Towards class-incremental open-set scenarios for video-based action recognition
- 22 August 2026
- journal article
- Published by Elsevier in Neural Networks
- Vol. 205 (Pt B) , 109529
Abstract
No abstract availableKeywords
Funding Information
- Natural Science Foundation of Sichuan Province (2026NSFSC0418)
- Tangshan Science and Technology Bureau
- National Natural Science Foundation of China (62576296)
- Fundamental Research Funds for the Central Universities (2682025ZTPY052)
This publication has 14 references indexed in Scilit:
- EAAR: Efficient and Accurate Action Recognition model with enhanced spatio-temporal perceptionNeural Networks, 2025
- Background debiased class incremental learning for video action recognitionImage and Vision Computing, 2024
- Rethinking Few-Shot Class-Incremental Learning With Open-Set Hypothesis in Hyperbolic GeometryIEEE Transactions on Multimedia, 2023
- Exploring Rich Semantics for Open-Set Action RecognitionIEEE Transactions on Multimedia, 2023
- OpenMix+: Revisiting Data Augmentation for Open Set RecognitionIEEE Transactions on Circuits and Systems for Video Technology, 2023
- Spatial-Temporal Exclusive Capsule Network for Open Set Action RecognitionIEEE Transactions on Multimedia, 2023
- Spatial location constraint prototype loss for open set recognitionComputer Vision and Image Understanding, 2023
- Motion-Driven Spatial and Temporal Adaptive High-Resolution Graph Convolutional Networks for Skeleton-Based Action RecognitionIEEE Transactions on Circuits and Systems for Video Technology, 2022
- Dense Semantics-Assisted Networks for Video Action RecognitionIEEE Transactions on Circuits and Systems for Video Technology, 2021
- VII. Mathematical contributions to the theory of evolution.—III. Regression, heredity, and panmixiaPhilosophical Transactions of the Royal Society A, 1896