Part feature learning plays a crucial role in achieving fine-grained semantic understanding in unsupervised vehicle re-identification. However, existing approaches directly model part and global features, which can easily lead to severe gradient vanishing issues due to their unequal feature information and unreliable pseudo-labels. To address this problem, in this article, we propose a triplet contrastive representation learning (TCRL) framework, which leverages cluster features to bridge the part features and global features for unsupervised vehicle re-identification. Specifically, TCRL devises three memory banks to store the instance/cluster features and proposes a proxy contrastive loss (PCL) to make contrastive learning between adjacent memory banks, thus presenting the associations between the part and global features as a transition of the part-cluster and cluster-global associations. Since the cluster memory bank copes with all the vehicle features, it can summarize them into a discriminative feature representation. To deeply exploit the instance/cluster information, TCRL proposes two additional loss functions. For the instance-level feature, a hybrid contrastive loss (HCL) re-defines the sample correlations by approaching the positive instance features and pushing all negative instance features away. For the cluster-level feature, a weighted regularization cluster contrastive loss (WRCCL) refines the pseudo labels by penalizing the mislabeled images according to the instance similarity. Extensive experiments show that TCRL outperforms many state-of-the-art unsupervised vehicle re-identification approaches.

In this paper, we study the problem of Text-to-Image Person Re-identification (TIReID), which aims to find images of the same identity described by a text sentence from a pool of candidate images. Benefiting from Vision-Language Pre-training, such as CLIP (Contrastive Language-Image Pretraining), the TIReID techniques have achieved remarkable progress recently. However, most existing methods only focus on instance-level matching and ignore identity-level matching, which involves associating multiple images and texts belonging to the same person. In this paper, we propose a novel prototypical prompting framework (Propot) designed to simultaneously model instance-level and identity-level matching for TIReID. Our Propot transforms the identity-level matching problem into a prototype learning problem, aiming to learn identity-enriched prototypes. Specifically, Propot works by 'initialize, adapt, enrich, then aggregate'. We first use CLIP to generate high-quality initial prototypes. Then, we propose a domain-conditional prototypical prompting (DPP) module to adapt the prototypes to the TIReID task using task-related information. Further, we propose an instance-conditional prototypical prompting (IPP) module to update prototypes conditioned on intra-modal and inter-modal instances to ensure prototype diversity. Finally, we design an adaptive prototype aggregation module to aggregate these prototypes, generating final identity-enriched prototypes. With identity-enriched prototypes, we diffuse its rich identity information to instances through prototype-to-instance contrastive loss to facilitate identity-level matching. Extensive experiments conducted on three benchmarks demonstrate the superiority of Propot compared to existing TIReID methods.

Text-to-image person re-identification (TIReID) retrieves pedestrian images of the same identity based on a query text. However, existing methods typically treat it as a one-to-one image-text matching problem, only focusing on the relationship between image-text pairs within a view. The many-to-many matching between image-text pairs across views under the same identity is not taken into account, which is one of the main reasons for the poor performance of existing methods. To this end, we propose a simple yet effective framework, called LCR2S, for modeling many-to-many correspondences of the same identity by learning comprehensive representations for both modalities from a novel perspective. We construct a support set for each image (text) by using other images (texts) under the same identity and design a multi-head attentional fusion module to fuse the image (text) and its support set. The resulting enriched image and text features are aligned to train a "richer" TIReID model with many-to-many correspondences. Since the support set is unavailable during inference, we propose to distill the knowledge learned by the "richer" model into a lightweight model for inference with a single image/text as input. The lightweight model focus on semantic association and reasoning of multi-view information, which can generate a comprehensive representation containing multi-view information with only a single-view input to perform accurate text-to-image retrieval during inference. In particular, we use the intra-modal features and inter-modal semantic relations of the "richer" model to supervise the lightweight model to inherit its powerful capability. Extensive experiments demonstrate the effectiveness of LCR2S, and it also achieves new state-of-the-art performance on three popular TIReID datasets.

The technology of laser projection positioning is widely applied in advanced manufacturing fields (e.g. composite plying, parts location and installation). In order to use it better, a laser projection positioning (LPP) system is designed and implemented. Firstly, the LPP system is built by a laser galvanometric scanning (LGS) system and a binocular vision system. Applying Single-hidden Layer Feed-forward Neural Network (SLFN), the system model is constructed next. Secondly, the LGS system and the binocular system, which are respectively independent, are integrated through a datadriven calibration method based on extreme learning machine (ELM) algorithm. Finally, a projection positioning method is proposed within the framework of the calibrated SLFN system model. A well-designed experiment is conducted to verify the viability and effectiveness of the proposed system. In addition, the accuracy of projection positioning are evaluated to show that the LPP system can achieves the good localization effect.

Despite the enormous progress, face animation is still considered one of the toughest tasks in computer society. In many cases, the facial data come from real human individuals by various 3D coordinate measuring equipments to get more realistic models. The animation irrelevant parts in the scanned data make the automatic face correspondence, which is a key and difficult problem in face animation, even harder. We present a pipeline that can get quite reasonable animation result fully automatically from raw scanned facial meshes, applications of face morphing and expression cloning are demonstrated.

Polygon meshes are ubiquitous in geometric model representation. Segmentation and parametrization of arbitrary polygon meshes are closely related and crucial in many applications. The primary aim of this paper is to find an efficient and practical way to segment and resample geometric models. We automatically generate a triangular patch network by a simplification algorithm. A simple and cheap algorithm is put forward for calculating the approximate shortest path between two points on triangle mesh, which serves for patch boundary of the segmentation. A set of interactive tools provides users with more freedom to control the final segmentation. The mesh parametrization algorithm in this paper can efficiently map a disk topology mesh surface to an isomorphic planar mesh without fixing boundary points. Ways are also provided to map the planar mesh with natural boundary to specific parameter domain, e.g. square or circular domain. The proposed method can be used in diverse applications, such as patchwise freeform surfaces fitting, multi-resolution analysis, texture mapping, remeshing of arbitrary polygon mesh and blank design of sheet metal forming. Examples are included to demonstrate the efficiency and quality of our method.