Manually reading and logging gauge data is time inefficient, and the eff...
Class-incremental learning is one of the most important settings for the...
Modern machine learning pipelines are limited due to data availability,
...
Recent advances in the Active Speaker Detection (ASD) problem build upon...
Continual learning (CL) is under-explored in the video domain. The few
e...
The recent and increasing interest in video-language research has driven...
Understanding movies and their structural patterns is a crucial task to
...
Video content creation keeps growing at an incredible pace; yet, creatin...
Humans are arguably one of the most important subjects in video streams,...
Active speaker detection requires a solid integration of multi-modal cue...
Current methods for active speak er detection focus on modeling short-te...
Instance-level video segmentation requires a solid integration of spatia...