The main progress for action segmentation comes from densely-annotated data for fully-supervised learning.
Ranked #13 on Action Segmentation on Breakfast
Despite the recent progress of fully-supervised action segmentation techniques, the performance is still not fully satisfactory.
Ranked #11 on Action Segmentation on GTEA
In order to overcome these challenges, we propose to use cross-modality attention with semantic graph embedding for multi label classification.
Ranked #8 on Multi-Label Classification on NUS-WIDE
Although great progress has been made to apply object-level recognition, recognizing the attributes of parts remains less applicable since the training data for part attributes recognition is usually scarce especially for internet-scale applications.
However, jointly using visual and inertial measurements to optimize SLAM objective functions is a problem of high computational complexity.