Cover Image

ToSA: Token Merging with Spatial Awareness

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Hsiang-Wei, Chai, Wenhao, Chen, Kuang-Ming, Yang, Cheng-Yen, Hwang, Jenq-Neng
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

SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory
by: Yang, Cheng-Yen, et al.
Published: (2024)

MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking
by: Huang, Hsiang-Wei, et al.
Published: (2024)

Reasoning Matters for 3D Visual Grounding
by: Huang, Hsiang-Wei, et al.
Published: (2026)

CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models
by: Huang, Hsiang-Wei, et al.
Published: (2026)

PackDiT: Joint Human Motion and Text Generation via Mutual Prompting
by: Jiang, Zhongyu, et al.
Published: (2025)

ToSA: Token Selective Attention for Efficient Vision Transformers
by: Singh, Manish Kumar, et al.
Published: (2024)

Technical Report for ReID-SAM on SkiTB Visual Tracking Challenge 2025
by: Li, Kunjun, et al.
Published: (2025)

GTA: Global Tracklet Association for Multi-Object Tracking in Sports
by: Sun, Jiacheng, et al.
Published: (2024)

UniHPR: Unified Human Pose Representation via Singular Value Contrastive Learning
by: Jiang, Zhongyu, et al.
Published: (2025)

A Density-Guided Temporal Attention Transformer for Indiscernible Object Counting in Underwater Video
by: Yang, Cheng-Yen, et al.
Published: (2024)

Boosting Online 3D Multi-Object Tracking through Camera-Radar Cross Check
by: Kuan, Sheng-Yao, et al.
Published: (2024)

Warehouse Spatial Question Answering with LLM Agent
by: Huang, Hsiang-Wei, et al.
Published: (2025)

Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic Segmentation
by: Chen, I-Hsiang, et al.
Published: (2025)

ToddlerAct: A Toddler Action Recognition Dataset for Gross Motor Development Assessment
by: Huang, Hsiang-Wei, et al.
Published: (2024)

MovieChat+: Question-aware Sparse Memory for Long Video Question Answering
by: Song, Enxin, et al.
Published: (2024)

Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field
by: Hu, Wenhao, et al.
Published: (2025)

VersaT2I: Improving Text-to-Image Models with Versatile Reward
by: Guo, Jianshu, et al.
Published: (2024)

Detector-in-the-Loop Tracking: Active Memory Rectification for Stable Glottic Opening Localization
by: Wang, Huayu, et al.
Published: (2026)

CityGen: Infinite and Controllable City Layout Generation
by: Deng, Jie, et al.
Published: (2023)

MPM: A Unified 2D-3D Human Pose Representation via Masked Pose Modeling
by: Zhang, Zhenyu, et al.
Published: (2023)

Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey
by: Wang, Gaoang, et al.
Published: (2022)

TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action
by: Cheng, Jen-Hao, et al.
Published: (2025)

Adapting SAM 2 for Visual Object Tracking: 1st Place Solution for MMVPR Challenge Multi-Modal Tracking
by: Yang, Cheng-Yen, et al.
Published: (2025)

RT-Pose: A 4D Radar Tensor-based 3D Human Pose Estimation and Localization Benchmark
by: Ho, Yuan-Hao, et al.
Published: (2024)

DAug: Diffusion-based Channel Augmentation for Radiology Image Retrieval and Classification
by: Jin, Ying, et al.
Published: (2024)

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

CityCraft: A Real Crafter for 3D City Generation
by: Deng, Jie, et al.
Published: (2024)

ProTPS: Prototype-Guided Text Prompt Selection for Continual Learning
by: Mei, Jie, et al.
Published: (2026)

AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
by: Chai, Wenhao, et al.
Published: (2024)

Single-image driven 3d viewpoint training data augmentation for effective wine label recognition
by: Huang, Yueh-Cheng, et al.
Published: (2024)

CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications
by: Zhang, Tianfang, et al.
Published: (2024)

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
by: Zhang, Luyuan, et al.
Published: (2026)

MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection
by: Liu, Hou-I, et al.
Published: (2024)

Tree Counting by Bridging 3D Point Clouds with Imagery
by: Li, Lei, et al.
Published: (2024)

Understanding Identity Continuity in Thermal Video through Scene-Level Consistency
by: Sun, Wei-Chieh, et al.
Published: (2026)

milliMamba: Specular-Aware Human Pose Estimation via Dual mmWave Radar with Multi-Frame Mamba Fusion
by: Kini, Niraj Prakash, et al.
Published: (2025)

From Global to Local: Rethinking CLIP Feature Aggregation for Person Re-Identification
by: Zheng, Aotian, et al.
Published: (2026)

ScalingGaussian: Enhancing 3D Content Creation with Generative Gaussian Splatting
by: Chen, Shen, et al.
Published: (2024)

Token Merging via Spatiotemporal Information Mining for Surgical Video Understanding
by: Jiang, Xixi, et al.
Published: (2025)

CubistMerge: Spatial-Preserving Token Merging For Diverse ViT Backbones
by: Gong, Wenyi, et al.
Published: (2025)