Image annotation has been an active research topic in the recent years due to its potentially large impact on both image understanding and web/database image search. In this paper...
In contrast to traditional machine learning algorithms, where all data are available in batch mode, the new paradigm of streaming data poses additional difficulties, since data sam...
The bounding box representation employed by many popular object detection models [3, 6] implicitly assumes all pixels inside the box belong to the object. This assumption makes th...
Many human action recognition tasks involve data that can be factorized into multiple views such as body postures and hand shapes. These views often interact with each other over ...
Understanding goals and preferences behind a user's online activities can greatly help information providers, such as search engine and E-Commerce web sites, to personalize c...
Honghua (Kathy) Dai, Lingzhi Zhao, Zaiqing Nie, Ji...