CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning
arXiv:2103.16392
Abstract
Weakly-supervised temporal action localization (WS-TAL) aims to localize actions in untrimmed videos with only video-level labels. Most existing models follow the "localization by classification" procedure: locate temporal regions contributing most to the video-level classification. Generally, they process each snippet (or frame) individually and thus overlook the fruitful temporal context relation. Here arises the single snippet cheating issue: "hard" snippets are too vague to be classified. In this paper, we argue that learning by comparing helps identify these hard snippets and we propose to utilize snippet Contrastive learning to Localize Actions, CoLA for short. Specifically, we propose a Snippet Contrast (SniCo) Loss to refine the hard snippet representation in feature space, which guides the network to perceive precise temporal boundaries and avoid the temporal interval interruption. Besides, since it is infeasible to access frame-level annotations, we introduce a Hard Snippet Mining algorithm to locate the potential hard snippets. Substantial analyses verify that this mining strategy efficaciously captures the hard snippets and SniCo Loss leads to more informative feature representation. Extensive experiments show that CoLA achieves state-of-the-art results on THUMOS'14 and ActivityNet v1.2 datasets. CoLA code is publicly available at https://github.com/zhang-can/CoLA.
arXiv commentaccepted by CVPR 2021, typos corrected, code link added
References in corpus (9)
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- A Simple Framework for Contrastive Learning of Visual Representations
- Data-Efficient Image Recognition with Contrastive Predictive Coding
- The THUMOS Challenge on Action Recognition for Videos "in the Wild"
- Contrastive Multiview Coding
- Supervised Contrastive Learning
- Marginalized Average Attentional Network for Weakly-Supervised Learning
- Weakly Supervised Action Localization by Sparse Temporal Pooling Network
- Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector