Cover Image

METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Mengyue, Chen, Shuo, Kersting, Kristian, Tresp, Volker, Ma, Yunpu
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

VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs
by: Liao, Ruotong, et al.
Published: (2024)

Memory Helps, but Confabulation Misleads: Understanding Streaming Events in Videos with MLLMs
by: Zhang, Gengyuan, et al.
Published: (2025)

OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model
by: Zhou, Xingcheng, et al.
Published: (2025)

When and Where do Events Switch in Multi-Event Video Generation?
by: Liao, Ruotong, et al.
Published: (2025)

LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering
by: Bi, Jinhe, et al.
Published: (2024)

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

StreamingTOM: Streaming Token Compression for Efficient Video Understanding
by: Chen, Xueyi, et al.
Published: (2025)

Dynamic Token Compression for Efficient Video Understanding through Reinforcement Learning
by: Wang, Shida, et al.
Published: (2026)

Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning
by: Ma, Yinchao, et al.
Published: (2026)

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

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

MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
by: Wu, Peiran, et al.
Published: (2025)

FlexSelect: Flexible Token Selection for Efficient Long Video Understanding
by: Zhang, Yunzhu, et al.
Published: (2025)

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

EarlyTom: Early Token Compression Completes Fast Video Understanding
by: Wang, Hesong, et al.
Published: (2026)

DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding
by: Zhang, Hongzhi, et al.
Published: (2025)

All Eyes on the Workflow: Automated and Efficient Event Discovery from Video Streams
by: Pegoraro, Marco, et al.
Published: (2026)

Localizing Events in Videos with Multimodal Queries
by: Zhang, Gengyuan, et al.
Published: (2024)

FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding
by: Cho, Janghoon, et al.
Published: (2025)

Multi-event Video-Text Retrieval
by: Zhang, Gengyuan, et al.
Published: (2023)

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

CacheFlow: Compressive Streaming Memory for Efficient Long-Form Video Understanding
by: Patel, Shrenik, et al.
Published: (2025)

Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding
by: Zhang, Renshan, et al.
Published: (2024)

UniCompress: Token Compression for Unified Vision-Language Understanding and Generation
by: Wang, Ziyao, et al.
Published: (2026)

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

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
by: Shen, Xiaoqian, et al.
Published: (2024)

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

StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding
by: Wang, Junxi, et al.
Published: (2026)

FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding
by: Guo, Yanan, et al.
Published: (2025)

Towards Event-oriented Long Video Understanding
by: Du, Yifan, et al.
Published: (2024)

OmniVLM: A Token-Compressed, Sub-Billion-Parameter Vision-Language Model for Efficient On-Device Inference
by: Chen, Wei, et al.
Published: (2024)

ApET: Approximation-Error Guided Token Compression for Efficient VLMs
by: Ma, Qiankun, et al.
Published: (2026)

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

Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries
by: Amoroso, Roberto, et al.
Published: (2024)

O-MARC: Omni Memory-Augmented Compression Distillation for Efficient Video Understanding
by: Wu, Peiran, et al.
Published: (2026)

Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding
by: Xie, Yuan, et al.
Published: (2025)

StreamForest: Efficient Online Video Understanding with Persistent Event Memory
by: Zeng, Xiangyu, et al.
Published: (2025)

LVC: A Lightweight Compression Framework for Enhancing VLMs in Long Video Understanding
by: Wang, Ziyi, et al.
Published: (2025)

EventPrune: Cascaded Event-Assisted Token Pruning for Efficient First-Person Dynamic Spatial Reasoning
by: Ma, Pengtao, et al.
Published: (2026)

LET-US: Long Event-Text Understanding of Scenes
by: Chen, Rui, et al.
Published: (2025)