Video Object Segmentation under Aquatic Domain Shift: A Diagnostic Benchmark and Restoration Adapter
cs.CV
Submitted: 2026-03-25
Updated: 2026-11-07
Terminology
Sources
- Improving Underwater Visual Tracking With a Large Scale Dataset and Image Enhancement
- Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes
- USIS16K: High-Quality Dataset for Underwater Salient Instance Segmentation
- Exploring the Underwater World Segmentation without Extra Training
- MARIS: Marine Open-Vocabulary Instance Segmentation with Geometric Enhancement and Semantic Alignment
- Advancing Marine Research: UWSAM Framework and UIIS10K Dataset for Precise Underwater Instance Segmentation
- DINOv2: Learning Robust Visual Features without Supervision
- The 2017 DAVIS Challenge on Video Object Segmentation
- Underwater Camouflaged Object Tracking Meets Vision-Language SAM2
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs