Cover Image

When Tracking Fails: Analyzing Failure Modes of SAM2 for Point-Based Tracking in Surgical Videos

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jang, Woowon, Im, Jiwon, Choi, Juseung, Rashidian, Niki, De Neve, Wesley, Ozbulak, Utku
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Revisiting the Evaluation Bias Introduced by Frame Sampling Strategies in Surgical Video Segmentation Using SAM2
by: Ozbulak, Utku, et al.
Published: (2025)

One Patient's Annotation is Another One's Initialization: Towards Zero-Shot Surgical Video Segmentation with Cross-Patient Initialization
by: Mousavi, Seyed Amir, et al.
Published: (2025)

Exploring Patient Data Requirements in Training Effective AI Models for MRI-based Breast Cancer Classification
by: Kang, Solha, et al.
Published: (2025)

SpurBreast: A Curated Dataset for Investigating Spurious Correlations in Real-world Breast MRI Classification
by: Won, Jong Bum, et al.
Published: (2025)

Improved Sub-Visible Particle Classification in Flow Imaging Microscopy via Generative AI-Based Image Synthesis
by: Ozbulak, Utku, et al.
Published: (2025)

Self-supervised Benchmark Lottery on ImageNet: Do Marginal Improvements Translate to Improvements on Similar Datasets?
by: Ozbulak, Utku, et al.
Published: (2025)

Towards Affordable Tumor Segmentation and Visualization for 3D Breast MRI Using SAM2
by: Kang, Solha, et al.
Published: (2025)

Color Flow Imaging Microscopy Improves Identification of Stress Sources of Protein Aggregates in Biopharmaceuticals
by: Cohrs, Michaela, et al.
Published: (2025)

Detecting Regional Spurious Correlations in Vision Transformers via Token Discarding
by: Kang, Solha, et al.
Published: (2025)

Identifying Critical Tokens for Accurate Predictions in Transformer-based Medical Imaging Models
by: Kang, Solha, et al.
Published: (2025)

Boosting 3D Liver Shape Datasets with Diffusion Models and Implicit Neural Representations
by: Nguyen, Khoa Tuan, et al.
Published: (2025)

SAM2S: Segment Anything in Surgical Videos via Semantic Long-term Tracking
by: Liu, Haofeng, et al.
Published: (2025)

Seg2Track-SAM2: SAM2-based Multi-object Tracking and Segmentation
by: Mendonça, Diogo, et al.
Published: (2025)

Toward Using Machine Learning as a Shape Quality Metric for Liver Point Cloud Generation
by: Nguyen, Khoa Tuan, et al.
Published: (2025)

ReSurgSAM2: Referring Segment Anything in Surgical Video via Credible Long-term Tracking
by: Liu, Haofeng, et al.
Published: (2025)

SurgiTrack: Fine-Grained Multi-Class Multi-Tool Tracking in Surgical Videos
by: Nwoye, Chinedu Innocent, et al.
Published: (2024)

Augmenting Efficient Real-time Surgical Instrument Segmentation in Video with Point Tracking and Segment Anything
by: Wu, Zijian, et al.
Published: (2024)

Training-free Temporal Object Tracking in Surgical Videos
by: Koley, Subhadeep, et al.
Published: (2026)

Point Tracking in Surgery--The 2024 Surgical Tattoos in Infrared (STIR) Challenge
by: Schmidt, Adam, et al.
Published: (2025)

EgoPoints: Advancing Point Tracking for Egocentric Videos
by: Darkhalil, Ahmad, et al.
Published: (2024)

Rethinking Memory Design in SAM-Based Visual Object Tracking
by: Alansari, Mohamad, et al.
Published: (2025)

SAM-PD: How Far Can SAM Take Us in Tracking and Segmenting Anything in Videos by Prompt Denoising
by: Zhou, Tao, et al.
Published: (2024)

Temporally Guided Articulated Hand Pose Tracking in Surgical Videos
by: Louis, Nathan, et al.
Published: (2021)

TSMS-SAM2: Multi-scale Temporal Sampling Augmentation and Memory-Splitting Pruning for Promptable Video Object Segmentation and Tracking in Surgical Scenarios
by: Xu, Guoping, et al.
Published: (2025)

ComPose: When to Trust Hands for Object Pose Tracking
by: Shin, Jisu, et al.
Published: (2026)

SAM 2++: Tracking Anything at Any Granularity
by: Zhang, Jiaming, et al.
Published: (2025)

Evaluating Visual Explanations of Attention Maps for Transformer-based Medical Imaging
by: Chung, Minjae, et al.
Published: (2025)

SAM-DA: UAV Tracks Anything at Night with SAM-Powered Domain Adaptation
by: Fu, Changhong, et al.
Published: (2023)

Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation
by: Jeong, Hyeonho, et al.
Published: (2024)

Tracking Skiers from the Top to the Bottom
by: Dunnhofer, Matteo, et al.
Published: (2023)

Repurposing Video Diffusion Transformers for Robust Point Tracking
by: Son, Soowon, et al.
Published: (2025)

Point Prompting: Counterfactual Tracking with Video Diffusion Models
by: Shrivastava, Ayush, et al.
Published: (2025)

SatSAM2: Motion-Constrained Video Object Tracking in Satellite Imagery using Promptable SAM2 and Kalman Priors
by: Fan, Ruijie, et al.
Published: (2025)

MV-TAP: Tracking Any Point in Multi-View Videos
by: Koo, Jahyeok, et al.
Published: (2025)

Generative Video Motion Editing with 3D Point Tracks
by: Lee, Yao-Chih, et al.
Published: (2025)

Track-On2: Enhancing Online Point Tracking with Memory
by: Aydemir, Görkay, et al.
Published: (2025)

Track-On: Transformer-based Online Point Tracking with Memory
by: Aydemir, Görkay, et al.
Published: (2025)

Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation
by: Bharadhwaj, Homanga, et al.
Published: (2024)

EXAONE Path 2.0: Pathology Foundation Model with End-to-End Supervision
by: Pyeon, Myeongjang, et al.
Published: (2025)

Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track
by: Pan, Feiyu, et al.
Published: (2024)