arXiv Computer Vision
Routing Before Looking: Query-Adaptive Evidence Acquisition for Long-form Video Understanding
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 1
From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for Long-Video Agents
arXiv:2608.31005v1 Announce Type: new Abstract: Existing long-video agents acquire evidence through one uniform behavior, ignoring whether the required evidence is concentrated, requires broad occurr...
arXiv AI
Aug 11
Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding
arXiv:2608. 07663v1 Announce Type: cross Abstract: When videos extend from hours to days, directly processing them end-to-end becomes impractical for current Multi-modal Large Language Models (MLLMs).
arXiv Computer Vision
Sep 10
Beyond Frame Selection: Rethinking Long-Video Understanding with MLLMs
arXiv:2608.05592v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have made strong progress in video understanding, yet long videos remain difficult: the visual token budge...
arXiv Computer Vision
Oct 7
EC-RAG: Event Chain Retrieval-Augmented Generation for Long Video Understanding
arXiv:2610.08674v1 Announce Type: new Abstract: Current large video-language models (LVLMs) still face challenges when dealing with long videos, mainly because frames are often processed independentl...
arXiv AI
Aug 20
Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios
Event-Causal RAG (EC‑RAG) is a lightweight retrieval‑augmented framework designed for reasoning over ultra‑long and streaming videos. It segments video streams into semantically complete events using a dual visual‑audio sentinel mechanism, representing each event as a State‑Event‑State (SES) structure that captures pre‑event, event, and post‑event states. During question answering, bidirectional graph retrieval accesses relevant predecessor and successor events from a dual vector‑graph memory, and answers are generated using both this structured memory and the corresponding video evidence. The authors also introduce ECV‑1H, an hour‑scale long‑video QA benchmark with over 150 hours of untrimmed video and 1,251 human‑annotated QA pairs, where EC‑RAG achieves significant accuracy gains across multiple video foundation models while maintaining efficient streaming memory usage on a single RTX 5090 GPU.
arXiv AI
Aug 25
Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents
arXiv:2608.23329v1 Announce Type: cross Abstract: Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video a...