End-to-end dense video grounding via parallel regression
Authors:
- Fengyuan ShiFSFengyuan Shi
- Weilin HuangWHWeilin Huang
- Limin WangLWLimin Wang
- 7 March 2024
- journal article
- research article
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 242
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2022ZD0160900)
- National Natural Science Foundation of China (62076119)
This publication has 34 references indexed in Scilit:
- Hierarchical Semantic Correspondence Networks for Video Paragraph Grounding2023
- Semi-supervised Video Paragraph Grounding with Contrastive Encoder2022
- Masked Autoencoders Are Scalable Vision Learners2022
- Learning to combine the modalities of language and video for temporal moment localizationComputer Vision and Image Understanding, 2022
- Cascaded Prediction Network via Segment Tree for Temporal Video Grounding2021
- Context-aware Biaffine Localizing Network for Temporal Sentence Grounding2021
- Dense Regression Network for Video Grounding2020
- MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment2019
- BSN: Boundary Sensitive Network for Temporal Action Proposal Generation2018
- Deep Residual Learning for Image Recognition2016