When Trackers Fail: VLM-Guided Verification and Recovery for Robust Video Object Segmentation
cs.CV
Submitted: 2026-10-11
Updated: 2026-10-11
Terminology
Sources
- Qwen3-VL Technical Report
- SAM 3: Segment Anything with Concepts
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation
- AgentRVOS: Reasoning over Object Tracks for Zero-Shot Referring Video Object Segmentation
- CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for Videos
- SAM 2: Segment Anything in Images and Videos
- SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory
- Advancing Complex Video Object Segmentation via Progressive Concept Construction
- ViLLa: Video Reasoning Segmentation with Large Language Model
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models