Cover Image

M2P: Improving Visual Foundation Models with Mask-to-Point Weakly-Supervised Learning for Dense Point Tracking

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Qiangqiang, Yang, Tianyu, Fang, Bo, Wan, Jia, Di Martino, Matias, Sapiro, Guillermo, Chan, Antoni B.
Format:	Preprint
Published:	2026
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

Learning Tracking Representations from Single Point Annotations
by: Wu, Qiangqiang, et al.
Published: (2024)

Dense Point-to-Mask Optimization with Reinforced Point Selection for Crowd Instance Segmentation
by: Chen, Hongru, et al.
Published: (2026)

Order-Aware Test-Time Adaptation: Leveraging Temporal Dynamics for Robust Streaming Inference
by: Kim, Young Kyung, et al.
Published: (2026)

Vision Transformers with Natural Language Semantics
by: Kim, Young Kyung, et al.
Published: (2024)

Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting
by: Lin, Wei, et al.
Published: (2025)

SPOT: Sparsification with Attention Dynamics via Token Relevance in Vision Transformers
by: Schlesinger, Oded, et al.
Published: (2025)

ViSS-R1: Self-Supervised Reinforcement Video Reasoning
by: Fang, Bo, et al.
Published: (2025)

DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks
by: Wu, Qiangqiang, et al.
Published: (2023)

Robust Zero-Shot Crowd Counting and Localization With Adaptive Resolution SAM
by: Wan, Jia, et al.
Published: (2024)

Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Counting
by: Huang, Jiyang, et al.
Published: (2026)

Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds
by: Wei, Jiacheng, et al.
Published: (2021)

Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders
by: Fang, Bo, et al.
Published: (2025)

DistinctAD: Distinctive Audio Description Generation in Contexts
by: Fang, Bo, et al.
Published: (2024)

Chain-of-Image Generation: Toward Monitorable and Controllable Image Generation
by: Kim, Young Kyung, et al.
Published: (2025)

Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Tracking
by: Wu, Qiangqiang, et al.
Published: (2025)

Online Dense Point Tracking with Streaming Memory
by: Dong, Qiaole, et al.
Published: (2025)

Pro2SAM: Mask Prompt to SAM with Grid Points for Weakly Supervised Object Localization
by: Yang, Xi, et al.
Published: (2025)

A Fixed-Point Approach to Unified Prompt-Based Counting
by: Lin, Wei, et al.
Published: (2024)

Weakly Supervised Point Clouds Transformer for 3D Object Detection
by: Tang, Zuojin, et al.
Published: (2023)

Can Visual Foundation Models Achieve Long-term Point Tracking?
by: Aydemir, Görkay, et al.
Published: (2024)

Integrating SAM Supervision for 3D Weakly Supervised Point Cloud Segmentation
by: You, Lechun, et al.
Published: (2025)

Markerless Head Tracking for Accurate and Accessible Neuronavigation
by: Xie, Ziye, et al.
Published: (2026)

AllTracker: Efficient Dense Point Tracking at High Resolution
by: Harley, Adam W., et al.
Published: (2025)

Triple Point Masking
by: Liu, Jiaming, et al.
Published: (2024)

PointPatchRL -- Masked Reconstruction Improves Reinforcement Learning on Point Clouds
by: Gyenes, Balázs, et al.
Published: (2024)

Weakly-Supervised Learning of Dense Functional Correspondences
by: Stojanov, Stefan, et al.
Published: (2025)

Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning
by: Ge, Shiping, et al.
Published: (2024)

PointGAC: Geometric-Aware Codebook for Masked Point Cloud Modeling
by: Li, Abiao, et al.
Published: (2025)

PIPsUS: Self-Supervised Point Tracking in Ultrasound
by: Chen, Wanwen, et al.
Published: (2024)

Dense Center-Direction Regression for Object Counting and Localization with Point Supervision
by: Tabernik, Domen, et al.
Published: (2024)

Weakly Supervised Point Cloud Segmentation via Conservative Propagation of Scene-level Labels
by: Xia, Shaobo, et al.
Published: (2023)

Pan-FM: A Pan-Organ Foundation Model with Saliency-Guided Masking for Missing Robustness
by: Wu, Qiangqiang, et al.
Published: (2026)

Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation
by: Dai, Qiyuan, et al.
Published: (2024)

Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation
by: Zhang, Haojie, et al.
Published: (2023)

Point Tracking Improves World Action Models
by: Guan, Jiarui, et al.
Published: (2026)

Diffusion Masked Pretraining for Dynamic Point Cloud
by: Zhang, Zhuoyue, et al.
Published: (2026)

Self-Supervised Any-Point Tracking by Contrastive Random Walks
by: Shrivastava, Ayush, et al.
Published: (2024)

Finding Meaning in Points: Weakly Supervised Semantic Segmentation for Event Cameras
by: Cho, Hoonhee, et al.
Published: (2024)

Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation
by: Pan, Zhiyi, et al.
Published: (2024)

Online Long-term Point Tracking in the Foundation Model Era
by: Aydemir, Görkay
Published: (2025)