Describe me if you can! Characterized Instance-level Human Parsing
This work addresses the need for fast and accurate human description methods in applications like person search and fashion, though it is incremental as it builds on existing datasets and methods.
The authors tackled the lack of datasets for multi-instance human parsing with detailed attribute characteristics by proposing CCIHP, a dataset with 20 new labels covering color, size, and pattern attributes, and introduced HPTR, a transformer-based method that is the fastest in the state of the art while maintaining comparable precision.
Several computer vision applications such as person search or online fashion rely on human description. The use of instance-level human parsing (HP) is therefore relevant since it localizes semantic attributes and body parts within a person. But how to characterize these attributes? To our knowledge, only some single-HP datasets describe attributes with some color, size and/or pattern characteristics. There is a lack of dataset for multi-HP in the wild with such characteristics. In this article, we propose the dataset CCIHP based on the multi-HP dataset CIHP, with 20 new labels covering these 3 kinds of characteristics. In addition, we propose HPTR, a new bottom-up multi-task method based on transformers as a fast and scalable baseline. It is the fastest method of multi-HP state of the art while having precision comparable to the most precise bottom-up method. We hope this will encourage research for fast and accurate methods of precise human descriptions.