PDAN: Pyramid Dilated Attention Network for Action Detection
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.
PDF AbstractCode
Datasets
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Action Detection | Charades | PDAN (RGB+Flow) | mAP | 26.5 | # 4 | |
Temporal Action Localization | MultiTHUMOS | PDAN | Average mAP | 17.3 | # 5 | |
Action Detection | Multi-THUMOS | PDAN | mAP | 47.6 | # 3 | |
Action Detection | TSU | PDAN | Frame-mAP | 32.7 | # 1 |