Many current successful Person Re-Identification(ReID) methods train a model with the softmax loss function to classify images of different persons and obtain the feature vectors at the same time. However, the underlying feature embedding space is ignored. In this paper, we use a modified softmax function, termed Sphere Softmax, to solve the classification problem and learn a hypersphere manifold embedding simultaneously. A balanced sampling strategy is also introduced. Finally, we propose a convolutional neural network called SphereReID adopting Sphere Softmax and training a single model end-to-end with a new warming-up learning rate schedule on four challenging datasets including Market-1501, DukeMTMC-reID, CHHK-03, and CUHK-SYSU. Experimental results demonstrate that this single model outperforms the state-of-the-art methods on all four datasets without fine-tuning or reranking. For example, it achieves 94.4% rank-1 accuracy on Market-1501 and 83.9% rank-1 accuracy on DukeMTMC-reID. The code and trained weights of our model will be released.
Video object tracking represents a very important computer vision domain. In this paper, a perceptual hashing based template-matching method for object tracking is proposed to efficiently track objects in challenging video sequences. In the tracking process, we first apply three existing basic perceptual hashing techniques to visual tracking, namely average hash (aHash), perceptive hash (pHash) and difference hash (dHash). Compared with previous tracking methods such as mean-shift or compressive tracking (CT), perceptual hashing-based tracking outperforms in terms of efficiency and accuracy. In order to further improve the accuracy of object localization and the robustness of tracking, we propose Laplace-based Hash (LHash) and Laplace-based Difference Hash (LDHash). By qualitative and quantitative comparison with some representative tracking algorithms, experimental results show that our improved perceptual hashing-based tracking algorithms perform favorably against the state-of-the-art algorithms under various challenging environments in terms of time cost, accuracy and robustness. Since our improved perceptual hashing can be a compact and efficient representation of objects, it can be further applied to fusing with depth information for more robust RGB-D video tracking.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.