Zero Shot Segmentation


Zero-shot segmentation is the process of segmenting objects in images without using any labeled data.

Target-Aware Video Diffusion Models

Add code
Mar 24, 2025
Viaarxiv icon

Semantic Segmentation of Transparent and Opaque Drinking Glasses with the Help of Zero-shot Learning

Add code
Mar 19, 2025
Viaarxiv icon

SPNeRF: Open Vocabulary 3D Neural Scene Segmentation with Superpoints

Add code
Mar 19, 2025
Viaarxiv icon

OpenCity3D: What do Vision-Language Models know about Urban Environments?

Add code
Mar 21, 2025
Viaarxiv icon

EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Models

Add code
Mar 18, 2025
Viaarxiv icon

Adapting to the Unknown: Training-Free Audio-Visual Event Perception with Dynamic Thresholds

Add code
Mar 21, 2025
Viaarxiv icon

VEGGIE: Instructional Editing and Reasoning of Video Concepts with Grounded Generation

Add code
Mar 19, 2025
Viaarxiv icon

Breaking the Box: Enhancing Remote Sensing Image Segmentation with Freehand Sketches

Add code
Mar 15, 2025
Viaarxiv icon

Eye on the Target: Eye Tracking Meets Rodent Tracking

Add code
Mar 13, 2025
Viaarxiv icon

CAM-Seg: A Continuous-valued Embedding Approach for Semantic Image Generation

Add code
Mar 19, 2025
Viaarxiv icon