CN107862258A - Method of calibration, device, equipment and the storage medium of video Chinese version content - Google Patents
Method of calibration, device, equipment and the storage medium of video Chinese version content Download PDFInfo
- Publication number
- CN107862258A CN107862258A CN201711000694.9A CN201711000694A CN107862258A CN 107862258 A CN107862258 A CN 107862258A CN 201711000694 A CN201711000694 A CN 201711000694A CN 107862258 A CN107862258 A CN 107862258A
- Authority
- CN
- China
- Prior art keywords
- text
- picture
- content
- video
- verified
- 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.)
- Pending
Links
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
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Processing (AREA)
Abstract
The applicable technical field of video image processing of the present invention, there is provided a kind of method of calibration, device, equipment and the storage medium of video Chinese version content, this method include:The verification verified to video to be verified according to receiving is asked, by Video segmentation to be verified into independent camera lens, choose the key frame of camera lens, extract picture corresponding to key frame in video to be verified, text identification is carried out to picture, to obtain the content of text in picture, calculate the matching degree of content of text and target text in pre-set text database, according to the matching degree being calculated, output lenses key frame corresponds to the corresponding check results of text in picture, so as to improve the verification efficiency of video Chinese version content, and save cost of labor and time cost.
Description
Technical field
The invention belongs to technical field of video image processing, more particularly to a kind of method of calibration of video Chinese version content,
Device, equipment and storage medium.
Background technology
With the high speed development of mobile Internet, pursuit of the people to life increasingly improves, in order to meet the needs of people,
Network multimedia technology just develops rapidly, and video is extensive by TV station, network as a kind of media format the most popular
Propagate, people can be by internet viewing, upload, all kinds of video informations of download, and internet has been increasingly becoming huge regard
Frequency warehouse, internet teaching follow tide to arise at the historic moment, and many electronic products or platform for coordinating study, can release and be based on now
The teaching video of master, the video of record class have classroom video, have the record classroom teaching video specially recorded, as this kind of internet is taught
Learn video and generally comprise substantial amounts of text message, for these videos, when doing video quality detection, master is that operation is at this stage
By manually while see video, while confirm whether video Chinese version content is wrong, it is necessary to substantial amounts of man power and material, and it is wrong
Rate is higher by mistake, detection efficiency is low.
The content of the invention
It is an object of the invention to provide a kind of method of calibration, device, equipment and the storage medium of video Chinese version content,
Aim to solve the problem that because prior art can not provide a kind of method of calibration of effective video Chinese version content, cause verification efficiency low
The problem of lower.
On the one hand, the invention provides a kind of method of calibration of video Chinese version content, methods described to comprise the steps:
Asked according to the verification for being verified to video to be verified of receiving, by the Video segmentation to be verified into independence
Camera lens;
The key frame of the camera lens is chosen, picture corresponding to key frame described in the video to be verified is extracted, to described
Picture carries out text identification, to obtain the content of text in the picture;
Calculate the matching degree of the content of text and target text in pre-set text database;
According to the matching degree being calculated, the corresponding verification knot that the camera lens key frame corresponds to text in picture is exported
Fruit.
On the other hand, the invention provides a kind of calibration equipment of video Chinese version content, described device to include:
Request reception unit, for according to the verification verified to the video to be verified request received, being treated described
Video segmentation is verified into independent camera lens;
Picture text identification unit, for choosing the key frame of the camera lens, extract and closed described in the video to be verified
Picture corresponding to key frame, text identification is carried out to the picture, to obtain the content of text in the picture;
Matching degree computing unit, for calculating the matching of the content of text and target text in pre-set text database
Degree;And
Check results output unit, for the matching degree being calculated according to, it is corresponding to export the camera lens key frame
The corresponding check results of text in picture.
On the other hand, present invention also offers a kind of computing device, including memory, processor and it is stored in described deposit
In reservoir and the computer program that can run on the processor, realized such as during computer program described in the computing device
The step of preceding methods described.
On the other hand, present invention also offers a kind of computer-readable recording medium, the computer-readable recording medium
Be stored with computer program, when the computer program is executed by processor realize as previously described method the step of.
The present invention is according to the verification request of being verified to video to be verified of receiving, by Video segmentation to be verified into only
Vertical camera lens, the key frame of camera lens is chosen, extract picture corresponding to key frame in video to be verified, text knowledge is carried out to picture
Not, to obtain the content of text in picture, the matching degree of content of text and target text in pre-set text database is calculated, according to
The matching degree being calculated, output lenses key frame corresponds to the corresponding check results of text in picture, so as to improve in video
The verification efficiency of content of text, and save cost of labor and time cost.
Brief description of the drawings
Fig. 1 is the implementation process figure of the method for calibration for the video Chinese version content that the embodiment of the present invention one provides;
Fig. 2 is the structural representation of the calibration equipment for the video Chinese version content that the embodiment of the present invention two provides;
Fig. 3 is the preferred structure schematic diagram of the calibration equipment for the video Chinese version content that the embodiment of the present invention two provides;
Fig. 4 is the matching degree computation subunit of the calibration equipment for the video Chinese version content that the embodiment of the present invention two provides
Preferred structure schematic diagram;And
Fig. 5 is the structural representation for the computing device that the embodiment of the present invention three provides.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
It is described in detail below in conjunction with specific implementation of the specific embodiment to the present invention:
Embodiment one:
Fig. 1 shows the implementation process of the method for calibration for the video Chinese version content that the embodiment of the present invention one provides, in order to
It is easy to illustrate, illustrate only the part related to the embodiment of the present invention, details are as follows:
In step S101, asked according to the verification verified to video to be verified received, by video to be verified
It is divided into independent camera lens.
The embodiment of the present invention is applied to the computing device of video Chinese version verification, and the computing device can set for local computing
Standby or high in the clouds computing device, for example, personal computer or cloud server, to be verified suitable for the text of different application scene,
Video to be verified, which can include the record classroom teaching video of recording, homemade network small video etc., has regarding for more content of text
Frequently.Video is linked up by camera lens one by one, is brought the content for representing different by the change of camera lens, therefore, is being received
The verification verified to video to be verified request after, by Video segmentation to be verified into independent camera lens.
In step s 102, the key frame of camera lens is chosen, picture corresponding to key frame in video to be verified is extracted, to picture
Text identification is carried out, to obtain the content of text in picture.
In embodiments of the present invention, it is crucial by Video segmentation to be verified into the key frame for after independent camera lens, choosing camera lens
Frame refers in a camera lens an existing frame or some frames can represent the camera lens static video properties video frame image,
Pass through the extraction to key frame, it is possible to the static characteristic of one camera lens is showed with the data volume of very little, therefore, can be made
A camera lens of video is represented with the key frame with compared with small data quantity, reduces the hardware spending of subsequent pictures identification.
Most of picture due to extraction is colour picture, and colour picture information contained amount is huge, when text identification responds
Between it is longer.It is therefore preferred that when carrying out text identification to picture, picture is converted into gray scale picture, and gray scale picture is entered
Row noise reduction process, text identification is carried out to the gray scale picture after noise reduction, to obtain the content of text in the gray scale picture after noise reduction,
So that picture to be identified is apparent, the text feature of picture is more prominent, so as in picture is improved the recognition speed of word it is same
When, improve the degree of accuracy of Text region.
In step s 103, the matching degree of content of text and target text in pre-set text database is calculated.
In embodiments of the present invention, it is necessary to build target text in local computing device or high in the clouds computing device in advance
Text database, the target text is the text occurred in video to be verified, in the text in the video to be verified
Appearance is verified.
When the content of text in calculating video to be verified is with the matching degree of target text in pre-set text database, preferably
Ground, the matching degree of the keyword and target text in pre-set text database of content of text is calculated, improving the same of calculating speed
The degree of accuracy of Shi Tigao matchings.It is further preferred that the words-frequency feature of analysis text in picture content, is selected according to words-frequency feature
Content of text keyword in picture, target text in the keyword of selection and pre-set text database is subjected to matching degree meter
Calculate, so as to further improve verification speed and the accuracy of verification.
In step S104, according to the matching degree being calculated, output lenses key frame corresponds to the correspondence of text in picture
Check results.
In embodiments of the present invention, text in picture is corresponded to according to the matching degree being calculated, output lenses key frame
Corresponding check results.As illustratively, reach for example, working as the matching degree being calculated absolutely or more than default matching degree
During threshold value, it is believed that the content of text of the picture matches completely with target text in text database in video to be verified, now
Export the assay " without text mistake in picture ".And for example, when the matching degree being calculated is less than matching degree threshold value, can recognize
Do not matched completely with target text in text database for the content of text of the picture, now, output " has text mistake in picture
Assay by mistake ".
In embodiments of the present invention, asked according to the verification verified to video to be verified received, will be to be verified
Video segmentation chooses the key frame of camera lens, picture corresponding to key frame in video to be verified is extracted, to picture into independent camera lens
Text identification is carried out, to obtain the content of text in picture, calculates content of text and target text in pre-set text database
Matching degree, according to the matching degree being calculated, output lenses key frame corresponds to the corresponding check results of text in picture, so as to carry
The high verification efficiency of video Chinese version content, saves cost of labor and time cost.
Embodiment two:
Fig. 2 shows the structure of the calibration equipment for the video Chinese version content that the embodiment of the present invention two provides, for the ease of
Illustrate, illustrate only the part related to the embodiment of the present invention, including:
Request reception unit 21, for according to the verification verified to the video to be verified request received, school will to be treated
Video segmentation is tested into independent camera lens.
The embodiment of the present invention is applied to the computing device of video Chinese version verification, and the computing device can set for local computing
Standby or high in the clouds computing device, to be verified suitable for the text of different application scene, video to be verified can include the record class recorded
Room teaching video, homemade network small video etc. have the video of more content of text.Video is connected by camera lens one by one
Come, the content for representing different is brought by the change of camera lens, therefore, in the verification verified to video to be verified received
After request, by Video segmentation to be verified into independent camera lens.
Picture text identification unit 22, for choosing the key frame of camera lens, extract in video to be verified corresponding to key frame
Picture, text identification is carried out to picture, to obtain the content of text in picture.
In embodiments of the present invention, it is crucial by Video segmentation to be verified into the key frame for after independent camera lens, choosing camera lens
Frame refers in a camera lens an existing frame or some frames can represent the camera lens static video properties video frame image,
Pass through the extraction to key frame, it is possible to the static characteristic of one camera lens is showed with the data volume of very little, therefore, can be made
A camera lens of video is represented with the key frame with compared with small data quantity, reduces the hardware spending of subsequent pictures identification.
Most of picture due to extraction is colour picture, and colour picture information contained amount is huge, when text identification responds
Between it is longer.It is therefore preferred that when carrying out text identification to picture, picture is converted into gray scale picture, and gray scale picture is entered
Row noise reduction process, text identification is carried out to the gray scale picture after noise reduction, to obtain the content of text in the gray scale picture after noise reduction,
While the recognition speed of word in improving picture, the degree of accuracy of Text region is improved.
Matching degree computing unit 23, for calculating the matching degree of content of text and target text in pre-set text database.
In embodiments of the present invention, it is necessary to build target text in local computing device or high in the clouds computing device in advance
Text database, the target text is the text occurred in video to be verified, in the text in the video to be verified
Appearance is verified.When the content of text in calculating video to be verified is with the matching degree of target text in pre-set text database,
Preferably, the matching degree of the keyword and target text in pre-set text database of content of text is calculated, is improving calculating speed
While improve matching the degree of accuracy.It is further preferred that the words-frequency feature of analysis text in picture content, according to words-frequency feature
The content of text keyword in picture is selected, target text in the keyword of selection and pre-set text database is subjected to matching degree
Calculate, so as to further improve verification speed and the accuracy of verification.
Check results output unit 24, for being corresponded to according to the matching degree being calculated, output lenses key frame in picture
The corresponding check results of text.
In embodiments of the present invention, text in picture is corresponded to according to the matching degree being calculated, output lenses key frame
Corresponding check results.As illustratively, reach for example, working as the matching degree being calculated absolutely or more than default matching degree
During threshold value, it is believed that the content of text of the picture matches completely with target text in text database in video to be verified, now
Export the assay " without text mistake in picture ".And for example, when the matching degree being calculated is less than matching degree threshold value, can recognize
Do not matched completely with target text in text database for the content of text of the picture, now, output " has text mistake in picture
Assay by mistake ".
Therefore, as shown in Figure 3, it is preferable that picture text identification unit 22 includes:
Picture processing unit 221, for picture to be converted into gray scale picture, and noise reduction process is carried out to gray scale picture, it is right
Gray scale picture after noise reduction carries out text identification, to obtain the content of text in the gray scale picture after noise reduction.
Matching degree computing unit 23 includes:
Matching degree computation subunit 231, for calculating the keyword of content of text and target text in pre-set text database
This matching degree.
Wherein, as shown in figure 4, it is further preferred that matching degree computation subunit 231 also includes:
Keywords analyzing unit 2311, for analyzing the words-frequency feature of content of text, selected according to words-frequency feature in picture
Content of text keyword;And
A Keywords matching unit 2312, for target text in the keyword of selection and pre-set text database to be carried out
Calculated with degree.
In embodiments of the present invention, each unit of the calibration equipment of video Chinese version content can be by corresponding hardware or software
Unit realize, each unit can be independent soft and hardware unit, can also be integrated into a soft and hardware unit, herein not to
The limitation present invention.
Embodiment three:
Fig. 5 shows the structure for the computing device that the embodiment of the present invention three provides, and for convenience of description, illustrate only and this
The related part of inventive embodiments.
The computing device 5 of the embodiment of the present invention includes processor 50, memory 51 and is stored in memory 51 and can
The computer program 52 run on processor 50.The processor 50 realizes above-mentioned video Chinese version when performing computer program 52
Step in the method for calibration embodiment of content, such as the step S101 to S104 shown in Fig. 1.Or processor 50 performs meter
The function of each unit in above-mentioned each device embodiment, such as the function of unit 21 to 24 shown in Fig. 2 are realized during calculation machine program 52.
In embodiments of the present invention, asked according to the verification verified to video to be verified received, will be to be verified
Video segmentation chooses the key frame of camera lens, picture corresponding to key frame in video to be verified is extracted, to picture into independent camera lens
Text identification is carried out, to obtain the content of text in picture, calculates content of text and target text in pre-set text database
Matching degree, according to the matching degree being calculated, output lenses key frame corresponds to the corresponding check results of text in picture, so as to carry
The high verification efficiency of video Chinese version content, and save cost of labor and time cost.
The computing device of the embodiment of the present invention can be local computing device or high in the clouds computing device.In the computing device 5
The step of processor 50 is realized when realizing the method for calibration of video Chinese version content when performing computer program 52 refers to foregoing
The description of embodiment of the method, will not be repeated here.
Example IV:
In embodiments of the present invention, there is provided a kind of computer-readable recording medium, the computer-readable recording medium are deposited
Computer program is contained, the computer program realizes that the method for calibration of above-mentioned video Chinese version content is implemented when being executed by processor
Step in example, for example, the step S101 to S104 shown in Fig. 1.Or the computer program is realized when being executed by processor
State the function of each unit in each device embodiment, such as the function of unit 21 to 24 shown in Fig. 2.
In embodiments of the present invention, asked according to the verification verified to video to be verified received, will be to be verified
Video segmentation chooses the key frame of camera lens, picture corresponding to key frame in video to be verified is extracted, to picture into independent camera lens
Text identification is carried out, to obtain the content of text in picture, calculates content of text and target text in pre-set text database
Matching degree, according to the matching degree being calculated, output lenses key frame corresponds to the corresponding check results of text in picture, so as to carry
The high verification efficiency of video Chinese version content, and save cost of labor and time cost.
The computer-readable recording medium of the embodiment of the present invention can include that any of computer program code can be carried
Entity or device, recording medium, for example, the memory such as ROM/RAM, disk, CD, flash memory.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should be included in the scope of the protection.
Claims (10)
1. a kind of method of calibration of video Chinese version content, it is characterised in that methods described comprises the steps:
Asked according to the verification for being verified to video to be verified of receiving, by the Video segmentation to be verified into independent mirror
Head;
The key frame of the camera lens is chosen, picture corresponding to key frame described in the video to be verified is extracted, to the picture
Text identification is carried out, to obtain the content of text in the picture;
Calculate the matching degree of the content of text and target text in pre-set text database;
According to the matching degree being calculated, the corresponding check results that the camera lens key frame corresponds to text in picture are exported.
2. the method as described in claim 1, it is characterised in that text identification is carried out to the picture, to obtain the picture
In content of text the step of, including:
The picture is converted into gray scale picture, and noise reduction process is carried out to the gray scale picture, to the gray scale after the noise reduction
Picture carries out text identification, to obtain the content of text in the gray scale picture after the noise reduction.
3. the method as described in claim 1, it is characterised in that calculate the content of text and target in pre-set text database
The step of matching degree of text, including:
Calculate the matching degree of the keyword and target text in pre-set text database of the content of text.
4. method as claimed in claim 3, it is characterised in that calculate the keyword and pre-set text data of the content of text
Include in storehouse the step of the matching degree of target text:
The words-frequency feature of the content of text is analyzed, the content of text keyword in the picture is selected according to words-frequency feature;
Calculate the matching degree of the keyword and target text in pre-set text database of the selection.
5. a kind of calibration equipment of video Chinese version content, it is characterised in that described device includes:
Request reception unit, will be described to be verified for being asked according to the verification verified to video to be verified received
Video segmentation is into independent camera lens;
Picture text identification unit, for choosing the key frame of the camera lens, extract key frame described in the video to be verified
Corresponding picture, text identification is carried out to the picture, to obtain the content of text in the picture;
Matching degree computing unit, for calculating the matching degree of the content of text and target text in pre-set text database;With
And
Check results output unit, for the matching degree being calculated according to, export the camera lens key frame and correspond to picture
The corresponding check results of Chinese version.
6. device as claimed in claim 5, it is characterised in that the picture text identification unit includes:
Picture processing unit, for the picture to be converted into gray scale picture, and noise reduction process is carried out to the gray scale picture, it is right
Gray scale picture after the noise reduction carries out text identification, to obtain the content of text in the gray scale picture after the noise reduction.
7. device as claimed in claim 5, it is characterised in that the matching degree computing unit includes:
Matching degree computation subunit, for calculating the keyword of the content of text and target text in pre-set text database
Matching degree.
8. device as claimed in claim 7, it is characterised in that the matching degree computation subunit includes:
Keywords analyzing unit, for analyzing the words-frequency feature of the content of text, selected according to words-frequency feature in the picture
Content of text keyword;And
Keywords matching unit, the matching of keyword and target text in pre-set text database for calculating the selection
Degree.
9. a kind of computing device, including memory, processor and it is stored in the memory and can be on the processor
The computer program of operation, it is characterised in that realize such as Claims 1-4 described in the computing device during computer program
The step of any one methods described.
10. a kind of computer-readable recording medium, the computer-readable recording medium storage has computer program, and its feature exists
In when the computer program is executed by processor the step of realization such as any one of Claims 1-4 methods described.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711000694.9A CN107862258A (en) | 2017-10-24 | 2017-10-24 | Method of calibration, device, equipment and the storage medium of video Chinese version content |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711000694.9A CN107862258A (en) | 2017-10-24 | 2017-10-24 | Method of calibration, device, equipment and the storage medium of video Chinese version content |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107862258A true CN107862258A (en) | 2018-03-30 |
Family
ID=61697339
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711000694.9A Pending CN107862258A (en) | 2017-10-24 | 2017-10-24 | Method of calibration, device, equipment and the storage medium of video Chinese version content |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107862258A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109901968A (en) * | 2019-01-31 | 2019-06-18 | 阿里巴巴集团控股有限公司 | A kind of automation page data method of calibration and device |
CN109982106A (en) * | 2019-04-29 | 2019-07-05 | 百度在线网络技术(北京)有限公司 | A kind of video recommendation method, server, client and electronic equipment |
CN110019817A (en) * | 2018-12-04 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of detection method, device and the electronic equipment of text in video information |
CN111064977A (en) * | 2019-12-05 | 2020-04-24 | 任子行网络技术股份有限公司 | Method, system and readable storage medium for online monitoring of network integrated art program record |
WO2020087713A1 (en) * | 2018-11-02 | 2020-05-07 | 深圳壹账通智能科技有限公司 | Video quality inspection method and apparatus, computer device and storage medium |
CN111767493A (en) * | 2020-07-07 | 2020-10-13 | 杭州安恒信息技术股份有限公司 | Method, device, equipment and storage medium for displaying content data of website |
CN112559817A (en) * | 2020-11-13 | 2021-03-26 | 北京创业光荣信息科技有限责任公司 | Report content checking method, system, computer equipment and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102222227A (en) * | 2011-04-25 | 2011-10-19 | 中国华录集团有限公司 | Video identification based system for extracting film images |
CN106845390A (en) * | 2017-01-18 | 2017-06-13 | 腾讯科技(深圳)有限公司 | Video title generation method and device |
-
2017
- 2017-10-24 CN CN201711000694.9A patent/CN107862258A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102222227A (en) * | 2011-04-25 | 2011-10-19 | 中国华录集团有限公司 | Video identification based system for extracting film images |
CN106845390A (en) * | 2017-01-18 | 2017-06-13 | 腾讯科技(深圳)有限公司 | Video title generation method and device |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020087713A1 (en) * | 2018-11-02 | 2020-05-07 | 深圳壹账通智能科技有限公司 | Video quality inspection method and apparatus, computer device and storage medium |
EP3876549A4 (en) * | 2018-11-02 | 2021-11-17 | One Connect Smart Technology Co., Ltd. (Shenzhen) | Video quality inspection method and apparatus, computer device and storage medium |
CN110019817A (en) * | 2018-12-04 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of detection method, device and the electronic equipment of text in video information |
CN109901968A (en) * | 2019-01-31 | 2019-06-18 | 阿里巴巴集团控股有限公司 | A kind of automation page data method of calibration and device |
CN109982106A (en) * | 2019-04-29 | 2019-07-05 | 百度在线网络技术(北京)有限公司 | A kind of video recommendation method, server, client and electronic equipment |
CN109982106B (en) * | 2019-04-29 | 2021-11-26 | 百度在线网络技术(北京)有限公司 | Video recommendation method, server, client and electronic equipment |
CN111064977A (en) * | 2019-12-05 | 2020-04-24 | 任子行网络技术股份有限公司 | Method, system and readable storage medium for online monitoring of network integrated art program record |
CN111767493A (en) * | 2020-07-07 | 2020-10-13 | 杭州安恒信息技术股份有限公司 | Method, device, equipment and storage medium for displaying content data of website |
CN112559817A (en) * | 2020-11-13 | 2021-03-26 | 北京创业光荣信息科技有限责任公司 | Report content checking method, system, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107862258A (en) | Method of calibration, device, equipment and the storage medium of video Chinese version content | |
US10776970B2 (en) | Method and apparatus for processing video image and computer readable medium | |
CN111476284B (en) | Image recognition model training and image recognition method and device and electronic equipment | |
CN109218629B (en) | Video generation method, storage medium and device | |
CN109117777A (en) | The method and apparatus for generating information | |
CN109862397B (en) | Video analysis method, device, equipment and storage medium | |
EP3992924A1 (en) | Machine learning based media content annotation | |
US20110150328A1 (en) | Apparatus and method for blockiing objectionable image on basis of multimodal and multiscale features | |
EP3249610B1 (en) | A method, an apparatus and a computer program product for video object segmentation | |
CN110956037B (en) | Multimedia content repeated judgment method and device | |
EP4239585A1 (en) | Video loop recognition method and apparatus, computer device, and storage medium | |
CN112150457A (en) | Video detection method, device and computer readable storage medium | |
CN110363206B (en) | Clustering of data objects, data processing and data identification method | |
CN113033677A (en) | Video classification method and device, electronic equipment and storage medium | |
CN110717421A (en) | Video content understanding method and device based on generation countermeasure network | |
CN112511818A (en) | Video playing quality detection method and device | |
CN116977774A (en) | Image generation method, device, equipment and medium | |
CN111651674A (en) | Bidirectional searching method and device and electronic equipment | |
CN111292333B (en) | Method and apparatus for segmenting an image | |
CN108717436B (en) | Commodity target rapid retrieval method based on significance detection | |
US20170228614A1 (en) | Methods and systems for detecting topic transitions in a multimedia content | |
CN111477212A (en) | Content recognition, model training and data processing method, system and equipment | |
CN115035453A (en) | Video title and tail identification method, device and equipment and readable storage medium | |
CN117009577A (en) | Video data processing method, device, equipment and readable storage medium | |
CN111046232B (en) | Video classification method, device and system |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180330 |
|
RJ01 | Rejection of invention patent application after publication |