19 citations · 28 across the 7 of their papers we have counts for
7 papers
UniDiff: Advancing Vision-Language Models with Generative and Discriminative Learning
Xiao Dong, Runhui Huang, Xiaoyong Wei +4
Recent advances in vision-language pre-training have enabled machines to perform better in multimodal object discrimination (e.g., image-text semantic alignment) and image synthesi…
Entity-Graph Enhanced Cross-Modal Pretraining for Instance-level Product Retrieval
Xiao Dong, Xunlin Zhan, Yunchao Wei +5
Our goal in this research is to study a more realistic environment in which we can conduct weakly-supervised multi-modal instance-level product retrieval for fine-grained product c…
elBERto: Self-supervised Commonsense Learning for Question Answering
Xunlin Zhan, Yuan Li, Xiao Dong +3
Commonsense question answering requires reasoning about everyday situations and causes and effects implicit in context. Typically, existing approaches first retrieve external evide…
M5Product: Self-harmonized Contrastive Learning for E-commercial Multi-modal Pretraining
Xiao Dong, Xunlin Zhan, Yangxin Wu +6
Despite the potential of multi-modal pre-training to learn highly discriminative feature representations from complementary data modalities, current progress is being slowed by the…
Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-modal Pretraining
Xunlin Zhan, Yangxin Wu, Xiao Dong +5
Nowadays, customer's demands for E-commerce are more diversified, which introduces more complications to the product retrieval industry. Previous methods are either subject to sing…
Rethink Maximum Mean Discrepancy for Domain Adaptation
Wei Wang, Haojie Li, Zhengming Ding +1
Existing domain adaptation methods aim to reduce the distributional difference between the source and target domains and respect their specific discriminative information, by estab…
Adaptive Collaborative Similarity Learning for Unsupervised Multi-view Feature Selection
Xiao Dong, Lei Zhu, Xuemeng Song +2
In this paper, we investigate the research problem of unsupervised multi-view feature selection. Conventional solutions first simply combine multiple pre-constructed view-specific…