Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ding, Kang, Wang, Hongsong, Gui, Jie, He, Lei
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Coordinate-Based Dual-Constrained Autoregressive Motion Generation
por: Ding, Kang, et al.
Publicado: (2026)

Dual Conditioned Motion Diffusion for Pose-Based Video Anomaly Detection
por: Wang, Hongsong, et al.
Publicado: (2024)

Dragging with Geometry: From Pixels to Geometry-Guided Image Editing
por: Pu, Xinyu, et al.
Publicado: (2025)

Towards Universal Skeleton-Based Action Recognition
por: Kuang, Jidong, et al.
Publicado: (2026)

Marrying Text-to-Motion Generation with Skeleton-Based Action Recognition
por: Kuang, Jidong, et al.
Publicado: (2026)

Region-aware Image-based Human Action Retrieval with Transformers
por: Wang, Hongsong, et al.
Publicado: (2024)

Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models
por: Han, Chaolei, et al.
Publicado: (2025)

Structure-Aware Fine-Grained Gaussian Splatting for Expressive Avatar Reconstruction
por: Su, Yuze, et al.
Publicado: (2026)

Data-Free Class-Incremental Gesture Recognition with Prototype-Guided Pseudo Feature Replay
por: Wang, Hongsong, et al.
Publicado: (2025)

Attribution as Retrieval: Model-Agnostic AI-Generated Image Attribution
por: Wang, Hongsong, et al.
Publicado: (2026)

Point-Supervised Skeleton-Based Human Action Segmentation
por: Wang, Hongsong, et al.
Publicado: (2026)

OZ-TAL: Online Zero-Shot Temporal Action Localization
por: Han, Chaolei, et al.
Publicado: (2026)

Multimodal Skeleton-Based Action Representation Learning via Decomposition and Composition
por: Wang, Hongsong, et al.
Publicado: (2025)

Heterogeneous Skeleton-Based Action Representation Learning
por: Wang, Hongsong, et al.
Publicado: (2025)

Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to Tail
por: He, Yina, et al.
Publicado: (2024)

Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment
por: Kuang, Jidong, et al.
Publicado: (2024)

LOTA: Bit-Planes Guided AI-Generated Image Detection
por: Wang, Hongsong, et al.
Publicado: (2025)

Efficient Diffusion-Based 3D Human Pose Estimation with Hierarchical Temporal Pruning
por: Bi, Yuquan, et al.
Publicado: (2025)

USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation
por: Weng, Wanjiang, et al.
Publicado: (2024)

EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation
por: Tan, Xiaofeng, et al.
Publicado: (2026)

BitC-3DGS: High-Capacity 3D Gaussian Splatting Watermarking via Bit Compression
por: Bi, Yuquan, et al.
Publicado: (2026)

Global-Aware Edge Prioritization for Pose Graph Initialization
por: Wei, Tong, et al.
Publicado: (2026)

HQ-OV3D: A High Box Quality Open-World 3D Detection Framework based on Diffision Model
por: Liu, Qi, et al.
Publicado: (2025)

Fast Inference of Visual Autoregressive Model with Adjacency-Adaptive Dynamical Draft Trees
por: Lei, Haodong, et al.
Publicado: (2025)

Not All Parameters Matter: Masking Diffusion Models for Enhancing Generation Ability
por: Wang, Lei, et al.
Publicado: (2025)

From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection
por: Cai, Lincan, et al.
Publicado: (2025)

RAGSR: Regional Attention Guided Diffusion for Image Super-Resolution
por: He, Haodong, et al.
Publicado: (2025)

Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection
por: Tan, Xiaofeng, et al.
Publicado: (2024)

AVGGT: Rethinking Global Attention for Accelerating VGGT
por: Sun, Xianbing, et al.
Publicado: (2025)

Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention
por: Chen, Taiye, et al.
Publicado: (2025)

Small Object Detection in Complex Backgrounds with Multi-Scale Attention and Global Relation Modeling
por: Tao, Wenguang, et al.
Publicado: (2026)

Temporal Consistency-Aware Text-to-Motion Generation
por: Wang, Hongsong, et al.
Publicado: (2026)

SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization
por: Tan, Xiaofeng, et al.
Publicado: (2024)

ReAlign: Bilingual Text-to-Motion Generation via Step-Aware Reward-Guided Alignment
por: Weng, Wanjiang, et al.
Publicado: (2025)

DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward Supervision
por: Zou, Xiandong, et al.
Publicado: (2025)

Robust 3D Face Alignment with Multi-Path Neural Architecture Search
por: Jiang, Zhichao, et al.
Publicado: (2024)

UItron: Foundational GUI Agent with Advanced Perception and Planning
por: Zeng, Zhixiong, et al.
Publicado: (2025)

Linear-Time Global Visual Modeling without Explicit Attention
por: He, Ruize, et al.
Publicado: (2026)

CogPortrait: Fine-Grained Eye-Region Control in Portrait Animation via Hierarchical Agent Planning
por: Feng, He, et al.
Publicado: (2026)

Morpho-Aware Global Attention for Image Matting
por: Yang, Jingru, et al.
Publicado: (2024)