1 code implementation • 12 Jun 2023 • Rong-Cheng Tu, Yatai Ji, Jie Jiang, Weijie Kong, Chengfei Cai, Wenzhe Zhao, Hongfa Wang, Yujiu Yang, Wei Liu
MGSC promotes learning more representative global features, which have a great impact on the performance of downstream tasks, while MLTC reconstructs modal-fusion local tokens, further enhancing accurate comprehension of multimodal data.
1 code implementation • 23 Sep 2022 • Rong-Cheng Tu, Xian-Ling Mao, Kevin Qinghong Lin, Chengfei Cai, Weize Qin, Hongfa Wang, Wei Wei, Heyan Huang
Recently, to improve the unsupervised image retrieval performance, plenty of unsupervised hashing methods have been proposed by designing a semantic similarity matrix, which is based on the similarities between image features extracted by a pre-trained CNN model.
no code implementations • 6 Nov 2020 • Rong-Cheng Tu, Xian-Ling Mao, Rongxin Tu, Binbin Bian, Wei Wei, Heyan Huang
Finally, by minimizing the novel \textit{margin-dynamic-softmax loss}, the modality-specific hashing networks can be trained to generate hash codes which can simultaneously preserve the cross-modal similarity and abundant semantic information well.
no code implementations • 29 Jul 2019 • Rong-Cheng Tu, Xian-Ling Mao, Bing Ma, Yong Hu, Tan Yan, Wei Wei, He-Yan Huang
Specifically, by an iterative optimization algorithm, DCHUC jointly learns unified hash codes for image-text pairs in a database and a pair of hash functions for unseen query image-text pairs.
no code implementations • 24 Nov 2018 • Rong-Cheng Tu, Xian-Ling Mao, Bo-Si Feng, Bing-Bing Bian, Yu-shu Ying
Recently, similarity-preserving hashing methods have been extensively studied for large-scale image retrieval.