Zobrazeno 1 - 10
of 760
pro vyhledávání: '"Wang, Mengjiao"'
Autor:
Singh, Harman, Zhang, Pengchuan, Wang, Qifan, Wang, Mengjiao, Xiong, Wenhan, Du, Jingfei, Chen, Yu
Contrastively trained vision-language models have achieved remarkable progress in vision and language representation learning, leading to state-of-the-art models for various downstream multimodal tasks. However, recent research has highlighted severe
Externí odkaz:
http://arxiv.org/abs/2305.13812
Autor:
He, Yunzhong, Tian, Yuxin, Wang, Mengjiao, Chen, Feier, Yu, Licheng, Tang, Maolong, Chen, Congcong, Zhang, Ning, Kuang, Bin, Prakash, Arul
Embedding-based Retrieval (EBR) in e-commerce search is a powerful search retrieval technique to address semantic matches between search queries and products. However, commercial search engines like Facebook Marketplace Search are complex multi-stage
Externí odkaz:
http://arxiv.org/abs/2302.11052
Autor:
Mirchandani, Suvir, Yu, Licheng, Wang, Mengjiao, Sinha, Animesh, Jiang, Wenwen, Xiang, Tao, Zhang, Ning
Multimodal tasks in the fashion domain have significant potential for e-commerce, but involve challenging vision-and-language learning problems - e.g., retrieving a fashion item given a reference image plus text feedback from a user. Prior works on m
Externí odkaz:
http://arxiv.org/abs/2210.15028
Autor:
Wang, Mengjiao1 (AUTHOR) 202121622930@smail.xtu.edu.cn, Qin, Fengtai1 (AUTHOR)
Publikováno v:
Entropy. Jun2024, Vol. 26 Issue 6, p467. 15p.
Autor:
Lei, Jie, Chen, Xinlei, Zhang, Ning, Wang, Mengjiao, Bansal, Mohit, Berg, Tamara L., Yu, Licheng
Dual encoders and cross encoders have been widely used for image-text retrieval. Between the two, the dual encoder encodes the image and text independently followed by a dot product, while the cross encoder jointly feeds image and text as the input a
Externí odkaz:
http://arxiv.org/abs/2203.05465
Vision-and-Language (V+L) pre-training models have achieved tremendous success in recent years on various multi-modal benchmarks. However, the majority of existing models require pre-training on a large set of parallel image-text data, which is costl
Externí odkaz:
http://arxiv.org/abs/2203.00242
Autor:
Yu, Licheng, Chen, Jun, Sinha, Animesh, Wang, Mengjiao MJ, Chen, Hugo, Berg, Tamara L., Zhang, Ning
We introduce CommerceMM - a multimodal model capable of providing a diverse and granular understanding of commerce topics associated to the given piece of content (image, text, image+text), and having the capability to generalize to a wide range of t
Externí odkaz:
http://arxiv.org/abs/2202.07247
Autor:
Wang, Mengjiao, Ding, Liting
Publikováno v:
Industrial Lubrication and Tribology, 2023, Vol. 75, Issue 8, pp. 875-882.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/ILT-04-2023-0113
Autor:
Hu, Jinye, Zhou, Wenguang, Wang, Yunpu, Jiang, Haiwei, Wu, Jiabo, Luo, Ting, Wang, Mengjiao, Wang, Weixin, Wang, Qi, Hu, Yuhang, Fan, Liangliang
Publikováno v:
In Chemical Engineering Journal 15 August 2024 494
Autor:
Li, Yi1 (AUTHOR), Wang, Mengjiao1 (AUTHOR) 15823110127@163.com
Publikováno v:
Journal of Inequalities & Applications. 3/21/2024, Vol. 2024 Issue 1, p1-18. 18p.