Online understanding of who is talking to the camera wearer is a key capability for egocentric social interaction. However, existing talk-to-me (TTM) studies are commonly formulated as offline clip...
<p><strong>Tác giả:</strong> Feiyu Du, Xi He, Jia Li, Yapeng Tian, Weili Wu</p>
<p>Online understanding of who is talking to the camera wearer is a key capability for egocentric social interaction. However, existing talk-to-me (TTM) studies are commonly formulated as offline clip-level recognition, which is poorly aligned with online interaction and overlooks the diverse non-TTM speaking states that naturally arise in egocentric videos. In this paper, we revisit this problem by reformulating it as an online, frame-level prediction task. Instead of treating TTM as a binary p...</p>
<p>📄 DOI: <a href="https://doi.org/https://doi.org/10.1145/3767308.3836441" target="_blank" rel="noopener">https://doi.org/10.1145/3767308.3836441</a></p>
<p>📖 <a href="https://doi.org/https://doi.org/10.1145/3767308.3836441" target="_blank" rel="noopener">Xem bài báo đầy đủ</a></p>
Bài viết được biên soạn lại bởi LIFVietnam. Nguồn tham khảo: OpenAlex
