T-DEED: Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in Sports Videos

arXiv:2404.05392v1 Announce Type: new
Abstract: In this paper, we introduce T-DEED, a Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in sports videos. T-DEED addresses multiple challenges in the task, including the need for discriminability among frame representations, high output temporal resolution to maintain prediction precision, and the necessity to capture information at different temporal scales to handle events with varying dynamics. It tackles these challenges through its specifically designed architecture, featuring an encoder-decoder for leveraging multiple temporal scales and achieving …

abstract arxiv challenges cs.cv decoder encoder encoder-decoder event multiple paper precision prediction resolution sports temporal type videos