Search papers, labs, and topics across Lattice.
University of Bristol
4
0
4
Models trained with hand-object masked strategies can achieve superior HOI recognition by effectively isolating and utilizing hand- and object-centric cues.
Whareformer outperforms prior models in tracking occluded objects in egocentric videos, achieving state-of-the-art results with minimal training data.
A new dataset and transformer model that together nearly double the success rate for 3D hand-object pose estimation in real-world settings.
HOI-DETR achieves over 20 percentage points improvement in mAP for Hand-Object Interaction detection, setting a new benchmark in the field.
