EventLens: Event-Aware Hierarchical Evidence Construction for Long-Video Understanding
- 1 November 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (11) , 17510-17524
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62176144)
- Fundamental Research Project of Shandong, China (ZR2024ZD08)
- Undergraduate Education Reform Project of Shandong Province (Z202450)
This publication has 29 references indexed in Scilit:
- VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos2025
- Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis2025
- BOLT: Boost Large Vision-Language Model Without Training for Long-Form Video Understanding2025
- DrVideo: Document Retrieval Based Long Video Understanding2025
- NVILA: Efficient Frontier Visual Language Models2025
- MLVU: Benchmarking Multi-task Long Video Understanding2025
- Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding2025
- Re-thinking Temporal Search for Long-Form Video Understanding2025
- Adaptive Keyframe Sampling for Long Video Understanding2025
- VideoAgent: Long-Form Video Understanding with Large Language Model as Agent2024