Learning Salient Boundary Feature for Anchor-free Temporal Action Localization
By Chuming Lin, C. Xu, Donghao Luo, Yabiao Wang, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Yanwei Fu. Computer Vision and Pattern Recognition, 2021
319 citations recorded by the source corpus.
Temporal action localization is an important yet challenging task in video understanding. Typically, such a task aims at inferring both the action category and localization of the start and end frame for each action instance in a long, untrimmed video. While most current models achieve good results by using pre-defined anchors and numerous actionness, such methods could be bothered with both large number of outputs and heavy tuning of locations and sizes corresponding to different anchors. Instead, anchor-free methods is lighter, getting rid of redundant hyper-parameters, but gains few attention. In this paper, we propose the first purely anchor-free temporal localization method, which is both efficient and effective. Our model includes (i) an end-to-end trainable basic predictor, (ii) a saliency-based refinement module to gather more valuable boundary features for each proposal with a novel boundary pooling, and (iii) several consistency constraints to make sure our model can find the accurate boundary given arbitrary proposals. Extensive experiments show that our method beats all anchor-based and actionness-guided methods with a remarkable margin on THUMOS14, achieving state-of-the-art results, and comparable ones on ActivityNet v1.3. Code is available at https://github.com/TencentYoutuResearch/ActionDetection-AFSD.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/d9a447690ba5845cc466f42e96962ee3aee732eb
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Jianxin Wu
- Chen-Lin Zhang
- Yin Li
- Kristen Grauman
- Luc Van Gool
- Ming-Hsuan Yang
- Andrew Zisserman
- Jitendra Malik
Citations in the corpus
- ActionFormer: Localizing Moments of Actions with Transformers (2022, methodology): “Indeed, our formulation follows a minimalist design of sequence labeling by classifying every moment and regressing their action boundaries, previously discussed in [35,78].”