Image de couverture de livre

K-frames: Scene-Driven Any-k Keyframe Selection for long video understanding

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yao, Yifeng, Yun, Yike, Wang, Jing, Zhang, Huishuai, Zhao, Dongyan, Tian, Ke, Wang, Zhihao, Qiu, Minghui, Wang, Tao
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

FREAK: A Fine-grained Hallucination Evaluation Benchmark for Advanced MLLMs
par: Yin, Zhihan, et autres
Publié: (2026)

Evidence-Enhanced Triplet Generation Framework for Hallucination Alleviation in Generative Question Answering
par: Du, Haowei, et autres
Publié: (2024)

ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models
par: Wang, Yueqian, et autres
Publié: (2025)

Understanding Multimodal Hallucination with Parameter-Free Representation Alignment
par: Wang, Yueqian, et autres
Publié: (2024)

Koala: Key frame-conditioned long video-LLM
par: Tan, Reuben, et autres
Publié: (2024)

CrossCheck-Bench: Diagnosing Compositional Failures in Multimodal Conflict Resolution
par: Tian, Baoliang, et autres
Publié: (2025)

ReasVQA: Advancing VideoQA with Imperfect Reasoning Process
par: Liang, Jianxin, et autres
Publié: (2025)

Adaptive Keyframe Selection for Scalable 3D Scene Reconstruction in Dynamic Environments
par: Jha, Raman, et autres
Publié: (2025)

Motion Keyframe Interpolation for Any Human Skeleton via Temporally Consistent Point Cloud Sampling and Reconstruction
par: Mo, Clinton, et autres
Publié: (2024)

Anything in Any Scene: Photorealistic Video Object Insertion
par: Bai, Chen, et autres
Publié: (2024)

Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA
par: Liang, Jianxin, et autres
Publié: (2025)

VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format
par: Wang, Yueqian, et autres
Publié: (2024)

MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning
par: Wang, Yueqian, et autres
Publié: (2025)

KeyframeFace: Language-Driven Facial Animation via Semantic Keyframes
par: Wu, Jingchao, et autres
Publié: (2025)

Placing Human Animations into 3D Scenes by Learning Interaction- and Geometry-Driven Keyframes
par: Mullen Jr, James F., et autres
Publié: (2022)

Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes
par: Gong, Zhuocheng, et autres
Publié: (2025)

Efficient Continual Pre-training by Mitigating the Stability Gap
par: Guo, Yiduo, et autres
Publié: (2024)

Adaptive Keyframe Sampling for Long Video Understanding
par: Tang, Xi, et autres
Publié: (2025)

SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents
par: Yuan, Danlong, et autres
Publié: (2026)

ReMamba: Equip Mamba with Effective Long-Sequence Modeling
par: Yuan, Danlong, et autres
Publié: (2024)

xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
par: Cheng, Xin, et autres
Publié: (2024)

HorizonForge: Driving Scene Editing with Any Trajectories and Any Vehicles
par: Wang, Yifan, et autres
Publié: (2026)

Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video Understanding
par: Wang, Shaoguang, et autres
Publié: (2026)

CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition
par: Phung, Quynh, et autres
Publié: (2025)

Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing
par: Liu, Lin, et autres
Publié: (2026)

Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale
par: Wei, Dongxu, et autres
Publié: (2026)

The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injection
par: He, Qingdong, et autres
Publié: (2025)

Submodular Optimization for Keyframe Selection & Usage in SLAM
par: Thorne, David, et autres
Publié: (2024)

KeyVideoLLM: Towards Large-scale Video Keyframe Selection
par: Liang, Hao, et autres
Publié: (2024)

Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation Training
par: Gao, Ziqi, et autres
Publié: (2024)

KeySG: Hierarchical Keyframe-Based 3D Scene Graphs
par: Werby, Abdelrhman, et autres
Publié: (2025)

ClipGStream: Clip-Stream Gaussian Splatting for Any Length and Any Motion Multi-View Dynamic Scene Reconstruction
par: Liang, Jie, et autres
Publié: (2026)

Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models
par: Wang, Haoxiang, et autres
Publié: (2026)

OLion: Approaching the Hadamard Ideal by Intersecting Spectral and $\ell_{\infty}$ Implicit Biases
par: Wang, Zixiao, et autres
Publié: (2026)

AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training
par: Zhang, Huishuai, et autres
Publié: (2025)

FOCUS: Efficient Keyframe Selection for Long Video Understanding
par: Zhu, Zirui, et autres
Publié: (2025)

Gradient Descent with Polyak's Momentum Finds Flatter Minima via Large Catapults
par: Phunyaphibarn, Prin, et autres
Publié: (2023)

Shorten After You're Right: Lazy Length Penalties for Reasoning RL
par: Yuan, Danlong, et autres
Publié: (2025)

KFFocus: Highlighting Keyframes for Enhanced Video Understanding
par: Nie, Ming, et autres
Publié: (2025)

AdaRD-key: Adaptive Relevance-Diversity Keyframe Sampling for Long-form Video understanding
par: Zhang, Xian, et autres
Publié: (2025)