Two-Stream Convolutional Networks for Action Recognition in Videos
GPTKB entity
Statements (20)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:academic_journal
|
gptkbp:author |
gptkb:Andrew_Zisserman
gptkb:Karen_Simonyan |
gptkbp:citation |
highly cited
|
gptkbp:field |
computer vision
action recognition |
gptkbp:hasMethod |
two-stream convolutional network architecture
|
https://www.w3.org/2000/01/rdf-schema#label |
Two-Stream Convolutional Networks for Action Recognition in Videos
|
gptkbp:influenced |
deep learning for video analysis
|
gptkbp:publicationYear |
2014
|
gptkbp:publishedIn |
gptkb:Advances_in_Neural_Information_Processing_Systems
|
gptkbp:trainer |
gptkb:HMDB-51
gptkb:UCF-101 |
gptkbp:url |
https://arxiv.org/abs/1406.2199
|
gptkbp:uses |
optical flow
RGB frames spatial stream temporal stream |
gptkbp:bfsParent |
gptkb:Karen_Simonyan
|
gptkbp:bfsLayer |
7
|