Cover Image

Inference-Time Temporal Probability Smoothing for Stable Video Segmentation with SAM2 under Weak Prompts

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Deka, Dawar Jyoti
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

Prompt Sensitivity in Vision-Language Grounding: How Small Changes in Wording Affect Object Detection
by: Deka, Dawar Jyoti, et al.
Published: (2026)

EP-SAM: Weakly Supervised Histopathology Segmentation via Enhanced Prompt with Segment Anything
by: Song, Joonhyeon, et al.
Published: (2024)

WeakMedSAM: Weakly-Supervised Medical Image Segmentation via SAM with Sub-Class Exploration and Prompt Affinity Mining
by: Wang, Haoran, et al.
Published: (2025)

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

SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation
by: Chen, Pengfei, et al.
Published: (2024)

Self-Prompt SAM: Medical Image Segmentation via Automatic Prompt SAM Adaptation
by: Xie, Bin, 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)

FastSmoothSAM: A Fast Smooth Method For Segment Anything Model
by: Xu, Jiasheng, et al.
Published: (2025)

Auto-Prompting SAM for Weakly Supervised Landslide Extraction
by: Wang, Jian, et al.
Published: (2025)

OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts
by: Xiao, Shiting, et al.
Published: (2025)

Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation
by: Chen, Gordon, et al.
Published: (2026)

Evaluating SAM2 for Video Semantic Segmentation
by: Ariff, Syed Hesham Syed, et al.
Published: (2025)

SSP-SAM: SAM with Semantic-Spatial Prompt for Referring Expression Segmentation
by: Tang, Wei, et al.
Published: (2026)

Correspondence as Video: Test-Time Adaption on SAM2 for Reference Segmentation in the Wild
by: Wang, Haoran, et al.
Published: (2025)

VideoSAM: Open-World Video Segmentation
by: Guo, Pinxue, et al.
Published: (2024)

RFMedSAM 2: Automatic Prompt Refinement for Enhanced Volumetric Medical Image Segmentation with SAM 2
by: Xie, Bin, et al.
Published: (2025)

HFP-SAM: Hierarchical Frequency Prompted SAM for Efficient Marine Animal Segmentation
by: Zhang, Pingping, et al.
Published: (2026)

SAM2-SGP: Enhancing SAM2 for Medical Image Segmentation via Support-Set Guided Prompting
by: Xing, Yang, et al.
Published: (2025)

OFL-SAM2: Prompt SAM2 with Online Few-shot Learner for Efficient Medical Image Segmentation
by: Lan, Meng, et al.
Published: (2025)

ProSAM: Enhancing the Robustness of SAM-based Visual Reference Segmentation with Probabilistic Prompts
by: Wang, Xiaoqi, et al.
Published: (2025)

Semantic-aware SAM for Point-Prompted Instance Segmentation
by: Wei, Zhaoyang, et al.
Published: (2023)

Automating MedSAM by Learning Prompts with Weak Few-Shot Supervision
by: Gaillochet, Mélanie, et al.
Published: (2024)

RevSAM2: Prompt SAM2 for Medical Image Segmentation via Reverse-Propagation without Fine-tuning
by: Bai, Yunhao, et al.
Published: (2024)

MirrorSAM2: Segment Mirror in Videos with Depth Perception
by: Xu, Mingchen, et al.
Published: (2025)

Biomedical SAM 2: Segment Anything in Biomedical Images and Videos
by: Yan, Zhiling, et al.
Published: (2024)

Temporal Prompting Matters: Rethinking Referring Video Object Segmentation
by: Lin, Ci-Siang, et al.
Published: (2025)

Memory-SAM: Human-Prompt-Free Tongue Segmentation via Retrieval-to-Prompt
by: Chae, Joongwon, et al.
Published: (2025)

Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes
by: Zhao, Xiaoqi, et al.
Published: (2024)

SAM-DCE: Addressing Token Uniformity and Semantic Over-Smoothing in Medical Segmentation
by: Hu, Yingzhen, et al.
Published: (2025)

Weakly Supervised Segmentation of Hyper-Reflective Foci with Compact Convolutional Transformers and SAM2
by: Morelle, Olivier, et al.
Published: (2025)

SSS: Semi-Supervised SAM-2 with Efficient Prompting for Medical Imaging Segmentation
by: Zhu, Hongjie, et al.
Published: (2025)

PanoSAM2: Lightweight Distortion- and Memory-aware Adaptions of SAM2 for 360 Video Object Segmentation
by: Xiao, Dingwen, et al.
Published: (2026)

WPS-SAM: Towards Weakly-Supervised Part Segmentation with Foundation Models
by: Wu, Xinjian, et al.
Published: (2024)

SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
by: Ding, Shuangrui, et al.
Published: (2024)

MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation
by: Rong, Fu, et al.
Published: (2025)

Vision and Language Reference Prompt into SAM for Few-shot Segmentation
by: Sakurai, Kosuke, et al.
Published: (2025)

VesSAM: Efficient Multi-Prompting for Segmenting Complex Vessel
by: Fu, Suzhong, et al.
Published: (2025)

DiffuSAM: Diffusion-Based Prompt-Free SAM2 for Few-Shot and Source-Free Medical Image Segmentation
by: Grossman, Tal, et al.
Published: (2026)

MapSAM2: Adapting SAM2 for Automatic Segmentation of Historical Map Images and Time Series
by: Xia, Xue, et al.
Published: (2025)

Learning from Noisy Prompts: Saliency-Guided Prompt Distillation for Robust Segmentation with SAM
by: Kang, Jingxuan, et al.
Published: (2026)