的方法的执行主体(例如图1所示的服务器)可以通过有线连接方式或者无线连接方式获取目标视频。
需要说明的是，步骤401可以采用与前述实施例中的步骤201类似的方式实现。相应地，上文针对步骤201的描述也适可用于本实施例的步骤401，此处不再赘述。
步骤402，将目标视频输入预先训练的视频识别模型的特征提取网络，获得目标视频的视频特征。
在本实施例中，视频识别模型可以包括特征提取网络，进而，基于步骤401中得到的目标视频，上述执行主体可以将目标视频输入视频识别模型的特征提取网络，获得目标视频的视频特征。
可以理解的是，目标视频实质上是一个按照时间的先后顺序排列的目标图像序列。因此，目标视频的视频特征可以由目标图像序列中的目标图像的图像特征来体现。
在本实施例中，特征提取网络可以用于提取目标视频所对应的目标图像的图像特征，并基于图像特征，生成目标视频所对应的视频特征及输出。
具体的，上述执行主体可以将所获得的图像特征直接确定为目标视频所对应的视频特征，也可以对所获得的图像特征进行处理，并将处理后的图像特征确定为目标视频所对应的视频特征。作为示例，上述执行主体可以对所获得图像特征进行融合，获得融合后的特征，进而将融合后的特征确定为目标视频所对应的视频特征。
在这里，特征提取网络可以包括用于提取图像特征的结构(例如卷积层)，当然也可以包括其他结构(例如池化层)，此处不做限制。
步骤403，将所获得的视频特征分别输入视频识别模型的第一视频识别子模型和第二视频识别子模型，获得目标视频所对应的、包括第一识别结果和第二识别结果的识别结果对。
在本实施例中，视频识别模型还可以包括第一视频识别子模型和第二视频识别子模型，进而，上述执行主体可以将所获得的视频特征分别输入视频识别模型的第一视频识别子模型和第二视频识别子模型，获得目标视频所对应的、包括第一识别结果和第二识别结果的识别结果对。其中，第一识别结果可以用于表征视频所包括的前景。第二识别结果可以用于表征视频所包括的背景。识别结果对中的识别结果(第一识别结果和第二识别结果)可以包括但不限于以下至少一项：文字、数字、符号、图像、视频。
在本实施例中，第一视频识别子模型与特征提取网络连接，用于基于所输入的视频特征，生成第一识别结果。第二视频子模型与特征提取网络连接，用于基于所输入的视频特征，生成第二识别结果。在 这里，第一视频识别子模型和第二视频子模型可以包括用于生成结果的结构(例如分类器、全连接层)，当然还可以包括其他结构(例如输出层)，此处不做限制。
从图4中可以看出，与图2对应的实施例相比，本实施例中的用于生成信息的方法的流程400突出了将目标视频输入特征提取网络，获得目标视频的视频特征，并将所获得的视频特征作为共享特征，分别输入第一视频识别子模型和第二视频识别子模型，进而获得识别结果对的步骤。由此，本实施例描述的方案可以利用目标视频的整体特征(包括前景特征和背景特征)，生成第一识别结果和第二识别结果，对于第一识别结果而言，增加了背景特征这一参考数据，对于第二识别结果，增加了前景特征这一参考数据，进而可以实现更为准确的视频识别，提高了信息生成的准确性。
进一步参考图5，作为对上述各图所示方法的实现，本申请提供了一种用于生成信息的装置的一个实施例，该装置实施例与图2所示的方法实施例相对应，该装置具体可以应用于各种电子设备中。
如图5所示，本实施例的用于生成信息的装置500包括：获取单元501和输入单元502。其中，获取单元501被配置成获取目标视频；输入单元502被配置成将目标视频输入预先训练的视频识别模型，获得目标视频所对应的识别结果对，其中，视频识别模型用于表征视频与识别结果对的对应关系，识别结果对包括第一识别结果和第二识别结果，第一识别结果用于表征视频所包括的前景，第二识别结果用于表征视频所包括的背景。
在本实施例中，用于生成信息的装置500的获取单元501可以通过有线连接方式或者无线连接方式获取目标视频。其中，目标视频可以为待对其进行识别的视频。
需要说明的是，获取单元501可以获取与之通信连接的电子设备(例如图1所示的终端设备)发送的目标视频，也可以获取预先存储于本地的目标视频。
在本实施例中，基于获取单元501中得到的目标视频，输入单元 502可以将目标视频输入预先训练的视频识别模型，获得目标视频所对应的识别结果对。其中，视频识别模型可以用于表征视频与识别结果对的对应关系。识别结果对包括第一识别结果和第二识别结果。第一识别结果可以用于表征视频所包括的前景。第二识别结果可以用于表征视频所包括的背景。识别结果对中的识别结果(第一识别结果和第二识别结果)可以包括但不限于以下至少一项：文字、数字、符号、图像、视频。
在这里，可以理解的是，视频所包括的前景通常是指视频所对应的拍摄内容(例如人物、动物、行为等)，视频所包括的背景通常是指上述拍摄内容所属于的拍摄场景(例如天空、球场、森林等)。
在本实施例的一些可选的实现方式中，视频识别模型可以包括第一视频识别子模型、第二视频识别子模型和特征提取网络；以及输入单元502可以包括：第一输入模块(图中未示出)，被配置成将目标视频输入特征提取网络，获得目标视频的视频特征；第二输入模块(图中未示出)，被配置成将所获得的视频特征分别输入第一视频识别子模型和第二视频识别子模型，获得目标视频所对应的、包括第一识别结果和第二识别结果的识别结果对。
在本实施例的一些可选的实现方式中，视频识别模型可以通过如下步骤训练得到：获取训练样本集，其中，训练样本包括样本视频和针对样本视频预先标注的样本识别结果对；将训练样本集中的训练样本的样本视频作为输入，将所输入的样本视频所对应的样本识别结果对作为期望输出，利用机器学习方法训练得到视频识别模型。
在本实施例的一些可选的实现方式中，将训练样本集中的训练样本的样本视频作为输入，将所输入的样本视频所对应的样本识别结果对作为输出，利用机器学习方法训练得到视频识别模型，包括：将训练样本集划分成预设数量个训练样本组；从预设数量个训练样本组中选取训练样本组作为候选训练样本组，以及基于候选训练样本组和预先确定的初始模型，执行以下训练步骤：对于候选训练样本组，将训练样本的样本视频作为输入，将所输入的样本视频所对应的样本识别结果对作为输出，利用机器学习方法对初始模型进行训练，获得初始 视频识别模型；确定预先设置的用于指示训练完成的完成条件是否满足；响应于确定完成条件满足，基于所获得的初始视频识别模型，生成视频识别模型；响应于确定完成条件不满足，从未被选取的训练样本组中选取训练样本组作为新的候选训练样本组，以及将最近一次获得的初始视频识别模型作为新的初始模型，继续执行训练步骤。
在本实施例的一些可选的实现方式中，完成条件可以包括但不限于以下至少一项：预设数量个训练样本组中不包括未被选取的训练样本组；将候选训练样本组中的训练样本的样本视频输入初始模型所得到的实际识别结果对相对于所输入的样本视频所对应的样本识别结果对的损失值小于预设损失阈值。
本申请的上述实施例提供的装置500通过获取单元501获取目标视频，然后输入单元502将目标视频输入预先训练的视频识别模型，获得目标视频所对应的识别结果对，其中，视频识别模型用于表征视频与识别结果对的对应关系，识别结果对包括第一识别结果和第二识别结果，第一识别结果用于表征视频所包括的前景，第二识别结果用于表征视频所包括的背景，从而可以利用预先训练的视频识别模型，同时对目标视频的前景和背景进行识别，提高了信息生成的多样性。
下面参考图6，其示出了适于用来实现本申请实施例的电子设备的计算机***600的结构示意图。图6示出的电子设备仅仅是一个示例，不应对本申请实施例的功能和使用范围带来任何限制。
如图6所示，计算机***600包括中央处理单元(CPU)601，其可以根据存储在只读存储器(ROM)602中的程序或者从存储部分608加载到随机访问存储器(RAM)603中的程序而执行各种适当的动作和处理。在RAM 603中，还存储有***600操作所需的各种程序和数据。CPU 601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。
以下部件连接至I/O接口605：包括键盘、鼠标等的输入部分606；包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分607；包括硬盘等的存储部分608；以及包括诸如LAN卡、 调制解调器等的网络接口卡的通信部分609。通信部分609经由诸如因特网的网络执行通信处理。驱动器610也根据需要连接至I/O接口605。可拆卸介质611，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器610上，以便于从其上读出的计算机程序根据需要被安装入存储部分608。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分609从网络上被下载和安装，和/或从可拆卸介质611被安装。在该计算机程序被中央处理单元(CPU)601执行时，执行本申请的方法中限定的上述功能。需要说明的是，本申请所述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的***、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本申请中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行***、装置或者器件使用或者与其结合使用。而在本申请中，计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行***、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：无线、电线、光缆、RF等 等，或者上述的任意合适的组合。
附图中的流程图和框图，图示了按照本申请各种实施例的***、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的***来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本申请实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中，例如，可以描述为：一种处理器包括获取单元和输入单元。其中，这些单元的名称在某种情况下并不构成对该单元本身的限定，例如，获取单元还可以被描述为“获取目标视频的单元”。
作为另一方面，本申请还提供了一种计算机可读介质，该计算机可读介质可以是上述实施例中描述的电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：获取目标视频；将目标视频输入预先训练的视频识别模型，获得目标视频所对应的识别结果对，其中，视频识别模型用于表征视频与识别结果对的对应关系，识别结果对包括第一识别结果和第二识别结果，第一识别结果用于表征视频所包括的前景，第二识别结果用于表征视频所包括的背景。
以上描述仅为本申请的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本申请中所涉及的发明范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离 上述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本申请中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (12)

  1. 一种用于生成信息的方法，包括：
    获取目标视频；
    将所述目标视频输入预先训练的视频识别模型，获得所述目标视频所对应的识别结果对，其中，所述视频识别模型用于表征视频与识别结果对的对应关系，识别结果对包括第一识别结果和第二识别结果，第一识别结果用于表征视频所包括的前景，第二识别结果用于表征视频所包括的背景。
  2. 根据权利要求1所述的方法，其中，所述视频识别模型包括第一视频识别子模型、第二视频识别子模型和特征提取网络；以及
    所述将所述目标视频输入预先训练的视频识别模型，获得所述目标视频所对应的识别结果对，包括：
    将所述目标视频输入所述特征提取网络，获得所述目标视频的视频特征；
    将所获得的视频特征分别输入所述第一视频识别子模型和所述第二视频识别子模型，获得所述目标视频所对应的、包括第一识别结果和第二识别结果的识别结果对。
  3. 根据权利要求1或2所述的方法，其中，所述视频识别模型通过如下步骤训练得到：
    获取训练样本集，其中，训练样本包括样本视频和针对样本视频预先标注的样本识别结果对；
    将所述训练样本集中的训练样本的样本视频作为输入，将所输入的样本视频所对应的样本识别结果对作为期望输出，利用机器学习方法训练得到视频识别模型。
  4. 根据权利要求3所述的方法，其中，所述将所述训练样本集中的训练样本的样本视频作为输入，将所输入的样本视频所对应的样本 识别结果对作为输出，利用机器学习方法训练得到视频识别模型，包括：
    将训练样本集划分成预设数量个训练样本组；
    从预设数量个训练样本组中选取训练样本组作为候选训练样本组，以及基于候选训练样本组和预先确定的初始模型，执行以下训练步骤：对于候选训练样本组，将训练样本的样本视频作为输入，将所输入的样本视频所对应的样本识别结果对作为输出，利用机器学习方法对初始模型进行训练，获得初始视频识别模型；确定预先设置的用于指示训练完成的完成条件是否满足；响应于确定完成条件满足，基于所获得的初始视频识别模型，生成视频识别模型；
    响应于确定完成条件不满足，从未被选取的训练样本组中选取训练样本组作为新的候选训练样本组，以及将最近一次获得的初始视频识别模型作为新的初始模型，继续执行所述训练步骤。
  5. 根据权利要求4所述的方法，其中，所述完成条件包括但不限于以下至少一项：预设数量个训练样本组中不包括未被选取的训练样本组；将候选训练样本组中的训练样本的样本视频输入初始模型所得到的实际识别结果对相对于所输入的样本视频所对应的样本识别结果对的损失值小于预设损失阈值。
  6. 一种用于生成信息的装置，包括：
    获取单元，被配置成获取目标视频；
    输入单元，被配置成将所述目标视频输入预先训练的视频识别模型，获得所述目标视频所对应的识别结果对，其中，所述视频识别模型用于表征视频与识别结果对的对应关系，识别结果对包括第一识别结果和第二识别结果，第一识别结果用于表征视频所包括的前景，第二识别结果用于表征视频所包括的背景。
  7. 根据权利要求1所述的装置，其中，所述视频识别模型包括第一视频识别子模型、第二视频识别子模型和特征提取网络；以及
    所述输入单元包括：
    第一输入模块，被配置成将所述目标视频输入所述特征提取网络，获得所述目标视频的视频特征；
    第二输入模块，被配置成将所获得的视频特征分别输入所述第一视频识别子模型和所述第二视频识别子模型，获得所述目标视频所对应的、包括第一识别结果和第二识别结果的识别结果对。
  8. 根据权利要求6或7所述的装置，其中，所述视频识别模型通过如下步骤训练得到：
    获取训练样本集，其中，训练样本包括样本视频和针对样本视频预先标注的样本识别结果对；
    将所述训练样本集中的训练样本的样本视频作为输入，将所输入的样本视频所对应的样本识别结果对作为期望输出，利用机器学习方法训练得到视频识别模型。
  9. 根据权利要求8所述的装置，其中，所述将所述训练样本集中的训练样本的样本视频作为输入，将所输入的样本视频所对应的样本识别结果对作为输出，利用机器学习方法训练得到视频识别模型，包括：
    将训练样本集划分成预设数量个训练样本组；
    从预设数量个训练样本组中选取训练样本组作为候选训练样本组，以及基于候选训练样本组和预先确定的初始模型，执行以下训练步骤：对于候选训练样本组，将训练样本的样本视频作为输入，将所输入的样本视频所对应的样本识别结果对作为输出，利用机器学习方法对初始模型进行训练，获得初始视频识别模型；确定预先设置的用于指示训练完成的完成条件是否满足；响应于确定完成条件满足，基于所获得的初始视频识别模型，生成视频识别模型；
    响应于确定完成条件不满足，从未被选取的训练样本组中选取训练样本组作为新的候选训练样本组，以及将最近一次获得的初始视频识别模型作为新的初始模型，继续执行所述训练步骤。
  10. 根据权利要求9所述的装置，其中，所述完成条件包括但不限于以下至少一项：预设数量个训练样本组中不包括未被选取的训练样本组；将候选训练样本组中的训练样本的样本视频输入初始模型所得到的实际识别结果对相对于所输入的样本视频所对应的样本识别结果对的损失值小于预设损失阈值。
  11. 一种电子设备，包括：
    一个或多个处理器；
    存储装置，其上存储有一个或多个程序，
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-5中任一所述的方法。
  12. 一种计算机可读介质，其上存储有计算机程序，其中，该程序被处理器执行时实现如权利要求1-5中任一所述的方法。
PCT/CN2018/116184 2018-06-21 2018-11-19 用于生成信息的方法和装置 WO2019242222A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810644175.4 2018-06-21
CN201810644175.4A CN108830235B (zh) 2018-06-21 2018-06-21 用于生成信息的方法和装置

Publications (1)

Publication Number Publication Date
WO2019242222A1 true WO2019242222A1 (zh) 2019-12-26

Family

ID=64142947

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/116184 WO2019242222A1 (zh) 2018-06-21 2018-11-19 用于生成信息的方法和装置

Country Status (2)

Country Link
CN (1) CN108830235B (zh)
WO (1) WO2019242222A1 (zh)

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111667003A (zh) * 2020-06-05 2020-09-15 北京百度网讯科技有限公司 数据清洗方法、装置、设备以及存储介质
CN111768007A (zh) * 2020-06-28 2020-10-13 北京百度网讯科技有限公司 用于挖掘数据的方法和装置
CN111950344A (zh) * 2020-06-28 2020-11-17 北京百度网讯科技有限公司 生物类别的识别方法、装置、存储介质及电子设备
CN112101282A (zh) * 2020-09-25 2020-12-18 北京瞰天科技有限公司 水上目标识别方法、装置及电子设备和存储介质
CN112215908A (zh) * 2020-10-12 2021-01-12 国家计算机网络与信息安全管理中心 面向压缩域的视频内容比对***、优化方法、比对方法
CN112541705A (zh) * 2020-12-23 2021-03-23 北京百度网讯科技有限公司 生成用户行为评估模型的方法、装置、设备以及存储介质
CN112819078A (zh) * 2021-02-04 2021-05-18 上海明略人工智能(集团)有限公司 一种识别模型的迭代方法和装置
CN112949456A (zh) * 2021-02-26 2021-06-11 北京达佳互联信息技术有限公司 视频特征提取模型训练、视频特征提取方法和装置
CN113204695A (zh) * 2021-05-12 2021-08-03 北京百度网讯科技有限公司 网站识别方法和装置
CN113361575A (zh) * 2021-05-28 2021-09-07 北京百度网讯科技有限公司 模型训练方法、装置和电子设备
CN113378921A (zh) * 2021-06-09 2021-09-10 北京百度网讯科技有限公司 数据筛选方法、装置及电子设备
CN113642727A (zh) * 2021-08-06 2021-11-12 北京百度网讯科技有限公司 神经网络模型的训练方法和多媒体信息的处理方法、装置
CN113705682A (zh) * 2021-08-27 2021-11-26 微民保险代理有限公司 用户行为特征的处理方法及装置
CN114091128A (zh) * 2021-11-23 2022-02-25 北京百度网讯科技有限公司 一种排样方案的确定方法、装置及电子设备
WO2023035896A1 (zh) * 2021-09-08 2023-03-16 北京有竹居网络技术有限公司 视频的识别方法、装置、可读介质和电子设备
CN116156271A (zh) * 2022-12-14 2023-05-23 北京奇艺世纪科技有限公司 视频标题的生成方法、装置、电子设备及可读存储介质

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108830235B (zh) * 2018-06-21 2020-11-24 北京字节跳动网络技术有限公司 用于生成信息的方法和装置
CN110288089B (zh) * 2019-06-28 2021-07-09 北京百度网讯科技有限公司 用于发送信息的方法和装置
CN112995665A (zh) * 2021-03-10 2021-06-18 慧视云创(深圳)智能科技有限公司 一种用于摄像装置的视频编码方法及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103207870A (zh) * 2012-01-17 2013-07-17 华为技术有限公司 一种照片分类管理方法、服务器、装置及***
US20150117777A1 (en) * 2013-10-28 2015-04-30 Cyberlink Corp. Systems and Methods for Automatically Applying Effects Based on Media Content Characteristics
CN107133354A (zh) * 2017-05-25 2017-09-05 北京小米移动软件有限公司 图像描述信息的获取方法及装置
CN107909145A (zh) * 2017-12-05 2018-04-13 苏州天瞳威视电子科技有限公司 一种卷积神经网络模型的训练方法
CN108090497A (zh) * 2017-12-28 2018-05-29 广东欧珀移动通信有限公司 视频分类方法、装置、存储介质及电子设备
CN108830235A (zh) * 2018-06-21 2018-11-16 北京字节跳动网络技术有限公司 用于生成信息的方法和装置

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101777114B (zh) * 2009-01-08 2013-04-24 北京中星微电子有限公司 视频监控智能分析***和方法及头肩检测跟踪***和方法
CN115690558A (zh) * 2014-09-16 2023-02-03 华为技术有限公司 数据处理的方法和设备
US9754416B2 (en) * 2014-12-23 2017-09-05 Intel Corporation Systems and methods for contextually augmented video creation and sharing
CN107154051B (zh) * 2016-03-03 2020-06-12 株式会社理光 背景剪除方法及装置
CN105825234A (zh) * 2016-03-16 2016-08-03 电子科技大学 一种融合超像素和背景模型的前景检测方法
CN106383912B (zh) * 2016-10-14 2019-09-03 北京字节跳动网络技术有限公司 一种图片检索方法和装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103207870A (zh) * 2012-01-17 2013-07-17 华为技术有限公司 一种照片分类管理方法、服务器、装置及***
US20150117777A1 (en) * 2013-10-28 2015-04-30 Cyberlink Corp. Systems and Methods for Automatically Applying Effects Based on Media Content Characteristics
CN107133354A (zh) * 2017-05-25 2017-09-05 北京小米移动软件有限公司 图像描述信息的获取方法及装置
CN107909145A (zh) * 2017-12-05 2018-04-13 苏州天瞳威视电子科技有限公司 一种卷积神经网络模型的训练方法
CN108090497A (zh) * 2017-12-28 2018-05-29 广东欧珀移动通信有限公司 视频分类方法、装置、存储介质及电子设备
CN108830235A (zh) * 2018-06-21 2018-11-16 北京字节跳动网络技术有限公司 用于生成信息的方法和装置

Cited By (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111667003A (zh) * 2020-06-05 2020-09-15 北京百度网讯科技有限公司 数据清洗方法、装置、设备以及存储介质
CN111667003B (zh) * 2020-06-05 2023-11-03 北京百度网讯科技有限公司 数据清洗方法、装置、设备以及存储介质
CN111768007A (zh) * 2020-06-28 2020-10-13 北京百度网讯科技有限公司 用于挖掘数据的方法和装置
CN111950344A (zh) * 2020-06-28 2020-11-17 北京百度网讯科技有限公司 生物类别的识别方法、装置、存储介质及电子设备
CN111768007B (zh) * 2020-06-28 2023-08-08 北京百度网讯科技有限公司 用于挖掘数据的方法和装置
CN111950344B (zh) * 2020-06-28 2023-06-27 北京百度网讯科技有限公司 生物类别的识别方法、装置、存储介质及电子设备
CN112101282A (zh) * 2020-09-25 2020-12-18 北京瞰天科技有限公司 水上目标识别方法、装置及电子设备和存储介质
CN112101282B (zh) * 2020-09-25 2024-04-26 北京瞰天科技有限公司 水上目标识别方法、装置及电子设备和存储介质
CN112215908B (zh) * 2020-10-12 2022-12-02 国家计算机网络与信息安全管理中心 面向压缩域的视频内容比对***、优化方法、比对方法
CN112215908A (zh) * 2020-10-12 2021-01-12 国家计算机网络与信息安全管理中心 面向压缩域的视频内容比对***、优化方法、比对方法
CN112541705B (zh) * 2020-12-23 2024-01-23 北京百度网讯科技有限公司 生成用户行为评估模型的方法、装置、设备以及存储介质
CN112541705A (zh) * 2020-12-23 2021-03-23 北京百度网讯科技有限公司 生成用户行为评估模型的方法、装置、设备以及存储介质
CN112819078A (zh) * 2021-02-04 2021-05-18 上海明略人工智能(集团)有限公司 一种识别模型的迭代方法和装置
CN112819078B (zh) * 2021-02-04 2023-12-15 上海明略人工智能(集团)有限公司 一种图片识别模型的迭代方法和装置
CN112949456A (zh) * 2021-02-26 2021-06-11 北京达佳互联信息技术有限公司 视频特征提取模型训练、视频特征提取方法和装置
CN112949456B (zh) * 2021-02-26 2023-12-12 北京达佳互联信息技术有限公司 视频特征提取模型训练、视频特征提取方法和装置
CN113204695A (zh) * 2021-05-12 2021-08-03 北京百度网讯科技有限公司 网站识别方法和装置
CN113204695B (zh) * 2021-05-12 2023-09-26 北京百度网讯科技有限公司 网站识别方法和装置
CN113361575A (zh) * 2021-05-28 2021-09-07 北京百度网讯科技有限公司 模型训练方法、装置和电子设备
CN113361575B (zh) * 2021-05-28 2023-10-20 北京百度网讯科技有限公司 模型训练方法、装置和电子设备
CN113378921A (zh) * 2021-06-09 2021-09-10 北京百度网讯科技有限公司 数据筛选方法、装置及电子设备
CN113642727A (zh) * 2021-08-06 2021-11-12 北京百度网讯科技有限公司 神经网络模型的训练方法和多媒体信息的处理方法、装置
CN113642727B (zh) * 2021-08-06 2024-05-28 北京百度网讯科技有限公司 神经网络模型的训练方法和多媒体信息的处理方法、装置
CN113705682A (zh) * 2021-08-27 2021-11-26 微民保险代理有限公司 用户行为特征的处理方法及装置
CN113705682B (zh) * 2021-08-27 2024-05-14 微民保险代理有限公司 用户行为特征的处理方法及装置
WO2023035896A1 (zh) * 2021-09-08 2023-03-16 北京有竹居网络技术有限公司 视频的识别方法、装置、可读介质和电子设备
CN114091128A (zh) * 2021-11-23 2022-02-25 北京百度网讯科技有限公司 一种排样方案的确定方法、装置及电子设备
CN116156271A (zh) * 2022-12-14 2023-05-23 北京奇艺世纪科技有限公司 视频标题的生成方法、装置、电子设备及可读存储介质

Also Published As

Publication number Publication date
CN108830235A (zh) 2018-11-16
CN108830235B (zh) 2020-11-24

Similar Documents

Publication Publication Date Title
WO2019242222A1 (zh) 用于生成信息的方法和装置
WO2020000879A1 (zh) 图像识别方法和装置
US11978245B2 (en) Method and apparatus for generating image
WO2019237657A1 (zh) 用于生成模型的方法和装置
JP6994588B2 (ja) 顔特徴抽出モデル訓練方法、顔特徴抽出方法、装置、機器および記憶媒体
CN111476871B (zh) 用于生成视频的方法和装置
CN109492128B (zh) 用于生成模型的方法和装置
US11436863B2 (en) Method and apparatus for outputting data
WO2020000876A1 (zh) 用于生成模型的方法和装置
CN109993150B (zh) 用于识别年龄的方法和装置
CN111260545A (zh) 生成图像的方法和装置
JP7222008B2 (ja) 動画クリップの検索方法及び装置
CN109034069B (zh) 用于生成信息的方法和装置
CN109189544B (zh) 用于生成表盘的方法和装置
US11087140B2 (en) Information generating method and apparatus applied to terminal device
CN108235004B (zh) 视频播放性能测试方法、装置和***
CN109583389B (zh) 绘本识别方法及装置
CN110046571B (zh) 用于识别年龄的方法和装置
WO2020093724A1 (zh) 生成信息的方法和装置
CN113033677A (zh) 视频分类方法、装置、电子设备和存储介质
JP2023526899A (ja) 画像修復モデルを生成するための方法、デバイス、媒体及びプログラム製品
CN108921138B (zh) 用于生成信息的方法和装置
CN110008926B (zh) 用于识别年龄的方法和装置
CN109241930B (zh) 用于处理眉部图像的方法和装置
CN109949213B (zh) 用于生成图像的方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18923527

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 06/05/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18923527

Country of ref document: EP

Kind code of ref document: A1