Skip to Main content Skip to Navigation
Conference papers

ActionVLAD: Learning spatio-temporal aggregation for action classification

Abstract : In this work, we introduce a new video representation for action classification that aggregates local convolu-tional features across the entire spatio-temporal extent of the video. We do so by integrating state-of-the-art two-stream networks [42] with learnable spatio-temporal feature aggregation [6]. The resulting architecture is end-to-end trainable for whole-video classification. We investigate different strategies for pooling across space and time and combining signals from the different streams. We find that: (i) it is important to pool jointly across space and time, but (ii) appearance and motion streams are best aggregated into their own separate representations. Finally, we show that our representation outperforms the two-stream base architecture by a large margin (13% relative) as well as out-performs other baselines with comparable base architec-tures on HMDB51, UCF101, and Charades video classification benchmarks.
Document type :
Conference papers
Complete list of metadata

Cited literature [57 references]  Display  Hide  Download
Contributor : Josef Sivic <>
Submitted on : Tuesday, January 9, 2018 - 12:04:32 PM
Last modification on : Thursday, July 1, 2021 - 5:58:09 PM
Long-term archiving on: : Wednesday, May 23, 2018 - 4:06:50 PM


Files produced by the author(s)


  • HAL Id : hal-01678686, version 1
  • ARXIV : 1704.02895



Rohit Girdhar, Deva Ramanan, Abhinav Gupta, Josef Sivic, Bryan Russell. ActionVLAD: Learning spatio-temporal aggregation for action classification. IEEE Conference on Computer Vision and Pattern Recognition, 2017, Honolulu, United States. ⟨hal-01678686⟩



Record views


Files downloads