论文题目：Text-based Person Search via Multi-Granularity Embedding Learning

论文作者：Chengji Wang, Zhiming Luo, Yaojin Lin, Shaozi Li.

论文摘要：

Most existing text-based person search methods highly depend on exploring the corresponding relations between the regions of image and the words in sentence. However, these methods correlated image regions and words in the same semantic granularity. It 1) results to construct irrelevant corresponding relations between image and text, 2) causes to ambiguity embedding problem.In this study, we propose a novel multi-granularity embedding learning model for text-based person search. It generates multi-granularity embeddings of partial person body in a coarse-to-fine manner by revisiting the person image at different spatial scales. Specifically, we distill the partial knowledge from image scrips to guide the model to adaptively select the semantically relevant words from text. It can learn discriminative and modality-invariant visual-textual embeddings.In addition, we integrate the partial embeddings at each granularity and perform multi-granularity image-text matching. Extensive experiments validate the effectiveness of our method. It achieves new state-of-the-art performance due to the learned discriminative partial embeddings.

论文题目：A Multi-Constraint Similarity Learning with Adaptive Weighting for Visible-Thermal Person Re-Identification

论文作者：Yongguo Ling, Zhiming Luo, Yaojin Lin, Shaozi Li.

论文摘要：

The challenges of visible-thermal person re-identification (VT-ReID) lies in the inter-modality discrepancy and the intra-modality variations. An appropriate metric learning plays a crucial role in optimizing the feature similarity between the two modalities. However,  most existing metric learning-based methods mainly constrain the similarity between individual instances or class centers, which are inadequate to explore the rich data relationships in the cross-modality data. Besides, most of these methods fail to consider the importance of different pairs, incurring an inefficiency and ineffectiveness of optimization. To address these issues, we propose a Multi-Constraint (MC) similarity learning method that jointly considers the cross-modality relationships from three different aspects, i.e., Instance-to-Instance (I2I), Center-to-Instance (C2I), and Center-to-Center (C2C). Moreover, we devise an Adaptive Weighting Loss (AWL) function to implement the MC efficiently. In the AWL, we first use an adaptive margin pair mining to select informative pairs and then adaptively adjust weights of mined pairs based on their similarity. Finally, the mined and weighted pairs are used for the metric learning. Extensive experiments on two benchmark datasets demonstrate the superior performance of the proposed over the state-of-the-art methods.