no code implementations • 14 Jul 2023 • Fan Ni, Xu Zhang, Jianhui Wu, Guan-Nan Dong, Aichun Zhu, Hui Liu, Yue Zhang
To the best of our knowledge, TVPRN is the first successful attempt to use video for text-based person retrieval task and has achieved state-of-the-art performance on TVPReid dataset.
no code implementations • 7 Sep 2021 • Guan-Nan Dong, Chi-Man Pun, Zheng Zhang
Specifically, we take parents and children as a whole to extract the expressive local and non-local features.
no code implementations • 7 Sep 2021 • Guan-Nan Dong, Chi-Man Pun, Zheng Zhang
To this end, we propose a novel deep collaborative multi-modal learning (DCML) to integrate the underlying information presented in facial properties in an adaptive manner to strengthen the facial details for effective unsupervised kinship verification.