ECCV2022論文サマリ

Is Geometry Enough for Matching in Visual Localization?
by: Haruhi Shida
3D autonomous driving visual localiztion
MultiMAE: Multi-modal Multi-task Masked Autoencoders
by: Yui Iioka @Keio-Univ.
Attention Depth estimation Multi modal Segmentation Semantic segmentation
PT4AL: Using Self-Supervised Pretext Tasks for Active Learning
by: Anonymous
Representation learning Self supervised learning Active Learning
TEMOS: Generating Diverse Human Motions from Textual Descriptions
by: Kosuke Fukazawa
3D Multi modal Motion Synthesis Text to Motion
MotionCLIP: Exposing Human Motion Generation to CLIP Space
by: Kosuke Fukazawa
3D Multi modal Motion Synthesis Text to Motion