EC-RAG: Event Chain Retrieval-Augmented Generation for Long Video Understanding

arXiv:2610.08674 · cs.CV · Submitted 2026-10-06 · Read on arXiv

cs.CV

Submitted: 2026-10-06

Updated: 2026-10-06

Comments: 12 pages, 7 figures, 7 tables, including supplementary material

Code: https://github.com/JaidedAI/EasyOCR

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• RAG — 1× in this paper · explained in 3 episodes

Sources

• Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos
• Unsupervised Dense Information Retrieval with Contrastive Learning
• Aria: An Open Multimodal Native Mixture-of-Experts Model
• MM-VID: Advancing Video Understanding with GPT-4V(ision)
• Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution
• Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension
• Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner
• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
• PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
• AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding
• Long Context Transfer from Language to Vision
• LLaVA-Video: Video Instruction Tuning With Synthetic Data
• Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models
• MLVU: Benchmarking Multi-task Long Video Understanding

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models