Query-aligned video frame selection for long video understanding

arXiv:2609.31668 · cs.CV, cs.AI · Submitted 2026-09-15 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-15

Updated: 2026-09-15

Terminology

• Benchmark — 30× in this paper · explained in 2 episodes
• Alignment — 16× in this paper · explained in 1 episode
• Accuracy — 12× in this paper · explained in 1 episode
• Cosine Similarity — 11× in this paper · explained in 3 episodes
• Alignment Scores — 5× in this paper · explained in 1 episode
• Ablation — 4× in this paper · explained in 1 episode
• Ablation study — 3× in this paper · explained in 1 episode
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Model-Agnostic — 3× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Anomaly Recognition — 2× in this paper
• Embeddings — 2× in this paper · explained in 2 episodes
• Topic Reasoning — 2× in this paper
• Vector Representations — 2× in this paper · explained in 2 episodes
• Vision-language models — 2× in this paper · explained in 2 episodes
• Action Count — 1× in this paper
• Action Order — 1× in this paper
• Ego Reasoning — 1× in this paper
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• In International Conference on Learning Representations — 1× in this paper
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Multimodal Inputs — 1× in this paper · explained in 2 episodes

Sources

• VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
• Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
• KeyVideoLLM: Towards Large-scale Video Keyframe Selection
• SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding
• LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
• LLaVA-Video: Video Instruction Tuning With Synthetic Data
• 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