Cover Image

FlexSelect: Flexible Token Selection for Efficient Long Video Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yunzhu, Lu, Yu, Wang, Tianyi, Rao, Fengyun, Yang, Yi, Zhu, Linchao
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment
by: Suo, Yucheng, et al.
Published: (2025)

GPD: Guided Progressive Distillation for Fast and High-Quality Video Generation
by: Liang, Xiao, et al.
Published: (2026)

HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization
by: Zhou, Zitang, et al.
Published: (2025)

FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention
by: Lu, Yu, et al.
Published: (2024)

OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding
by: Zhao, Ruixiang, et al.
Published: (2026)

One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding
by: Zhang, Zheyu, et al.
Published: (2026)

Combating Label Noise With A General Surrogate Model For Sample Selection
by: Liang, Chao, et al.
Published: (2023)

VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization
by: Atanov, Andrei, et al.
Published: (2026)

FOCUS: Efficient Keyframe Selection for Long Video Understanding
by: Zhu, Zirui, et al.
Published: (2025)

AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding
by: Qi, Haozhe, et al.
Published: (2026)

STORM: Token-Efficient Long Video Understanding for Multimodal LLMs
by: Jiang, Jindong, et al.
Published: (2025)

DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval
by: Yang, Xiangpeng, et al.
Published: (2024)

VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing
by: Yang, Xiangpeng, et al.
Published: (2025)

Video Token Merging for Long-form Video Understanding
by: Lee, Seon-Ho, et al.
Published: (2024)

EVA: Zero-shot Accurate Attributes and Multi-Object Video Editing
by: Yang, Xiangpeng, et al.
Published: (2024)

FlexTraj: Image-to-Video Generation with Flexible Point Trajectory Control
by: Zhang, Zhiyuan, et al.
Published: (2025)

Context-Aware Token Selection and Packing for Enhanced Vision Transformer
by: Zhang, Tianyi, et al.
Published: (2024)

KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs
by: Song, Baiyang, et al.
Published: (2026)

D-ORCA: Dialogue-Centric Optimization for Robust Audio-Visual Captioning
by: Tang, Changli, et al.
Published: (2026)

Adaptive Greedy Frame Selection for Long Video Understanding
by: Huang, Yuning, et al.
Published: (2026)

MVP: Multiple View Prediction Improves GUI Grounding
by: Zhang, Yunzhu, et al.
Published: (2025)

Event-Anchored Frame Selection for Effective Long-Video Understanding
by: Chen, Wang, et al.
Published: (2026)

TokenMotion: Motion-Guided Vision Transformer for Video Camouflaged Object Detection Via Learnable Token Selection
by: Yu, Zifan, et al.
Published: (2023)

TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning
by: Luo, Siqi, et al.
Published: (2025)

Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding
by: Chen, Wang, et al.
Published: (2026)

METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding
by: Wang, Mengyue, et al.
Published: (2025)

AudioScenic: Audio-Driven Video Scene Editing
by: Shen, Kaixin, et al.
Published: (2024)

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
by: Song, Enxin, et al.
Published: (2023)

FlexPara: Flexible Neural Surface Parameterization
by: Zhao, Yuming, et al.
Published: (2025)

MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs
by: Xu, Yunqiu, et al.
Published: (2024)

FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding
by: Huang, De-An, et al.
Published: (2025)

FlexEControl: Flexible and Efficient Multimodal Control for Text-to-Image Generation
by: He, Xuehai, et al.
Published: (2024)

Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding
by: Liu, Xiangrui, et al.
Published: (2025)

Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models
by: Chen, Yuxiao, et al.
Published: (2026)

$\text{PKS}^4$:Parallel Kinematic Selective State Space Scanners for Efficient Video Understanding
by: Zeng, Lingjie, et al.
Published: (2026)

FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusion
by: Lu, Yu, et al.
Published: (2025)

SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding
by: Xu, Mingze, et al.
Published: (2025)

Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding
by: Hu, Pengfei, et al.
Published: (2025)

Principles of Visual Tokens for Efficient Video Understanding
by: Hao, Xinyue, et al.
Published: (2024)

Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations
by: Zhang, Xu, et al.
Published: (2023)