Connecting Words to Motion: Unleashing Video Highlights and Moments Through Cross Attention Temporal Grounding
- 30 November 2024
- book chapter
- Published by Springer Nature
- p. 91-100
Abstract
No abstract availableKeywords
This publication has 28 references indexed in Scilit:
- Less is More: CLIPBERT for Video-and-Language Learning via Sparse Sampling2021
- MINI-Net: Multiple Instance Ranking Network for Video Highlight Detection2020
- TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval2020
- Local-Global Video-Text Interactions for Temporal Grounding2020
- Less Is More: Learning Highlight Detection From Video Duration2019
- MSR-VTT: A Large Video Description Dataset for Bridging Video and Language2016
- ActivityNet: A large-scale video benchmark for human activity understanding2015
- TVSum: Summarizing web videos using titles2015
- Ranking Domain-Specific Highlights by Analyzing Edited Videos2014
- Discovering important people and objects for egocentric video summarization2012