Given a query image from a camera, person re-identification (Re-ID) can retrieve the images of the same identity from a gallery, the images of which are captured by the other cameras. Therefore, person Re-ID has been widely used in the field of video surveillance. However, person Re-ID still suffers from a series of challenges, such as illumination changes, pose variations, and occlusions. Although the person Re-ID methods based on attention mechanism give an effective and feasible solution for the above challenges, attention mechanism may make a network focus too much on the most salient discriminative features and ignore other potential discriminative features. To solve this problem, we propose a two-level salient feature complementary network (TSFC-Net) to extract the most salient discriminative features and the secondary salient discriminative features of pedestrian images for person Re-ID. Specifically, TSFC-Net first extracts the most salient discriminative features of pedestrian images by embedding the spatial and channel attention modules in the backbone network, and then extracts the secondary salient discriminative features of pedestrian images by a secondary salient feature mining module (SSFM). Since the final features of pedestrian images fuse the most salient discriminative features and the secondary salient discriminative features, TSFC-Net can significantly improve the richness and discrimination capability of pedestrian representations. In addition, we conduct extensive experiments on the Market-1501, DukeMTMC-reID, and CUHK03 data sets, and the experimental results indicate that our TSFC-Net has a better performance compared with most of the state-of-the-art person Re-ID methods.

Most of existing local-based person re-identification (re-ID) methods extract powerful feature representations from multiple body regions of a pedestrian. However, local-based person re-ID methods employ horizontal or grid slicing to divide pedestrian images, which can easily cause network redundancy and misalignment of pedestrian body parts. Attention mechanisms have been recently introduced to computer vision tasks to strengthen local salient features and suppress irrelevant features simultaneously. However, attention mechanisms overemphasize local salient features, which may lead to potential significant information being missed. To address the above issues, we proposed a local information interaction enhancement network (LIEN) for person re-ID. The network integrates attention mechanism with local-based strategy to achieve mutually facilitating and complementary effects. Specifically, LIEN was composed of three parts: a backbone network, a dual attention module (DAM), and a local information interaction module (LIM). DAM was used to guide the backbone network to extract the local salient information, and LIM was used to mine the potential significant information that DAM ignored by exploring the correlations between different channel-level local features. With the combination of DAM and LIM, LIEN mined the salient features while obtaining more potential effective features. In particular, the way that it extracts local features, LIEN effectively avoided pedestrian misalignment caused by uniformly dividing pedestrian images. We evaluated the performance of LIEN on public person datasets, and experimental results indicated that LIEN achieved a more advanced performance.

Monocular 3D object detection has attracted attention due to its cost-effectiveness and ease of deployment. To improve detection performance, current methods commonly adopt data augmentation strategies to increase sample diversity. However, these approaches often rely on additional data or external models, and may introduce noise interference. Meanwhile, most methods neglect the widespread occlusion problem in real world scenarios, which significantly restricts further progress in detection performance. To address these challenges, we propose MonoDAPE, a monocular 3D object detection framework that integrates a Data Augmentation strategy named Cut-Clone3D and an occlusion Perception Enhancement (OPE) module. Specifically, Cut-Clone3D enriches sample and object distributions by seamlessly transplanting annotated objects into novel 3D scenes while strictly adhering to geometric projection constraints. The OPE module simulates realistic occlusion by generating random masks according to occlusion priors and substituting features of non-occluded objects with those from occluding objects, ensuring the continuity and asymmetry of occlusion. Moreover, we introduce a depth consistency loss that adjusts the distance relationship between mutually occluded objects, further improving prediction robustness. We conducted extensive experiments on the KITTI dataset to validate the effectiveness of our approach. On the KITTI test set, MonoDAPE achieved AP_3D (IoU = 0.7, Car) of 27.24%, 20.41%, and 17.52% at the easy, moderate, and hard levels, respectively, demonstrating state of-the-art performance.

With growing concerns over data privacy, researchers have started using virtual data as an alternative to sensitive real-world images for training person re-identification (Re-ID) models. However, existing virtual datasets produced by game engines still face challenges such as complex construction and poor domain generalization, making them difficult to apply in real scenarios. To address these challenges, we propose a Dual-stage Prompt-driven Privacy-preserving Paradigm (DPPP). In the first stage, we generate rich prompts incorporating multi-dimensional attributes such as pedestrian appearance, illumination, and viewpoint that drive the diffusion model to synthesize diverse data end-to-end, building a large-scale virtual dataset named GenePerson with 130,519 images of 6,641 identities. In the second stage, we propose a Prompt-driven Disentanglement Mechanism (PDM) to learn domain-invariant generalization features. With the aid of contrastive learning, we employ two textual inversion networks to map images into pseudo-words representing style and content, respectively, thereby constructing style-disentangled content prompts to guide the model in learning domain-invariant content features at the image level. Experiments demonstrate that models trained on GenePerson with PDM achieve state-of-the-art generalization performance, surpassing those on popular real and virtual Re-ID datasets.