Imagen de Portada

VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ding, Yang, Zhang, Yizhen, Lai, Xin, Chu, Ruihang, Yang, Yujiu
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing
por: Chen, Yuqing, et al.
Publicado: (2025)

Zoomer: Adaptive Image Focus Optimization for Black-box MLLM
por: Qian, Jiaxu, et al.
Publicado: (2025)

From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning
por: Luo, Ruilin, et al.
Publicado: (2026)

Generative Universal Verifier as Multimodal Meta-Reasoner
por: Zhang, Xinchen, et al.
Publicado: (2025)

PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning
por: Zhang, Yizhen, et al.
Publicado: (2025)

Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understanding
por: Chen, Houlun, et al.
Publicado: (2026)

TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning
por: Pan, Junwen, et al.
Publicado: (2025)

The Devil is in Temporal Token: High Quality Video Reasoning Segmentation
por: Gong, Sitong, et al.
Publicado: (2025)

Video-Zero: Self-Evolution Video Understanding
por: Zhang, Ruixu, et al.
Publicado: (2026)

Tempo-R0: A Video-MLLM for Temporal Video Grounding through Efficient Temporal Sensing Reinforcement Learning
por: Yue, Feng, et al.
Publicado: (2025)

Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning
por: Chen, Ruizhe, et al.
Publicado: (2025)

Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events
por: Liu, Xiaolin, et al.
Publicado: (2026)

TimeScope: Towards Task-Oriented Temporal Grounding In Long Videos
por: Liu, Xiangrui, et al.
Publicado: (2025)

UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding
por: Tang, Fei, et al.
Publicado: (2026)

Video-Infinity: Distributed Long Video Generation
por: Tan, Zhenxiong, et al.
Publicado: (2024)

Mitigating the Reasoning Tax in Vision-Language Fine-Tuning with Input-Adaptive Depth Aggregation
por: Ren, Yiming, et al.
Publicado: (2026)

PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning
por: Zhao, Yusong, et al.
Publicado: (2026)

Space-time Reinforcement Network for Video Object Segmentation
por: Chen, Yadang, et al.
Publicado: (2024)

Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks
por: Yang, Cheng, et al.
Publicado: (2025)

Iterative Zoom-In: Temporal Interval Exploration for Long Video Understanding
por: Li, Chenglin, et al.
Publicado: (2025)

DeepSport: A Multimodal Large Language Model for Comprehensive Sports Video Reasoning via Agentic Reinforcement Learning
por: Zou, Junbo, et al.
Publicado: (2025)

VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG
por: Fu, Honghao, et al.
Publicado: (2026)

ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning
por: Li, Yifan, et al.
Publicado: (2025)

VCA: Video Curious Agent for Long Video Understanding
por: Yang, Zeyuan, et al.
Publicado: (2024)

Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning
por: Li, Jiazheng, et al.
Publicado: (2026)

AdaFocus: Adaptive Relevance-Diversity Sampling with Zero-Cache Look-back for Efficient Long Video Understanding
por: Yang, Xiao, et al.
Publicado: (2026)

VRBench: A Benchmark for Multi-Step Reasoning in Long Narrative Videos
por: Yu, Jiashuo, et al.
Publicado: (2025)

Learning Local and Global Temporal Contexts for Video Semantic Segmentation
por: Sun, Guolei, et al.
Publicado: (2022)

FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning
por: Ge, Haonan, et al.
Publicado: (2025)

VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning
por: Liu, Ye, et al.
Publicado: (2025)

AVBench: Human-Aligned and Automated Evaluation Benchmark for Audio-Video Generative Models
por: Yang, Jialiang, et al.
Publicado: (2026)

Mining Multi-Modality Spatio-Temporal Cues for Video Important Person Identification
por: Wang, Xiao, et al.
Publicado: (2026)

SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
por: Chen, Junsong, et al.
Publicado: (2025)

Zoom In, Reason Out: Efficient Far-field Anomaly Detection in Expressway Surveillance Videos via Focused VLM Reasoning Guided by Bayesian Inference
por: Mao, Xiaowei, et al.
Publicado: (2026)

Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning
por: Tian, Shulin, et al.
Publicado: (2025)

StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter
por: Liu, Gongye, et al.
Publicado: (2023)

TimeSearch: Hierarchical Video Search with Spotlight and Reflection for Human-like Long Video Understanding
por: Pan, Junwen, et al.
Publicado: (2025)

1st Place Solution for 5th LSVOS Challenge: Referring Video Object Segmentation
por: Luo, Zhuoyan, et al.
Publicado: (2024)

Slot-ID: Identity-Preserving Video Generation from Reference Videos via Slot-Based Temporal Identity Encoding
por: Lai, Yixuan, et al.
Publicado: (2026)

Unified and Dynamic Graph for Temporal Character Grouping in Long Videos
por: Shu, Xiujun, et al.
Publicado: (2023)