LongVLM: Efficient Long Video Understanding via Large Language Models
Top Cited Papers
- 25 October 2024
- book chapter
- Published by Springer Nature
- p. 453-470
Abstract
No abstract availableKeywords
All Related Versions
This publication has 37 references indexed in Scilit:
- Towards Long-Form Video Understanding2021
- Temporal Aggregate Representations for Long-Range Video Understanding2020
- Long-Term Feature Banks for Detailed Video Understanding2019
- Timeception for Complex Action Recognition2019
- Temporal Relational Reasoning in Videos2018
- Learning Dynamic Memory Networks for Object Tracking2018
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition2016
- MSR-VTT: A Large Video Description Dataset for Bridging Video and Language2016
- Long-term recurrent convolutional networks for visual recognition and description2015
- ActivityNet: A large-scale video benchmark for human activity understanding2015