9 datasets found

BEHAVE: Dataset and method for tracking human object interactions.

Text-conditioned human motion generation has experienced significant advancements with diffusion models trained on extensive motion capture data and corresponding textual...

The dataset used in the paper is a spatio-temporal graph representing human activity detection and anticipation.

The VidHOI dataset is a large-scale dataset for video-based human-object interaction detection, comprising 6,366 videos for training set and 756 videos for validation.

Full-body articulated human-object interaction

CG-HOI: Contact-Guided 3D Human-Object Interaction Generation

The BEHAVE dataset is annotated with text descriptions for 3D human-object interactions.

The V-COCO dataset contains 2,533 training images, 2,867 validation images, and 4,946 test images, including 24 action classes.

The Something-Something V1 & V2 dataset is a large-scale video dataset created by crowdsourcing. It contains about 100k videos over 174 categories, and the number of videos...