Asynchronous Temporal Fields for Action Recognition

@article{Sigurdsson2017AsynchronousTF,
  title={Asynchronous Temporal Fields for Action Recognition},
  author={Gunnar A. Sigurdsson and S. Divvala and Ali Farhadi and A. Gupta},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={5650-5659}
}
  • Gunnar A. Sigurdsson, S. Divvala, +1 author A. Gupta
  • Published 2017
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • Actions are more than just movements and trajectories: we cook to eat and we hold a cup to drink from it. A thorough understanding of videos requires going beyond appearance modeling and necessitates reasoning about the sequence of activities, as well as the higher-level constructs such as intentions. But how do we model and reason about these? We propose a fully-connected temporal CRF model for reasoning over various aspects of activities that includes objects, actions, and intentions, where… CONTINUE READING
    R-C3D: Region Convolutional 3D Network for Temporal Activity Detection
    • 291
    • Highly Influenced
    • PDF
    Videos as Space-Time Region Graphs
    • 240
    • PDF
    Hidden Two-Stream Convolutional Networks for Action Recognition
    • 138
    • PDF
    Temporal Relational Reasoning in Videos
    • 285
    • PDF
    Non-local Neural Networks
    • 1,561
    • PDF
    Video Action Transformer Network
    • 90
    • PDF
    AutoLoc: Weakly-Supervised Temporal Action Localization in Untrimmed Videos
    • 72
    • PDF
    What Actions are Needed for Understanding Human Actions in Videos?
    • 79
    • PDF
    Attend and Interact: Higher-Order Object Interactions for Video Understanding
    • 70
    • PDF
    Predictive-Corrective Networks for Action Detection
    • 45
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 70 REFERENCES
    Learning realistic human actions from movies
    • 3,363
    • PDF
    Two-Stream Convolutional Networks for Action Recognition in Videos
    • 3,959
    • Highly Influential
    • PDF
    End-to-End Learning of Action Detection from Frame Glimpses in Videos
    • 372
    • PDF
    Long-term recurrent convolutional networks for visual recognition and description
    • 3,194
    • PDF
    3D Convolutional Neural Networks for Human Action Recognition
    • 3,139
    • PDF
    Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs
    • 408
    • PDF
    Anticipating Visual Representations from Unlabeled Video
    • 285
    • PDF
    Unsupervised Learning of Video Representations using LSTMs
    • 1,427
    • PDF
    Finding action tubes
    • 462
    • PDF