CN111709945A - Video copy detection method based on depth local features - Google Patents
Video copy detection method based on depth local features Download PDFInfo
- Publication number
- CN111709945A CN111709945A CN202010691138.6A CN202010691138A CN111709945A CN 111709945 A CN111709945 A CN 111709945A CN 202010691138 A CN202010691138 A CN 202010691138A CN 111709945 A CN111709945 A CN 111709945A
- Authority
- CN
- China
- Prior art keywords
- video
- fusion
- extracting
- feature map
- local features
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a video copy detection method based on depth local features, which comprises the following steps: (1) extracting frame images from video data, and constructing an image pyramid by using different scales; (2) constructing a deep convolutional neural network model, extracting a feature map from an input image pyramid, and performing feature fusion on the feature map to obtain a fusion feature map; (3) training the deep convolutional neural network model by using a metric learning mode; (4) extracting a fusion characteristic graph from the image pyramid by using the trained deep convolution neural network model; (5) extracting key points from the fusion feature map by using maximum suppression, and extracting corresponding local features according to the key points; (6) and performing video copy detection according to the local characteristics. The method has the advantages of higher extraction speed and stronger local feature representation, so that the local features can be accurately detected aiming at various complex transformed copy videos, and the method has the characteristic of high robustness.
Description
Technical Field
The invention relates to the technical field of multimedia information processing, in particular to a video copy detection method based on depth local features.
Background
In the current mobile internet era, the difficulty of preventing tampering video data from spreading wantonly is increased due to the characteristics of complexity of multimedia video data, appearance of various video editing software, wide sources and the like. Related network supervision departments want to effectively supervise the online multimedia video data and cannot rely on manual supervision and user reporting.
The current solution is to use the traditional image processing or global feature extraction method, the traditional algorithm has low processing efficiency and low accuracy, and the global feature extraction method has good processing effect on the general edited video, but the processing effect on the edited video with various complex transformations is difficult to achieve. Both the traditional image processing method and the global feature extraction method have certain defects for the current multimedia video on the Internet.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: aiming at the existing problems, a video copy detection method based on the depth local features is provided.
The technical scheme adopted by the invention is as follows:
a video copy detection method based on depth local features comprises the following steps:
(1) extracting frame images from video data, and constructing an image pyramid by using different scales;
(2) constructing a deep convolutional neural network model, extracting a feature map from an input image pyramid, and performing feature fusion on the feature map to obtain a fusion feature map;
(3) training the deep convolutional neural network model by using a metric learning mode;
(4) extracting a fusion characteristic graph from the image pyramid by using the trained deep convolution neural network model;
(5) extracting key points from the fusion feature map by using maximum suppression, and extracting corresponding local features according to the key points;
(6) and performing video copy detection according to the local characteristics.
Further, the deep convolutional neural network model is a full convolutional model comprising n-1 convolutional layers and 1 fusion convolutional layer; wherein the content of the first and second substances,
the n-i layers to the n-1 layers of convolution layers are used for extracting a characteristic diagram from an input image pyramid;
the fusion convolutional layer is used for carrying out feature fusion on the feature maps extracted by the n-i to n-1 convolutional layers to obtain a fusion feature map; i is more than or equal to 2 and less than or equal to n-1, and both i and n are integers.
Furthermore, the convolution channel of the n-i layers to the n-1 layers of convolution layers is 128.
Further, the convolution kernel size of the (n-1) th convolutional layer is 1 × 1, which is used for convolving the feature map to 1 × 1 size, and the feature map output by the convolutional layer is used as a global feature for model training.
Further, the step (6) comprises the following sub-steps:
(6.1) carrying out steps (1) to (5) on the library video to obtain local features of the library video;
(6.2) the local characteristics of the video to be detected are obtained through the steps (1) to (5);
(6.3) carrying out random consistency space verification on the local features of the video to be detected and the local features of the library video, and filtering out non-relevant matching points;
(6.4) calculating the similarity according to the residual matching points;
and (6.5) sequencing the similarity calculation results to obtain a source video data result.
Preferably, the similarity is calculated by means of vector inner product.
Preferably, the frame image extracted for the video data in step (1) is a key frame image.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
the method extracts the fusion characteristic graph based on the deep convolutional neural network model, obtains key points by adopting maximum suppression, and can extract high-efficiency local characteristics, thereby comprehensively describing the video frame image. Compared with the traditional local feature extraction algorithm, the method has the advantages that the extraction speed is higher, the local feature representation is stronger, therefore, the local feature can be accurately detected aiming at various complex transformed copy videos, the method has the characteristic of high robustness, and a feasible technical scheme is provided for a network supervision department for supervising a large amount of tampered and arbitrarily spread multimedia video data on the Internet.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a flowchart of a video copy detection method based on a deep local feature according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a deep convolutional neural network model according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of key point and local feature extraction of the present invention.
FIG. 4 is a diagram of the effectiveness of video copy detection according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the detailed description and specific examples, while indicating the preferred embodiment of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
The technique according to the present invention will be explained as follows:
convolutional Neural Networks (CNN) are a class of feed forward Neural Networks (fed forward Neural Networks) that contain convolution computations and have a deep structure, and are one of the representative algorithms for deep learning (deep).
Metric Learning (Metric Learning) is an algorithm that is central in the tasks of fine-grained classification, retrieval, face, etc., and can learn the subtle differences of images through training.
The features and properties of the present invention are described in further detail below with reference to examples.
As shown in fig. 1, the video copy detection method based on the depth local feature provided in this embodiment includes the following steps:
s1, extracting frame images for the video data, and then constructing an image pyramid by using different scales;
the video data is a temporal collection of images, and thus the processing for the video can be performed by extracting frame images, but since extracting the number of frames on a time scale causes much redundant information, it is preferable to extract key frame images for the video data. Therefore, the key frame extraction is carried out by utilizing the correlation of the video frame images, only one characteristic is reserved for similar characteristics, the redundancy is reduced, and the visual expression of the video data is improved. For example: the key frame extraction mainly utilizes the format and the content of the video frame image to judge, carries out characteristic judgment on the color, the texture, the structure and the like of the image, filters out similar pictures, ensures that only one frame is extracted from each scene, and the content of the part is the prior art and is not repeated herein.
S2, constructing a deep convolutional neural network model for extracting a feature map from the input image pyramid and carrying out feature fusion on the feature map to obtain a fusion feature map;
as shown in fig. 2, the deep convolutional neural network model is a full convolutional model including n-1 convolutional layers and 1 fusion convolutional layer, and no pooling layer is provided, so as to retain the original information of the image as much as possible; wherein the content of the first and second substances,
the n-i layers to the n-1 layers of convolution layers are used for extracting a characteristic diagram from an input image pyramid;
the fusion convolutional layer is used for carrying out feature fusion on the feature maps extracted by the n-i to n-1 convolutional layers to obtain a fusion feature map; i is more than or equal to 2 and less than or equal to n-1, and both i and n are integers. That is, the fused convolutional layers are the feature maps of the last several convolutional layers fused.
In some embodiments, the convolution channel of the n-i to n-1 convolutional layers is 128, so that the dimension of the subsequently extracted local features is kept at 128, and the scale of the feature map extracted by the convolutional layers is normalized, thereby enhancing the information of the fused feature map.
In some embodiments, the convolution kernel size of the (n-1) th convolutional layer is 1 × 1 for convolving the feature map to 1 × 1 size, and the feature map output by the convolutional layer is used as a global feature for model training.
S3, training the deep convolutional neural network model by using a metric learning mode;
and a metric learning mode is adopted, so that the model learns the slight difference between the images, and the detection precision is improved. The method specifically adopts the Arcface Loss function containing the angle information, is different from the traditional triple Loss function (triple Loss), and is easy to converge in model and richer in learned information.
S4, extracting a fusion feature map from the image pyramid by using the trained deep convolution neural network model;
s5, as shown in fig. 3, extracting key points from the fused feature map by using maximum suppression, and extracting corresponding local features according to the key points;
s6, video copy detection is carried out according to the local features:
s61, obtaining the local characteristics of the library video through the steps S1-S5, wherein the local characteristics can be understood as a local characteristic library of the library video which is configured in advance and used for detecting the video to be detected subsequently;
s62, processing the video to be detected by steps S1-S5 to obtain the local characteristics of the video; it should be noted that, if the pyramid is constructed on the key frame image and the local feature is obtained for the library video, the pyramid is constructed on the key frame image and the local feature is obtained for the video to be detected;
s63, performing random consistency spatial validation (RANSAC) on the local features of the video to be detected and the local features of the library video, and filtering out non-relevant matching points;
s64, calculating similarity according to the residual matching points by adopting a vector inner product mode;
s65, sorting the similarity calculation results to obtain the source video data result, as shown in fig. 4.
As can be seen from the above, the present invention has the following beneficial effects:
the method extracts the fusion characteristic graph based on the deep convolutional neural network model, obtains key points by adopting maximum suppression, and can extract high-efficiency local characteristics, thereby comprehensively describing the video frame image. Compared with the traditional local feature extraction algorithm, the method has the advantages that the extraction speed is higher, the local feature representation is stronger, therefore, the local feature can be accurately detected aiming at various complex transformed copy videos, the method has the characteristic of high robustness, and a feasible technical scheme is provided for a network supervision department for supervising a large amount of tampered and arbitrarily spread multimedia video data on the Internet.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (7)
1. A video copy detection method based on depth local features is characterized by comprising the following steps:
(1) extracting frame images from video data, and constructing an image pyramid by using different scales;
(2) constructing a deep convolutional neural network model, extracting a feature map from an input image pyramid, and performing feature fusion on the feature map to obtain a fusion feature map;
(3) training the deep convolutional neural network model by using a metric learning mode;
(4) extracting a fusion characteristic graph from the image pyramid by using the trained deep convolution neural network model;
(5) extracting key points from the fusion feature map by using maximum suppression, and extracting corresponding local features according to the key points;
(6) and performing video copy detection according to the local characteristics.
2. The method according to claim 1, wherein the deep convolutional neural network model is a full convolutional model comprising n-1 convolutional layers and 1 fusion convolutional layer; wherein the content of the first and second substances,
the n-i layers to the n-1 layers of convolution layers are used for extracting a characteristic diagram from an input image pyramid;
the fusion convolutional layer is used for carrying out feature fusion on the feature maps extracted by the n-i to n-1 convolutional layers to obtain a fusion feature map; i is more than or equal to 2 and less than or equal to n-1, and both i and n are integers.
3. The method according to claim 2, wherein the convolution channel of the n-i to n-1 convolutional layers is 128.
4. The method of claim 2, wherein the convolution kernel size of the (n-1) th layer of convolutional layer is 1 x 1 for convolving the feature map to 1 x 1 size, and the feature map output by the layer of convolutional layer is used as a global feature for model training.
5. The method for detecting video copy based on deep local features of claim 1, wherein the step (6) comprises the following sub-steps:
(6.1) carrying out steps (1) to (5) on the library video to obtain local features of the library video;
(6.2) the local characteristics of the video to be detected are obtained through the steps (1) to (5);
(6.3) carrying out random consistency space verification on the local features of the video to be detected and the local features of the library video, and filtering out non-relevant matching points;
(6.4) calculating the similarity according to the residual matching points;
and (6.5) sequencing the similarity calculation results to obtain a source video data result.
6. The method according to claim 5, wherein the similarity is calculated by means of vector inner product.
7. The method for detecting video copy based on deep local features of any one of claims 1 to 6, wherein the frame image extracted for the video data in step (1) is a key frame image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010691138.6A CN111709945B (en) | 2020-07-17 | 2020-07-17 | Video copy detection method based on depth local features |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010691138.6A CN111709945B (en) | 2020-07-17 | 2020-07-17 | Video copy detection method based on depth local features |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111709945A true CN111709945A (en) | 2020-09-25 |
| CN111709945B CN111709945B (en) | 2023-06-30 |
Family
ID=72546636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010691138.6A Active CN111709945B (en) | 2020-07-17 | 2020-07-17 | Video copy detection method based on depth local features |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111709945B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI776668B (en) * | 2021-09-07 | 2022-09-01 | 台達電子工業股份有限公司 | Image processing method and image processing system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376003A (en) * | 2013-08-13 | 2015-02-25 | 深圳市腾讯计算机***有限公司 | Video retrieval method and device |
| CN106845499A (en) * | 2017-01-19 | 2017-06-13 | 清华大学 | A kind of image object detection method semantic based on natural language |
| CN106991373A (en) * | 2017-03-02 | 2017-07-28 | 中国人民解放军国防科学技术大学 | A kind of copy video detecting method based on deep learning and graph theory |
| CN108197566A (en) * | 2017-12-29 | 2018-06-22 | 成都三零凯天通信实业有限公司 | Monitoring video behavior detection method based on multi-path neural network |
| US20190279014A1 (en) * | 2016-12-27 | 2019-09-12 | Beijing Sensetime Technology Development Co., Ltd | Method and apparatus for detecting object keypoint, and electronic device |
| CN110781350A (en) * | 2019-09-26 | 2020-02-11 | 武汉大学 | Pedestrian retrieval method and system oriented to full-picture monitoring scene |
| CN111126412A (en) * | 2019-11-22 | 2020-05-08 | 复旦大学 | Image key point detection method based on characteristic pyramid network |
| WO2020098225A1 (en) * | 2018-11-16 | 2020-05-22 | 北京市商汤科技开发有限公司 | Key point detection method and apparatus, electronic device and storage medium |
| CN111241338A (en) * | 2020-01-08 | 2020-06-05 | 成都三零凯天通信实业有限公司 | Depth feature fusion video copy detection method based on attention mechanism |
| CN111275044A (en) * | 2020-02-21 | 2020-06-12 | 西北工业大学 | Weak supervision target detection method based on sample selection and self-adaptive hard case mining |
-
2020
- 2020-07-17 CN CN202010691138.6A patent/CN111709945B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376003A (en) * | 2013-08-13 | 2015-02-25 | 深圳市腾讯计算机***有限公司 | Video retrieval method and device |
| US20190279014A1 (en) * | 2016-12-27 | 2019-09-12 | Beijing Sensetime Technology Development Co., Ltd | Method and apparatus for detecting object keypoint, and electronic device |
| CN106845499A (en) * | 2017-01-19 | 2017-06-13 | 清华大学 | A kind of image object detection method semantic based on natural language |
| CN106991373A (en) * | 2017-03-02 | 2017-07-28 | 中国人民解放军国防科学技术大学 | A kind of copy video detecting method based on deep learning and graph theory |
| CN108197566A (en) * | 2017-12-29 | 2018-06-22 | 成都三零凯天通信实业有限公司 | Monitoring video behavior detection method based on multi-path neural network |
| WO2020098225A1 (en) * | 2018-11-16 | 2020-05-22 | 北京市商汤科技开发有限公司 | Key point detection method and apparatus, electronic device and storage medium |
| CN110781350A (en) * | 2019-09-26 | 2020-02-11 | 武汉大学 | Pedestrian retrieval method and system oriented to full-picture monitoring scene |
| CN111126412A (en) * | 2019-11-22 | 2020-05-08 | 复旦大学 | Image key point detection method based on characteristic pyramid network |
| CN111241338A (en) * | 2020-01-08 | 2020-06-05 | 成都三零凯天通信实业有限公司 | Depth feature fusion video copy detection method based on attention mechanism |
| CN111275044A (en) * | 2020-02-21 | 2020-06-12 | 西北工业大学 | Weak supervision target detection method based on sample selection and self-adaptive hard case mining |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI776668B (en) * | 2021-09-07 | 2022-09-01 | 台達電子工業股份有限公司 | Image processing method and image processing system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111709945B (en) | 2023-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Torralba et al. | Labelme: Online image annotation and applications | |
| Ding et al. | Point cloud saliency detection by local and global feature fusion | |
| Parikh et al. | Exploring tiny images: The roles of appearance and contextual information for machine and human object recognition | |
| CN112232134B (en) | Human body posture estimation method based on hourglass network and attention mechanism | |
| CN111241338B (en) | Depth feature fusion video copy detection method based on attention mechanism | |
| CN111754396A (en) | Face image processing method and device, computer equipment and storage medium | |
| CN111079539A (en) | Video abnormal behavior detection method based on abnormal tracking | |
| CN113761359B (en) | Data packet recommendation method, device, electronic equipment and storage medium | |
| CN112818904A (en) | Crowd density estimation method and device based on attention mechanism | |
| CN116071709A (en) | Crowd counting method, system and storage medium based on improved VGG16 network | |
| CN115131218A (en) | Image processing method, image processing device, computer readable medium and electronic equipment | |
| Niu et al. | Image retargeting quality assessment based on registration confidence measure and noticeability-based pooling | |
| CN110163095B (en) | Loop detection method, loop detection device and terminal equipment | |
| Weng et al. | A survey on improved GAN based image inpainting | |
| CN111709945A (en) | Video copy detection method based on depth local features | |
| Zheng et al. | Pose flow learning from person images for pose guided synthesis | |
| CN114998814B (en) | Target video generation method and device, computer equipment and storage medium | |
| Xi et al. | Reconstructing piecewise planar scenes with multi-view regularization | |
| Zeng et al. | Multi-view self-supervised learning for 3D facial texture reconstruction from single image | |
| CN114329050A (en) | Visual media data deduplication processing method, device, equipment and storage medium | |
| CN111695526B (en) | Network model generation method, pedestrian re-recognition method and device | |
| Yin Albert et al. | Identifying and Monitoring Students’ Classroom Learning Behavior Based on Multisource Information | |
| Liu | 3DSportNet: 3D sport reconstruction by quality-aware deep multi-video summation | |
| Jam et al. | V-LinkNet: Learning Contextual Inpainting Across Latent Space of Generative Adversarial Network | |
| Raj | Learning Augmentation Policy Schedules for Unsuperivsed Depth Estimation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220517 Address after: 518000 22nd floor, building C, Shenzhen International Innovation Center (Futian science and Technology Plaza), No. 1006, Shennan Avenue, Xintian community, Huafu street, Futian District, Shenzhen, Guangdong Province Applicant after: Shenzhen wanglian Anrui Network Technology Co.,Ltd. Address before: Floor 4-8, unit 5, building 1, 333 Yunhua Road, high tech Zone, Chengdu, Sichuan 610041 Applicant before: CHENGDU 30KAITIAN COMMUNICATION INDUSTRY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |