Attribute Recognition from Adaptive Parts
Previous part-based attribute recognition approaches perform part detection and attribute recognition in separate steps. The parts are not optimized for attribute recognition and therefore could be sub-optimal. We present an end-to-end deep learning approach to overcome the limitation. It generates object parts from key points and perform attribute recognition accordingly, allowing adaptive spatial transform of the parts. Both key point estimation and attribute recognition are learnt jointly in a multi-task setting. Extensive experiments on two datasets verify the efficacy of proposed end-to-end approach.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeSimilar Papers 제목 키워드 기반
A Richly Annotated Dataset for Pedestrian Attribute Recognition
In this paper, we aim to improve the dataset foundation for pedestrian attribute recognition in real surveillance scenarios. Recognition of human attributes, such as gender, and clothes types, has great prospects in real…
AttributePedestrian Attribute RecognitionMask-Guided Multi-Task Network for Face Attribute Recognition
Face Attribute Recognition (FAR) plays a crucial role in applications such as person re-identification, face retrieval, and face editing. Conventional multi-task attribute recognition methods often process the entire fea…
Person Re-IdentificationAttributed Grammars for Joint Estimation of Human Attributes, Part and Pose
In this paper, we are interested in developing compositional models to explicit representing pose, parts and attributes and tackling the tasks of attribute recognition, pose estimation and part localization jointly. Thi…
AttributeHuman ParsingPose EstimationRecognizing Part Attributes with Insufficient Data
Recognizing attributes of objects and their parts is important to many computer vision applications. Although great progress has been made to apply object-level recognition, recognizing the attributes of parts remains le…
AttributeJoint-Partition Group Attention for skeleton-based action recognition
Skeleton-based action recognition aims to recognize human actions from the coordinates of human joints. By encoding coordinates as joint tokens, previous methods have successfully utilized the self-attention (SA) mechani…
Action RecognitionSkeleton Based Action Recognition