IEEE Transactions on Image Processing · 2022 · 24 citations · 60 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningAction RecognitionAction RepresentationDeep LearningRepresentation LearningAction DetectionCompact Feature EncodingLabelsLearned Feature RepresentationsTemporal Action LocalizationWeakly Supervised Action Recognition
Point-level weakly-supervised temporal action localization (P-WSTAL) aims to localize temporal extents of action instances and identify the corresponding categories with only a single point label for each action instance for training. Due to the sparse frame-level annotations, most existing models are in the localization-by-classification pipeline. However, there exist two major issues in this pipeline: large intra-action variation due to task gap between classification and localization and noisy classification learning caused by unreliable pseudo training samples. In this paper, we propose a novel framework CRRC-Net, which introduces a co-supervised feature learning module and a probabilistic pseudo label mining module, to simultaneously address the above two issues. Specifically, the co-supervised feature learning module is applied to exploit the complementary information in different modalities for learning more compact feature representations. Furthermore, the probabilistic pseudo label mining module utilizes the feature distances from action prototypes to estimate the likelihood of pseudo samples and rectify their corresponding labels for more reliable classification learning. Comprehensive experiments are conducted on different benchmarks and the experimental results show that our method achieves favorable performance with the state-of-the-art.
60
Learning realistic human actions from movies
Ivan Laptev, Marcin Marszałek, Cordelia Schmid et al. · 2008 · 3.5K citations · Full text
Rethinking the Faster R-CNN Architecture for Temporal Action Localization
Yu-Wei Chao, Sudheendra Vijayanarasimhan, Bryan Seybold et al. · 2018 · 763 citations
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
Tianwei Lin, Xiao Liu, Xin Li et al. · 2019 · 624 citations