3 accepted papers
Dataset distillation has emerged as an effective strategy, significantly reducing training costs and facilitating more efficient model deployment. Recent advances have leveraged generative models to distill datasets by capturing the underlying data distribution. Unfortunately, existing methods requi…
In this work, we present a novel approach to multi-view action recognition where we guide learned action representations to be separated from view-relevant information in a video. When trying to classify action instances captured from multiple viewpoints, there is a higher degree of difficulty due t…
Real world videos contain many complex actions with inherent relationships between action classes. In this work, we propose an attention-based architecture that model these action relationships for the task of temporal action localization in untrimmed videos. As opposed to previous works which lever…