Most existing Re-IDentification (Re-ID) methods are highly dependent on precise bounding boxes that enable images to be aligned with each other. However, due to the challenging practical scenarios, current detection models often produce inaccurate bounding boxes, which inevitably degenerate the performance of existing Re-ID algorithms. In this paper, we propose a novel coarse-to-fine pyramid model to relax the need of bounding boxes, which not only incorporates local and global information, but also integrates the gradual cues between them. The pyramid model is able to match at different scales and then search for the correct image of the same identity, even when the image pairs are not aligned. In addition, in order to learn discriminative identity representation, we explore a dynamic training scheme to seamlessly unify two losses and extract appropriate shared information between them. Experimental results clearly demonstrate that the proposed method achieves the state-of-the-art results on three datasets. Especially, our approach exceeds the current best method by 9.5% on the most challenging CUHK03 dataset.

The 3D CNN-based classification algorithm is a promising tool for the diagnosis of pre-invasive and invasive lung cancer and for the treatment choice decision.

A better understanding of the breast cancer online narrative is important for a clearer conceptualizing of the role of online platforms in mediating health related support. Sentiment analysis was conducted on a breast cancer online support group regarding Tamoxifen to understand users’ emotions and opinions. This analysis was then contextualized within online social support literature. Out of the 498 users, the most active users were 80% more positive than least active users while least active users were 48% more negative than most active ones; both differences were statistically significant. The higher the stage of cancer a user had, the less likelihood that she would have posted, and if she were to post, the post would have focused on her side effects and the anxiety/sadness that tailgates those side effects. The lower the stage of cancer a user had, the more likelihood that she would have posted, and additionally remained active on the forum and encouraged more (online) social support. This finding suggests that the online support platform may provide a context that exacerbates support for like-minded users where stronger ties are created around a specific sentiment within the community with less connection from those with dissimilar sentiments to the dominant group.

Text-based person search aims at retrieving target person in an image gallery using a descriptive sentence of that person. It is very challenging since modality gap makes effectively extracting discriminative features more difficult. Moreover, the inter-class variance of both pedestrian images and descriptions is small. Hence, comprehensive information is needed to align visual and textual clues across all scales. Most existing methods merely consider the local alignment between images and texts within a single scale (e.g. only global scale or only partial scale) or simply construct alignment at each scale separately. To address this problem, we propose a method that is able to adaptively align image and textual features across all scales, called NAFS (i.e. Non-local Alignment over Full-Scale representations). Firstly, a novel staircase network structure is proposed to extract full-scale image features with better locality. Secondly, a BERT with localityconstrained attention is proposed to obtain representations of descriptions at different scales. Then, instead of separately aligning features at each scale, a novel contextual non-local attention mechanism is applied to simultaneously discover latent alignments across all scales. The experimental results show that our method outperforms the stateof-the-art methods by 5.53% in terms of top-1 and 5.35% in terms of top-5 on text-based person search dataset. The code is available at https : / / github . com / TencentYoutuResearch/PersonReID-NAFS

Although great progress in supervised person re-identification (Re-ID) has been made recently, due to the viewpoint variation of a person, Re-ID remains a massive visual challenge. Most existing viewpoint-based person Re-ID methods project images from each viewpoint into separated and unrelated sub-feature spaces. They only model the identity-level distribution inside an individual viewpoint but ignore the underlying relationship between different viewpoints. To address this problem, we propose a novel approach, called Viewpoint-Aware Loss with Angular Regularization (VA-reID). Instead of one subspace for each viewpoint, our method projects the feature from different viewpoints into a unified hypersphere and effectively models the feature distribution on both the identity-level and the viewpoint-level. In addition, rather than modeling different viewpoints as hard labels used for conventional viewpoint classification, we introduce viewpoint-aware adaptive label smoothing regularization (VALSR) that assigns the adaptive soft label to feature representation. VALSR can effectively solve the ambiguity of the viewpoint cluster label assignment. Extensive experiments on the Market1501 and DukeMTMC-reID datasets demonstrated that our method outperforms the state-of-the-art supervised Re-ID methods.