http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112836687-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_e61d1d067171f47fb2cb73fe648367ae |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-49 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-46 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2411 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-25 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-00 |
filingDate | 2018-05-10-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f6ca22296b8cd57221e4e66187c98cf6 |
publicationDate | 2021-05-25-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-112836687-A |
titleOfInvention | Video behavior segmentation method, device, computer equipment and medium |
abstract | The present application discloses a video behavior segmentation method, device, computer equipment and medium. The method includes: dividing the video into segments based on the correlation coefficient between adjacent video frames in the video; for the video frame in the segment, identifying the scene of the video frame to obtain a scene feature vector; For the video frame in the clip, identify the local behavior feature of the video frame, and obtain a local behavior feature vector; based on the scene feature vector and the local behavior feature vector, identify the behavior category of the video frame and the behavior category corresponding to the behavior category. Confidence; based on the behavior category and confidence of the video frame of the segment, determine the behavior category of the segment; and combine adjacent segments with the same behavior category to obtain a segmentation result of the video. The method can simultaneously fuse the two-way model, comprehensively use the two dimensions of scene and local behavior, and extract the overall behavior information, so as to quickly segment the video. |
priorityDate | 2018-05-10-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Predicate | Subject |
---|---|
isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID458397426 |
Total number of triples: 16.