Name
Title | ||
|---|---|---|
Enhanced Action Recognition With Visual Attribute-Augmented 3D Convolutional Neural Network |
Abstract | ||
|---|---|---|
Visual attributes in individual video frames, such as the presence of characteristic objects and scenes, offer substantial information for action recognition in videos. With individual 2D video frame as input, visual attributes extraction could be achieved effectively and efficiently with more sophisticated convolutional neural network than current 3D CNNs with spatio-temporal filters, thanks to fewer parameters in 2D CNNs. In this paper, the integration of visual attributes (including detection, encoding and classification) into multistream 3D CNN is proposed for action recognition in trimmed videos, with the proposed visual Attribute-augmented3D CNN (A3D) framework. The visual attribute pipeline includes an object detection network, anattributes encoding network and a classification network. Our proposed A3D framework achieves state-of-the-art performance on both the HMDB51 and the UCF101 datasets. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/ICMEW.2018.8551536 | 2018 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) |
Keywords | Field | DocType |
Action Recognition,Visual Attributes,Detection,NetVLAD,Word2vec | Object detection,Computer vision,Pattern recognition,Convolutional neural network,Computer science,Action recognition,Artificial intelligence,Word2vec,Encoding (memory) | Conference |
ISSN | ISBN | Citations |
2330-7927 | 978-1-5386-4196-5 | 2 |
PageRank | References | Authors |
0.39 | 4 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yunfeng Wang | 1 | 4 | 1.79 |
| Wengang Zhou | 2 | 22 | 12.93 |
| Qilin Zhang | 3 | 38 | 10.54 |
| Houqiang Li | 4 | 2090 | 172.30 |