Pedestrian Attribute Recognition At Far Distance

By Yubin Deng, Ping Luo, Chen Change Loy, Xiaoou Tang. ACM Multimedia, 2014

477 citations recorded by the source corpus.

The capability of recognizing pedestrian attributes, such as gender and clothing style, at far distance, is of practical interest in far-view surveillance scenarios where face and body close-shots are hardly available. We make two contributions in this paper. First, we release a new pedestrian attribute dataset, which is by far the largest and most diverse of its kind. We show that the large-scale dataset facilitates the learning of robust attribute detectors with good generalization performance. Second, we present the benchmark performance by SVM-based method and propose an alternative approach that exploits context of neighboring pedestrian images for improved attribute inference.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c32cefb0c917bc0fa48f5ec2e914361a9f85b85f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Pedestrian detection aided by deep learning semantic tasks (2014, background): “This problem is challenging because of large variation and confusion in human body and background scene, as shown in Fig.1 (a), where the positive and hard negative patches have large ambiguity.”
Multi-Task Learning with Low Rank Attribute Embedding for Multi-Camera Person Re-Identification (2018, methodology): “As for attributes, using this descriptor as x, we learn binary SVMs referring to [44] to predict the same 20-bit attributes in [44] for PRID and 90-bit attributes in [67] for VIPeR.”
A large-scale car dataset for fine-grained categorization and verification (2015, background): “However, a large portion of the labeled attributes in the current attribute datasets [4], such as long hair and short pants lack strict criteria, which causes annotation ambiguities [1].”
Person Recognition in Personal Photo Collections (2017, unknown): ““PETA pedestrian attribute dataset” [74].”
Multi-Task Learning with Low Rank Attribute Embedding for Person Re-Identification (2015, methodology): “As for attributes, we learn binary SVMs as in [27] to predict the same 20-bit attributes in [27] for PRID and 90-bit attributes in [10] for VIPeR.”
Deep Attributes Driven Multi-Camera Person Re-identification (2016, methodology): “To conduct the ﬁrst stage training, we choose the PETA [42] dataset as the training set.”
Person Recognition in Personal Photo Collections (2015, methodology): “We also consider using the “PETA pedestrian attribute dataset” [11], which features 105 attributes annotations for 19 · 10(3) full-body pedestrian images.”