Papers › EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video...
EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition
Ahmed Abdelkawy, Asem Ali, Aly Farag
Existing multimodal-based human action recognition approaches are either computationally expensive, which limits their applicability in real-time scenarios, or fail to exploit the spatial temporal information of multiple data modalities. In this work, we present an efficient pose-driven attention-guided multimodal network (EPAM-Net) for action recognition in videos. Specifically, we adapted X3D networks for both RGB and pose streams to capture spatio-temporal features from RGB videos and their skeleton sequences. Then skeleton features are utilized to help the visual network stream focusing on key frames and their salient spatial regions using a spatial temporal attention block. Finally, the scores of the two streams of the proposed network are fused for final classification. The experimental results show that our method achieves competitive performance on NTU-D 60 and NTU RGB-D 120 benchmark datasets. Moreover, our model provides a 6.2--9.9x reduction in FLOPs (floating-point operation, in number of multiply-adds) and a 9--9.6x reduction in the number of network parameters. The code will be available at https://github.com/ahmed-nady/Multimodal-Action-Recognition.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Action Classification | Toyota Smarthome dataset | EPAM-Net | CS | 71.7 | #2 of 13 | Archive leaderboard | report |
| Action Classification | Toyota Smarthome dataset | EPAM-Net | CV2 | 67.8 | #2 of 13 | Archive leaderboard | report |
| Action Recognition | NTU RGB+D | EPAM-Net | Accuracy (CS) | 96.1 | #5 of 28 | Archive leaderboard | report |
| Action Recognition | NTU RGB+D | EPAM-Net | Accuracy (CV) | 99.0 | #5 of 28 | Archive leaderboard | report |
| Action Recognition | NTU RGB+D 120 | EPAM-Net | Accuracy (Cross-Setup) | 92.4 | #7 of 21 | Archive leaderboard | report |
| Action Recognition | NTU RGB+D 120 | EPAM-Net | Accuracy (Cross-Subject) | 94.3 | #7 of 21 | Archive leaderboard | report |
| Action Recognition In Videos | PKU-MMD | EPAM-Net | X-Sub | 96.2 | #3 of 5 | Archive leaderboard | report |
| Action Recognition In Videos | PKU-MMD | EPAM-Net | X-View | 98.4 | #3 of 5 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections