MarKey: Marginal Utility Guided Greedy Keyframe Selection for Long Video Understanding

arXiv:2609.15408 · cs.CV, cs.CL · Submitted 2026-09-14 · Read on arXiv

cs.CV, cs.CL

Submitted: 2026-09-14

Updated: 2026-09-14

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

Terminology

• Benchmark — 42× in this paper · explained in 2 episodes
• Redundancy — 41× in this paper · explained in 2 episodes
• Accuracy — 19× in this paper · explained in 1 episode
• Ablation — 8× in this paper · explained in 1 episode
• Cosine Similarity — 6× in this paper · explained in 3 episodes
• Embeddings — 5× in this paper · explained in 2 episodes
• Instruction Tuning — 4× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Training-Free Framework — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Abstraction — 2× in this paper · explained in 1 episode
• Aggregation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Generalizability — 2× in this paper · explained in 6 episodes
• RAG — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Temporal Reasoning — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Comparison of Mean Pairwise Cosine Similarity — 1× in this paper
• Contextual Understanding — 1× in this paper · explained in 2 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Instance Segmentation — 1× in this paper · explained in 3 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models
• LongVILA: Scaling Long-Context Visual Language Models for Long Videos
• EmoBench-M: Benchmarking Emotional Intelligence for Multimodal Large Language Models
• MMHBench: A Multi-Perspective Benchmark for Mental Health Understanding in Long-Form Videos
• VidCompress: Memory-Enhanced Temporal Compression for Video Understanding in Large Language Models
• ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding
• LLaVA-OneVision: Easy Visual Task Transfer
• Aria: An Open Multimodal Native Mixture-of-Experts Model
• LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
• Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input
• PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
• mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
• Frame-Voyager: Learning to Query Frames for Video Large Language Models
• Zelda: Video Analytics using Vision-Language Models
• LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
• Gemini: A Family of Highly Capable Multimodal Models
• Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

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