Papers › PDAN: Pyramid Dilated Attention Network for Action Detection
PDAN: Pyramid Dilated Attention Network for Action Detection
Rui Dai, Srijan Das, Luca Minciullo, Lorenzo Garattoni, Gianpiero Francesca, Francois Bremond
Handling long and complex temporal information is an important challenge for action detection tasks. This challenge is further aggravated by densely distributed actions in untrimmed videos. Previous action detection methods fail in selecting the key temporal information in long videos. To this end, we introduce the Dilated Attention Layer (DAL). Compared to the previous temporal convolution layer, DAL allocates attentional weights to local frames in the kernel, which enables it to learn better local representation across time. Furthermore, we introduce Pyramid Dilated Attention Network (PDAN) which is built upon DAL. With the help of multiple DALs with different dilation rates, PDAN can model short-term and long-term temporal relations simultaneously by focusing on local segments at the level of low and high temporal receptive fields. This property enables PDAN to handle complex temporal relations between different action instances in long untrimmed videos. To corroborate the effectiveness and robustness of our method, we evaluate it on three densely annotated, multi-label datasets: MultiTHUMOS, Charades, and Toyota Smarthome Untrimmed (TSU) dataset. PDAN is able to outperform previous state-of-the-art methods on all these datasets.
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 Detection | Charades | PDAN (RGB+Flow) | mAP | 26.5 | #5 of 16 | Archive leaderboard | report |
| Action Detection | Multi-THUMOS | PDAN | mAP | 47.6 | #3 of 8 | Archive leaderboard | report |
| Action Detection | TSU | PDAN | Frame-mAP | 32.7 | #1 of 2 | Archive leaderboard | report |
| Temporal Action Localization | MultiTHUMOS | PDAN | Average mAP | 17.3 | #6 of 8 | 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