
meta/sam-2-video
Segment and track objects in videos from point prompts. Provide a video plus click coordinates, foreground/background la...
Found 5 models (showing 1-5)
Segment and track objects in videos from point prompts. Provide a video plus click coordinates, foreground/background la...
Segment objects in video using natural-language instructions. Accepts a video and a text prompt (e.g., βthe person weari...
Segment objects in video from a natural-language instruction. Accepts a video and a text prompt describing the target ob...
Track multiple objects across video, associating detections over a long temporal window (up to 32 frames) to produce glo...
Track people in video and return an annotated video with bounding boxes and persistent track IDs using person detection...