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

Angelique Loesch (1) , Romaric Audigier (1)

1 LVIC - Laboratoire Vision et Ingénierie des Contenus

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. 1 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.

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

Domaines: Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Apprentissage [cs.LG]; Traitement des images [eess.IV]

Angelique Loesch, Romaric Audigier. Describe me if you can! Characterized instance-level human parsing. ICIP 2021 - 2021 IEEE International Conference on Image Processing, Sep 2021, Anchorage, United States. ⟨cea-03251774⟩