3 accepted papers
Cross-modal alignment aims to learn semantically consistent latent representations across diverse modalities. Prevailing methods rely on a text-guided aggregation paradigm to achieve fine-grained alignment, while they suffer from redundant patch-word correlations and high computational costs. To add
Group activity recognition in videos is a challenging task, with two major issues, i.e. attending to those persons and their body parts that contribute significantly to the activity, and modeling contextual person structures in the group. Most previous approaches fail to provide a practical solution…
This paper proposes a novel approach to athlete tracking in sports videos. It follows the framework of Compressive Tracking (CT), but extends it by two manners, i.e. scale refinement as well as occlusion recovery. For the former, an objectness method, namely Edge Box (EB) is adopted to generate prop…