Image de couverture de livre

GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ma, Junpeng, Zhou, Sashuai, Li, Guanghao, Gao, Xin, Cao, Yue, Zeng, Hengyu, Yan, Yuxiang, Wang, Zhibin, Song, Jun, Zheng, Bo, Zhang, Shanghang, Pu, Jian
Format:	Preprint
Publié:	2026
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

MacTok: Robust Continuous Tokenization for Image Generation
par: Zeng, Hengyu, et autres
Publié: (2026)

MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs
par: Ma, Junpeng, et autres
Publié: (2025)

Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection
par: Guo, Jiasheng, et autres
Publié: (2025)

Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models
par: Ruan, Jiaoyang, et autres
Publié: (2026)

SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation
par: Zhou, Sashuai, et autres
Publié: (2026)

DINO-VO: Learning Where to Focus for Enhanced State Estimation
par: Chen, Qi, et autres
Publié: (2026)

Learning Spatial-Aware Manipulation Ordering
par: Yan, Yuxiang, et autres
Publié: (2025)

Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning
par: Ma, Yinchao, et autres
Publié: (2026)

AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding
par: Li, Handong, et autres
Publié: (2026)

Global Trends of Trait Matching in Avian Frugivory and Its Consequences for the Complementarity and Irreplaceability of Birds
par: T. Morán‐López, et autres
Publié: (2025)

EC-SLAM: Effectively Constrained Neural RGB-D SLAM with Sparse TSDF Encoding and Global Bundle Adjustment
par: Li, Guanghao, et autres
Publié: (2024)

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

Unified Thinker: A General Reasoning Modular Core for Image Generation
par: Zhou, Sashuai, et autres
Publié: (2026)

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing
par: Yang, Hanqing, et autres
Publié: (2026)

DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding
par: Zhang, Peng, et autres
Publié: (2026)

PAPL-SLAM: Principal Axis-Anchored Monocular Point-Line SLAM
par: Li, Guanghao, et autres
Publié: (2024)

AndroidLens: Long-latency Evaluation with Nested Sub-targets for Android GUI Agents
par: Cao, Yue, et autres
Publié: (2025)

Twelve_Irreplaceable_Human_Capabilities_V1_PART_3
par: Park, Rae Hyun
Publié: (2025)

Twelve_Irreplaceable_Human_Capabilities_V1_PART_1
par: Park, Rae Hyun
Publié: (2025)

Powerful Student Care: Honoring Each Learner as Distinctive and Irreplaceable
par: Chandler, Grant, et autres
Publié: (2023)

ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation
par: Li, Guanghao, et autres
Publié: (2025)

Shot-Aware Frame Sampling for Video Understanding
par: Zhao, Mengyu, et autres
Publié: (2026)

Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding
par: Hu, Pengfei, et autres
Publié: (2025)

GIFT: Global stabilisation via Intrinsic Fine Tuning
par: Young, Rory, et autres
Publié: (2026)

The Substrate Consultant: Irreplaceable Human Data and the Future of Human-AI Collaboration
par: Sooh, Edouard
Publié: (2026)

The Third Generation of Nanogenerators: The Irreplaceable Potential Source Enabled by the Flexoelectric Nanogenerator
par: Li, Shang Ru, et autres
Publié: (2025)

Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs
par: Gao, Xin, et autres
Publié: (2025)

LADDER: An Efficient Framework for Video Frame Interpolation
par: Shen, Tong, et autres
Publié: (2024)

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

Frame by Familiar Frame: Understanding Replication in Video Diffusion Models
par: Rahman, Aimon, et autres
Publié: (2024)

Branch Target Buffer Reverse Engineering on Arm
par: Wan, Junpeng
Publié: (2024)

VideoScan: Enabling Efficient Streaming Video Understanding via Frame-level Semantic Carriers
par: Li, Ruanjun, et autres
Publié: (2025)

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

VUDG: A Dataset for Video Understanding Domain Generalization
par: Wang, Ziyi, et autres
Publié: (2025)

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

P‐3.9: Enhancing Embodied Intelligence in Human‐Computer Interaction: MISE – A Multimodal Interaction Framework for Smart Environments
par: Yongyang Yin, et autres
Publié: (2025)

End‐to‐End Attention‐Enhanced Transformer for Image Captioning in Biomimetic Wearable Devices
par: Yongyang Yin, et autres
Publié: (2025)

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

Enhancing Multi-modal Models with Heterogeneous MoE Adapters for Fine-tuning
par: Zhou, Sashuai, et autres
Publié: (2025)

A spatial-correlated multitask linear mixed-effects model for imaging genetics
par: Pu, Zhibin, et autres
Publié: (2024)