Image de couverture de livre

From Frames to Clips: Training-free Adaptive Key Clip Selection for Long-Form Video Understanding

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sun, Guangyu, Singhal, Archit, Uzkent, Burak, Shah, Mubarak, Chen, Chen, Kessler, Garin
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Narrative Aligned Long Form Video Question Answering
par: Jain, Rahul, et autres
Publié: (2026)

Learning to Rank Caption Chains for Video-Text Alignment
par: Blume, Ansel, et autres
Publié: (2026)

Think-Clip-Sample: Slow-Fast Frame Selection for Video Understanding
par: Tan, Wenhui, et autres
Publié: (2026)

Minimal Clips, Maximum Salience: Long Video Summarization via Key Moment Extraction
par: Pennec, Galann, et autres
Publié: (2025)

From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding
par: Wang, Xiangfeng, et autres
Publié: (2025)

Video-GPT via Next Clip Diffusion
par: Zhuang, Shaobin, et autres
Publié: (2025)

Towards Effective Long Video Understanding of Multimodal Large Language Models via One-shot Clip Retrieval
par: Chen, Tao, et autres
Publié: (2025)

RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos
par: Hannan, Tanveer, et autres
Publié: (2023)

CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models
par: Poppi, Tobia, et autres
Publié: (2026)

From Understanding to Engagement: Personalized pharmacy Video Clips via Vision Language Models (VLMs)
par: Mishra, Suyash, et autres
Publié: (2026)

FlexiClip: Locality-Preserving Free-Form Character Animation
par: Khandelwal, Anant
Publié: (2025)

Adaptive Greedy Frame Selection for Long Video Understanding
par: Huang, Yuning, et autres
Publié: (2026)

M-LLM Based Video Frame Selection for Efficient Video Understanding
par: Hu, Kai, et autres
Publié: (2025)

Event-Anchored Frame Selection for Effective Long-Video Understanding
par: Chen, Wang, et autres
Publié: (2026)

IA-CLAHE: Image-Adaptive Clip Limit Estimation for CLAHE
par: Otsuka, Rikuto, et autres
Publié: (2026)

Small Clips, Big Gains: Learning Long-Range Refocused Temporal Information for Video Super-Resolution
par: Zhou, Xingyu, et autres
Publié: (2025)

From Captions to Keyframes: KeyScore for Multimodal Frame Scoring and Video-Language Understanding
par: Lin, Shih-Yao, et autres
Publié: (2025)

SAGE: Structure-Aware Generative Video Transitions between Diverse Clips
par: Kan, Mia, et autres
Publié: (2025)

Feature Clipping for Uncertainty Calibration
par: Tao, Linwei, et autres
Publié: (2024)

Jailbreaking Multimodal Large Language Models using Multi-Clip Video
par: Kang, Choongwon, et autres
Publié: (2026)

Generative Frame Sampler for Long Video Understanding
par: Yao, Linli, et autres
Publié: (2025)

In-Context Learning with Unpaired Clips for Instruction-based Video Editing
par: Liao, Xinyao, et autres
Publié: (2025)

Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding
par: Li, Jialuo, et autres
Publié: (2025)

Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding
par: Chen, Wang, et autres
Publié: (2026)

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

ClipTBP: Clip-Pair based Temporal Boundary Prediction with Boundary-Aware Learning for Moment Retrieval
par: Kim, Ji-Hyeon, et autres
Publié: (2026)

Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion
par: Li, Kunyang, et autres
Publié: (2026)

MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs
par: Sun, Hui, et autres
Publié: (2025)

ClipTTT: CLIP-Guided Test-Time Training Helps LVLMs See Better
par: Nath, Mriganka, et autres
Publié: (2026)

Magic 1-For-1: Generating One Minute Video Clips within One Minute
par: Yi, Hongwei, et autres
Publié: (2025)

One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding
par: Zhang, Zheyu, et autres
Publié: (2026)

Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding
par: Fioresi, Joseph, et autres
Publié: (2025)

Semantic-Clipping: Efficient Vision-Language Modeling with Semantic-Guidedd Visual Selection
par: Li, Bangzheng, et autres
Publié: (2025)

Reasoning over the Behaviour of Objects in Video-Clips for Adverb-Type Recognition
par: Seshadri, Amrit Diggavi, et autres
Publié: (2023)

Spectrum Extraction and Clipping for Implicitly Linear Layers
par: Boroojeny, Ali Ebrahimpour, et autres
Publié: (2024)

KFS-Bench: Comprehensive Evaluation of Key Frame Sampling in Long Video Understanding
par: Li, Zongyao, et autres
Publié: (2025)

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding
par: Huang, De-An, et autres
Publié: (2025)

ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation
par: Li, Shengze, et autres
Publié: (2024)

PackCache: A Training-Free Acceleration Method for Unified Autoregressive Video Generation via Compact KV-Cache
par: Li, Kunyang, et autres
Publié: (2026)

MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding
par: Li, Pengyi, et autres
Publié: (2025)