Transformer feature collapse of Temporal Action Detection via Multi-granularity Semantic Enhancement
Authors:
- Xin AnXAXin An
- Peng ZhaoPZPeng Zhao
- Guiqin WangGWGuiqin Wang
- Cong ZhaoCZCong Zhao
- Shusen YangSYShusen Yang
- 8 February 2025
- journal article
- Published by Elsevier in Neurocomputing
- Vol. 626
Abstract
No abstract availableThis publication has 40 references indexed in Scilit:
- Attention-guided multi-granularity fusion model for video summarizationExpert Systems with Applications, 2024
- Self-attention-based long temporal sequence modeling method for temporal action detectionNeurocomputing, 2023
- ReAct: Temporal Action Detection with Relational Queries2022
- An Efficient Spatio-Temporal Pyramid Transformer for Action Detection2022
- TallFormer: Temporal Action Localization with a Long-Memory Transformer2022
- Human Action Recognition and Prediction: A SurveyInternational Journal of Computer Vision, 2022
- Bottom-Up Temporal Action Localization with Mutual Regularization2020
- Diagnosing Error in Temporal Action Detectors2018
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017
- ActivityNet: A large-scale video benchmark for human activity understanding2015