arXiv Computer Vision
Beyond Frame Selection: Rethinking Long-Video Understanding with MLLMs
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
Aug 6
Beyond Frame Selection: Rethinking Long-Video Understanding with MLLMs
Multimodal Large Language Models (MLLMs) have achieved strong progress in video understanding, yet it remains challenging because the token limitation makes MLLMs difficult to capture temporally sparse evidence. Existing methods typically rely on uniform sampling, or frame selection, but these strategies usually optimize either broad temporal coverage or local relevance, making it difficult to preserve both global storyline context and fine-grained evidence.
arXiv Computer Vision
Aug 31
Temporal Tree of Thought: Reasoning-Guided Visual Cue Search for Long-Video Understanding
arXiv:2608.27871v1 Announce Type: new Abstract: Long-video understanding remains challenging for Multimodal Large Language Models (MLLMs) due to limited context length. Uniform sampling may miss cruc...
arXiv AI
Aug 25
Coarse Indexing, Fine Evidence: Decoupling Temporal Granularity in Long-Video RAG
arXiv:2608.23011v1 Announce Type: cross Abstract: Graph-based retrieval-augmented generation (RAG) provides a scalable paradigm for long-video understanding, but existing systems typically inherit a...
arXiv AI
Jun 29
HiMu: Hierarchical Multimodal Frame Selection for Long Video Question Answering
arXiv:2603. 18558v2 Announce Type: replace-cross Abstract: Long-form video question answering requires reasoning over extended temporal contexts, making frame selection a critical bottleneck for multi-modal large language models (MLLMs) bound by finite context windows.
arXiv Machine Learning
Aug 28
Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos
The paper introduces PACE, a factor-guided, progressive framework for acquiring evidence in long-video question answering. PACE first indexes clip-level descriptions using question-derived factors, then refines evidence retrieval with contrastive cues derived from candidate answers. On the MMR‑V dataset, PACE achieves 42.6% accuracy and recovers 66.9% of annotated cues, outperforming direct inference and prior agentic baselines, and shows consistent improvements across several long-video benchmarks.
arXiv AI
Jul 29
Reasoning with Memory: A Temporal Granularity-Adaptive Framework for Training-Free Long Video Understanding
arXiv:2607. 24794v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) demonstrate superior generalization in fundamental video tasks, restricted context windows limit their long video understanding.