ABSTRACT
Recognising human attributes from surveillance footage is widely studied for attribute-based re-identification. However, most works assume coarse, expertly-defined categories, ineffective in describing challenging images. Such brittle representations are limited in descriminitive power and hamper the efficacy of learnt estimators. We aim to discover more relevant and precise subject descriptions, improving image retrieval and closing the semantic gap. Inspired by fine-grained and relative attributes, we introduce super-fine attributes, which now describe multiple, integral concepts of a single trait as multi-dimensional perceptual coordinates. Crowd prototyping facilitates efficient crowdsourcing of super-fine labels by pre-discovering salient perceptual concepts for prototype matching. We re-annotate gender, age and ethnicity traits from PETA, a highly diverse (19K instances, 8.7K identities) amalgamation of 10 re-id datasets including VIPER, CUHK and TownCentre. Employing joint attribute regression with the ResNet-152 CNN, we demonstrate substantially improved ranked retrieval performance with super-fine attributes in comparison to conventional binary labels, reporting up to a 11.2 and 14.8 percent mAP improvement for gender and age, further surpassed by ethnicity. We also find our 3 super-fine traits to outperform 35 binary attributes by 6.5 percent mAP for subject retrieval in a challenging zero-shot identification scenario.
