Sub-action Prototype Learning for Point-level Weakly-supervised Temporal Action Localization
Point-level weakly-supervised temporal action localization (PWTAL) aims to localize actions with only a single timestamp annotation for each action instance. Existing methods tend to mine dense pseudo labels to alleviate the label sparsity, but overlook the potential sub-action temporal structures, resulting in inferior performance. To tackle this problem, we propose a novel sub-action prototype learning framework (SPL-Loc) which comprises Sub-action Prototype Clustering (SPC) and Ordered Prototype Alignment (OPA). SPC adaptively extracts representative sub-action prototypes which are capable to perceive the temporal scale and spatial content variation of action instances. OPA selects relevant prototypes to provide completeness clue for pseudo label generation by applying a temporal alignment loss. As a result, pseudo labels are derived from alignment results to improve action boundary prediction. Extensive experiments on three popular benchmarks demonstrate that the proposed SPL-Loc significantly outperforms existing SOTA PWTAL methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Action LocalizationPseudo LabelTemporal Action LocalizationWeakly-supervised Temporal Action LocalizationSimilar Papers 제목 키워드 기반
Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learning
Addressing the annotation challenge in 3D Point Cloud segmentation has inspired research into weakly supervised learning. Existing approaches mainly focus on exploiting manifold and pseudo-labeling to make use of large u…
Point Cloud SegmentationSegmentationWeakly Supervised 3D Point Cloud SegmentationWeakly-supervised LearningPrototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation
Weakly supervised image segmentation with image-level labels has drawn attention due to the high cost of pixel-level annotations. Traditional methods using Class Activation Maps (CAMs) often highlight only the most d…
Contrastive LearningImage SegmentationSegmentationSemantic Segmentation+1Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation
Log anomaly detection is a critical task for system operations and security assurance. However, in networked systems at scale, log data are generated at massive scale while instance-level annotations are prohibitively ex…
Anomaly DetectionWeakly Supervised Semantic Segmentation for Large-Scale Point Cloud
Existing methods for large-scale point cloud semantic segmentation require expensive, tedious and error-prone manual point-wise annotations. Intuitively, weakly supervised training is a direct solution to reduce the cost…
ColorizationPseudo LabelSelf-Supervised LearningSemantic Segmentation+2Finding Meaning in Points: Weakly Supervised Semantic Segmentation for Event Cameras
Event cameras excel in capturing high-contrast scenes and dynamic objects, offering a significant advantage over traditional frame-based cameras. Despite active research into leveraging event cameras for semantic segment…
Contrastive LearningSegmentationSemantic SegmentationWeakly supervised Semantic Segmentation+1