Corpus ID: 362506

Action Recognition using Visual Attention

@article{Sharma2015ActionRU,
  title={Action Recognition using Visual Attention},
  author={Shikhar Sharma and Ryan Kiros and R. Salakhutdinov},
  journal={ArXiv},
  year={2015},
  volume={abs/1511.04119}
}
We propose a soft attention based model for the task of action recognition in videos. [...] Key Method The model essentially learns which parts in the frames are relevant for the task at hand and attaches higher importance to them. We evaluate the model on UCF-11 (YouTube Action), HMDB-51 and Hollywood2 datasets and analyze how the model focuses its attention depending on the scene and the action being performed.Expand
494 Citations
Improving human action recognitionby temporal attention
  • 3
Action Classification and Highlighting in Videos
  • 4
  • PDF
CHAM: Action recognition using convolutional hierarchical attention model
  • 6
  • Highly Influenced
  • PDF
DTA: Double LSTM with temporal-wise attention network for action recognition
  • 1
Joint spatial-temporal attention for action recognition
  • 9
Hierarchical Attention Network for Action Recognition in Videos
  • 56
  • Highly Influenced
  • PDF
Where and When Counts: Action Recognition in Videos
  • 2020
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 41 REFERENCES
Two-Stream Convolutional Networks for Action Recognition in Videos
  • 4,482
  • PDF
Multiple Object Recognition with Visual Attention
  • 730
  • PDF
Modeling video evolution for action recognition
  • 377
  • PDF
Describing Videos by Exploiting Temporal Structure
  • 762
  • PDF
Unsupervised Learning of Video Representations using LSTMs
  • 1,610
  • PDF
Action Recognition with Stacked Fisher Vectors
  • 318
  • PDF
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos
  • 244
  • PDF
DL-SFA: Deeply-Learned Slow Feature Analysis for Action Recognition
  • 107
  • PDF
Beyond short snippets: Deep networks for video classification
  • 1,673
  • Highly Influential
  • PDF
Long-term recurrent convolutional networks for visual recognition and description
  • 3,523
  • PDF
...
1
2
3
4
5
...