← Back to search

Models tagged "referring-segmentation"

Sort by:

Found 2 models (showing 1-2)

🤖 Model 🎥

bytedance/sa2va-4b-video

Segment objects in videos from natural-language instructions. Accepts a video and a text instruction (referring expressi...

🎥 • video-segmentation • video-grounding • 48 runs

🤖 Model 🖼️

bytedance/sa2va-4b-image

Segment objects and regions in images using natural language instructions. Accepts an image and a text instruction and r...

🖼️ • image-segmentation • visual-grounding • referring-segmentation • 132 runs