EgoSound: Benchmarking Sound Understanding in Egocentric Videos
Published in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Recommended citation: Zhu, B., Fu, Y., Dong, Q., Sun, G., Qian, T., Wu, Y., Paudel, D. P., Fu, Y., & Xue, X. (2026). EgoSound: Benchmarking Sound Understanding in Egocentric Videos. In CVPR. https://openaccess.thecvf.com/content/CVPR2026/papers/Zhu_EgoSound_Benchmarking_Sound_Understanding_in_Egocentric_Videos_CVPR_2026_paper.pdf
A benchmark for audio-visual reasoning and sound understanding in egocentric videos with multimodal large language models.