CueKFS: Agentic Cue-Driven Keyframe Selection for Long Video Understanding

arXiv:2609.31873 · cs.CV, cs.AI, cs.CL · Submitted 2026-09-25 · Read on arXiv

cs.CV, cs.AI, cs.CL

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• Accuracy — 14× in this paper · explained in 1 episode
• Benchmark — 8× in this paper · explained in 2 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 6× in this paper
• Ablation Studies — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 2× in this paper
• Wavelet Transform — 2× in this paper · explained in 2 episodes
• Action Groups — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 1× in this paper
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Qwen2.5-VL Technical Report
• HiMu: Hierarchical Multimodal Frame Selection for Long Video Question Answering
• Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding
• FrameOracle: Learning What to See and How Much to See in Videos
• Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding
• KeyVideoLLM: Towards Large-scale Video Keyframe Selection
• BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
• CLIP-It! Language-Guided Video Summarization
• Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval
• MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs
• MSJoE: Jointly Evolving MLLM and Sampler for Efficient Long-Form Video Understanding
• Adaptive Keyframe Sampling for Long Video Understanding
• SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
• Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video Understanding
• Query-Conditioned Evidential Keyframe Sampling for MLLM-Based Long-Form Video Understanding
• LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding
• Generative Frame Sampler for Long Video Understanding
• T*: Re-thinking Temporal Search for Long-Form Video Understanding
• Frame-Voyager: Learning to Query Frames for Video Large Language Models
• Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs

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