-
Chapter and Conference Paper
Unsupervised Person Re-identification via Differentiated Color Perception Learning
Unsupervised person re-identification (re-ID) encounters two key problems. One is the lack of label annotation in the target domain, and the other is the domain gap between different cameras. They are addresse...
-
Chapter and Conference Paper
Label Distribution Learning with Discriminative Instance Map**
Label distribution learning (LDL) is an effective tool to tackle label ambiguity since it allows one instance to be associated with multiple labels in different degrees. Therefore, the more complex but informa...
-
Chapter and Conference Paper
RLMixer: A Reinforcement Learning Approach for Integrated Ranking with Contrastive User Preference Modeling
There is a strong need for industrial recommender systems to output an integrated ranking of items from different categories, such as video and news, to maximize overall user satisfaction. Integrated ranking f...
-
Chapter and Conference Paper
A Sequence-to-Sequence Text Summarization Model with Topic Based Attention Mechanism
One of the limitation of automatic summarization is that how to take into account and reflect the implicit information conveyed between different text and the scene influence. In particularly, the generation o...