Learn More
Recent advances in clothes recognition have been driven by the construction of clothes datasets. Existing datasets are limited in the amount of annotations and are difficult to cope with the various challenges in real-world applications. In this work, we introduce DeepFashion 1 , a large-scale clothes dataset with comprehensive annotations. It contains over(More)
Nonverbal communication plays an important role in social interactions. However, most nonverbal communication relies on visual signals such as eye contact, head nods, facial expressions and body gestures. Visual nonverbal signals are inaccessible for the blind and hardly accessible for low vision individuals. In this paper, we present a qualitative study on(More)
Pattern Deformation penalty Pattern Deformation penalty Image Visualized model Pretrained on object-level annoation Pretrained on image-level annotation (a) (b) Figure 1: The motivation in new pretraining scheme (a) and jointly learning feature representation and deformable object parts shared by multiple object classes at different semantic levels (b). In(More)
Mobile social media penetrates into common people's lives and extensive researches are concerned about their use behaviors. However, the blind and visually impaired users as special user groups are often ignored. Only few researches have been conducted to understand their interactions with current mainstream mobile social media. By the assistance of Hong(More)
Crowd behavior analysis is an interdisciplinary topic. Understanding the collective crowd behaviors is one of the fundamental problems both in social science and natural science. Research of crowd behavior analysis can lead to a lot of critical applications, such as intelligent video surveillance, crowd abnormal detection, and public facility optimization.(More)
  • 1