IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023 · 72 citations · 66 references
ComputingComputer ScienceComputer VisionKnowledge RepresentationMachine LearningAction RecognitionAction RepresentationDeep LearningPattern RecognitionRepresentation LearningAction DetectionModel Performance AnalysisModel Performance EvaluationTemporal Action LocalizationWeak SupervisionWeakly Supervised Action Recognition
With the explosive growth of videos, weakly-supervised temporal action localization (WS-TAL) task has become a promising research direction in pattern analysis and machine learning. WS-TAL aims to detect and localize action instances with only video-level labels during training. Modern approaches have achieved impressive progress via powerful deep neural networks. However, robust and reliable WS-TAL remains challenging and underexplored due to considerable uncertainty caused by weak supervision, noisy evaluation environment, and unknown categories in the open world. To this end, we propose a new paradigm, named vectorized evidential learning (VEL), to explore local-to-global evidence collection for facilitating model performance. Specifically, a series of learnable meta-action units (MAUs) are automatically constructed, which serve as fundamental elements constituting diverse action categories. Since the same meta-action unit can manifest as distinct action components within different action categories, we leverage MAUs and category representations to dynamically and adaptively learn action components and action-component relations. After performing uncertainty estimation at both category-level and unit-level, the local evidence from action components is accumulated and optimized under the Subject Logic theory. Extensive experiments on the regular, noisy, and open-set settings of three popular benchmarks show that VEL consistently obtains more robust and reliable action localization performance than state-of-the-arts.
66
The Kinetics Human Action Video Dataset
Will Kay, João Carreira, Karen Simonyan et al. · arXiv (Cornell University) · 2017 · 2.9K citations · Full text
ActivityNet: A large-scale video benchmark for human activity understanding
Fabian Caba Heilbron, Víctor Escorcia, Bernard Ghanem et al. · 2015 · 2.6K citations