Describe me if you can! Characterized instance-level human parsing

Angélique Loesch (1) , Romaric Audigier (1)

1 DIASI - Département Intelligence Ambiante et Systèmes Interactifs

Several computer vision applications 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 baseline, to encourage research for fast and accurate methods of precise human descriptions.

Keywords: Human parsing; Characterized attributes; Dataset; Bottom-up segmentation; Scalability

Domains: Machine Learning [cs.LG]; Computer Vision and Pattern Recognition [cs.CV]; Databases [cs.DB]

Angélique Loesch, Romaric Audigier. Describe me if you can! Characterized instance-level human parsing. ICIP 2021 - IEEE International Conference on Image Processing, Sep 2021, Anchorage, United States. pp.2528-2532, ⟨10.1109/ICIP42928.2021.9506509⟩. ⟨cea-03660437⟩