16 datasets found

The Text-BEHAVE dataset is a large-scale dataset for 3D Human-Object Interaction, which integrates textual descriptions with the largest publicly available 3D HOI dataset.

The dataset used in the paper is COCO 2017 and HICO-DET

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.

HICO-Det is a benchmark for Human-Object Interaction (HOI) detection.

Human-Object Interaction (HOI) detection is a significant task to make a machine understand human activities in a static image at a fine-grained level.

Full-body articulated human-object interaction

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

The HICO-DET dataset is a large-scale human-object interaction (HOI) detection dataset, containing 9,658 images annotated with 600 HOI triplets.

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.

HICO dataset contains 600 HOI categories which have 117 unique verbs and 80 COCO object classes.

Human-Object Interaction (HOI) recognition at image level without using supervisions of object location and human pose.

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...