Image de couverture de livre

Not All Agents Matter: From Global Attention Dilution to Risk-Prioritized Game Planning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ding, Kang, Wang, Hongsong, Gui, Jie, He, Lei
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

Coordinate-Based Dual-Constrained Autoregressive Motion Generation
par: Ding, Kang, et autres
Publié: (2026)

Dual Conditioned Motion Diffusion for Pose-Based Video Anomaly Detection
par: Wang, Hongsong, et autres
Publié: (2024)

Dragging with Geometry: From Pixels to Geometry-Guided Image Editing
par: Pu, Xinyu, et autres
Publié: (2025)

Towards Universal Skeleton-Based Action Recognition
par: Kuang, Jidong, et autres
Publié: (2026)

Marrying Text-to-Motion Generation with Skeleton-Based Action Recognition
par: Kuang, Jidong, et autres
Publié: (2026)

Region-aware Image-based Human Action Retrieval with Transformers
par: Wang, Hongsong, et autres
Publié: (2024)

Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models
par: Han, Chaolei, et autres
Publié: (2025)

Structure-Aware Fine-Grained Gaussian Splatting for Expressive Avatar Reconstruction
par: Su, Yuze, et autres
Publié: (2026)

Data-Free Class-Incremental Gesture Recognition with Prototype-Guided Pseudo Feature Replay
par: Wang, Hongsong, et autres
Publié: (2025)

Attribution as Retrieval: Model-Agnostic AI-Generated Image Attribution
par: Wang, Hongsong, et autres
Publié: (2026)

Point-Supervised Skeleton-Based Human Action Segmentation
par: Wang, Hongsong, et autres
Publié: (2026)

OZ-TAL: Online Zero-Shot Temporal Action Localization
par: Han, Chaolei, et autres
Publié: (2026)

Multimodal Skeleton-Based Action Representation Learning via Decomposition and Composition
par: Wang, Hongsong, et autres
Publié: (2025)

Heterogeneous Skeleton-Based Action Representation Learning
par: Wang, Hongsong, et autres
Publié: (2025)

Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to Tail
par: He, Yina, et autres
Publié: (2024)

Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment
par: Kuang, Jidong, et autres
Publié: (2024)

LOTA: Bit-Planes Guided AI-Generated Image Detection
par: Wang, Hongsong, et autres
Publié: (2025)

Efficient Diffusion-Based 3D Human Pose Estimation with Hierarchical Temporal Pruning
par: Bi, Yuquan, et autres
Publié: (2025)

USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation
par: Weng, Wanjiang, et autres
Publié: (2024)

EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation
par: Tan, Xiaofeng, et autres
Publié: (2026)

BitC-3DGS: High-Capacity 3D Gaussian Splatting Watermarking via Bit Compression
par: Bi, Yuquan, et autres
Publié: (2026)

Global-Aware Edge Prioritization for Pose Graph Initialization
par: Wei, Tong, et autres
Publié: (2026)

HQ-OV3D: A High Box Quality Open-World 3D Detection Framework based on Diffision Model
par: Liu, Qi, et autres
Publié: (2025)

Fast Inference of Visual Autoregressive Model with Adjacency-Adaptive Dynamical Draft Trees
par: Lei, Haodong, et autres
Publié: (2025)

Not All Parameters Matter: Masking Diffusion Models for Enhancing Generation Ability
par: Wang, Lei, et autres
Publié: (2025)

From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection
par: Cai, Lincan, et autres
Publié: (2025)

RAGSR: Regional Attention Guided Diffusion for Image Super-Resolution
par: He, Haodong, et autres
Publié: (2025)

Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection
par: Tan, Xiaofeng, et autres
Publié: (2024)

AVGGT: Rethinking Global Attention for Accelerating VGGT
par: Sun, Xianbing, et autres
Publié: (2025)

Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention
par: Chen, Taiye, et autres
Publié: (2025)

Small Object Detection in Complex Backgrounds with Multi-Scale Attention and Global Relation Modeling
par: Tao, Wenguang, et autres
Publié: (2026)

Temporal Consistency-Aware Text-to-Motion Generation
par: Wang, Hongsong, et autres
Publié: (2026)

SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization
par: Tan, Xiaofeng, et autres
Publié: (2024)

ReAlign: Bilingual Text-to-Motion Generation via Step-Aware Reward-Guided Alignment
par: Weng, Wanjiang, et autres
Publié: (2025)

DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward Supervision
par: Zou, Xiandong, et autres
Publié: (2025)

Robust 3D Face Alignment with Multi-Path Neural Architecture Search
par: Jiang, Zhichao, et autres
Publié: (2024)

UItron: Foundational GUI Agent with Advanced Perception and Planning
par: Zeng, Zhixiong, et autres
Publié: (2025)

Linear-Time Global Visual Modeling without Explicit Attention
par: He, Ruize, et autres
Publié: (2026)

CogPortrait: Fine-Grained Eye-Region Control in Portrait Animation via Hierarchical Agent Planning
par: Feng, He, et autres
Publié: (2026)

Morpho-Aware Global Attention for Image Matting
par: Yang, Jingru, et autres
Publié: (2024)