Learning Motion in Feature Space:
Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection

Khoi-Nguyen C. Mac,   Dhiraj Joshi,   Raymond A. Yeh,   Jinjun Xiong,   Rogerio S. Feris,   Minh N. Do

Abstract

Fine-grained action detection is an important task with numerous applications in robotics and human-computer interaction. Existing methods typically utilize a two-stage approach including extraction of local spatio-temporal features followed by temporal modeling to capture long-term dependencies. While most recent papers have focused on the latter (long-temporal modeling), here, we focus on producing features capable of modeling fine-grained motion more efficiently. We propose a novel locally-consistent deformable convolution, which utilizes the change in receptive fields and enforces a local coherency constraint to capture motion information effectively. Our model jointly learns spatio-temporal features (instead of using independent spatial and temporal streams). The temporal component is learned from the feature space instead of pixel space, e.g. optical flow. The produced features can be flexibly used in conjunction with other long-temporal modeling networks, e.g. ST-CNN, DilatedTCN, and ED-TCN. Overall, our proposed approach robustly outperforms the original long-temporal models on two fine-grained action datasets: 50 Salads and GTEA, achieving F1 scores of 80.22% and 75.39% respectively.

(Accepted as an oral paper at ICCV'2019.)

Oral Presentation

Materials

[CVF] [arXiv] Poster Slides Code

Supplementary Materials

Supplementary
Materials
Slides
(Extended)
Demo - 50 Salads Demo - GTEA

Citation

@InProceedings{Mac_2019_ICCV,
    author    = {Mac, Khoi-Nguyen C. and 
                 Joshi, Dhiraj and 
                 Yeh, Raymond A. and 
                 Xiong, Jinjun and 
                 Feris, Rogerio S. and 
                 Do, Minh N.},
    title     = {Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection},
    booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2019}
}