ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 15416-15425
Abstract
No abstract availableFunding Information
- National Science Foundation of China (62472375)
- Zhejiang Provincial Natural Science Foundation of China (LD24F020014)
- Zhejiang Provincial Natural Science Foundation of China (LD25F020002)
- Zhejiang Pioneer (Jianbing) Project (2024C01032)
- Ningbo Yongjiang Talent Programme (2023A-198-G)
This publication has 14 references indexed in Scilit:
- Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding2025
- VideoChat: chat-centric video understandingScience China Information Sciences, 2025
- Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis2025
- MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding2024
- MovieChat: From Dense Token to Sparse Memory for Long Video Understanding2024
- VILA: On Pre-training for Visual Language Models2024
- Generative Agents: Interactive Simulacra of Human Behavior2023
- AutoAD: Movie Description in Context2023
- MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition2022
- Is Someone Speaking?2021