Similarity Learning with Spatial Constraints for Person Re-identification
Citations Over TimeTop 1% of 2016 papers
Abstract
Pose variation remains one of the major factors that adversely affect the accuracy of person re-identification. Such variation is not arbitrary as body parts (e.g. head, torso, legs) have relative stable spatial distribution. Breaking down the variability of global appearance regarding the spatial distribution potentially benefits the person matching. We therefore learn a novel similarity function, which consists of multiple sub-similarity measurements with each taking in charge of a subregion. In particular, we take advantage of the recently proposed polynomial feature map to describe the matching within each subregion, and inject all the feature maps into a unified framework. The framework not only outputs similarity measurements for different regions, but also makes a better consistency among them. Our framework can collaborate local similarities as well as global similarity to exploit their complementary strength. It is flexible to incorporate multiple visual cues to further elevate the performance. In experiments, we analyze the effectiveness of the major components. The results on four datasets show significant and consistent improvements over the state-of-the-art methods.
Related Papers
- → Reconstitution of Torso signaling in cultured cells suggests a role for both Trunk and Torso-like in receptor activation(2017)15 cited
- → Effects of Material Properties and Geometry on Electrocardiographic Forward Simulations(2000)60 cited
- → The Effects of Thoracic Inhomogeneities on the Relationship Between Epicardial and Torso Potentials(1986)81 cited
- A New Approach for Assessing Kinematics of Torso Twist in Baseball Batting: A Preliminary Report(2010)
- → Comparative Study on Body Suitability of Torso Patterns(2023)