UAV surveillance offers a unique aerial perspective, enabling the monitoring of large areas and capturing targets from angles that fixed ground cameras cannot achieve. UAV-based object re-identification (ReID) differs from the extensively studied city camera scenarios, as it involves identifying specific objects in aerial images captured from a dynamic bird's-eye view. The challenge lies in the significant variation in object perspectives and the often uncertain rotational changes captured by UAVs. Existing ReID methods designed for city cameras struggle to adapt to these rotational variations. To address these challenges, we propose a Transformer-based learnable rotation generalization enhancement method specifically for UAV-based ReID. To improve the model's adaptability to uncertain rotational changes, we introduce a learnable feature-level rotation simulation technique that generates multiple rotated features. Building on this, we design a rotation diversification loss to decorrelate different rotated features, ensuring a rich feature representation. Additionally, to mitigate the negative effects of image-level rotation augmentation, we propose instance-level and distribution-level rotation invariance regularization. This approach establishes explicit associations between images and their rotated counterparts, facilitating the learning of visually consistent rotation-invariant features. Instance-level constraints ensure that detailed features remain consistent during rotation, while distribution-level constraints maintain the model's semantic understanding. Notably, our method demonstrates strong versatility, covering a wide range of objects, including persons, vehicles, and various animals. Evaluations on multiple UAV-collected person and vehicle ReID datasets, as well as several animal datasets, consistently show outstanding performance, underscoring its robustness and adaptability to the unique challenges posed by UAV-based ReID.

Object Re-identification (Re-ID) aims to identify specific objects across different times and scenes, which is a widely researched task in computer vision. For a prolonged period, this field has been predominantly driven by deep learning technology based on convolutional neural networks. In recent years, the emergence of Vision Transformers has spurred a growing number of studies delving deeper into Transformer-based Re-ID, continuously breaking performance records and witnessing significant progress in the Re-ID field. Offering a powerful, flexible, and unified solution, Transformers cater to a wide array of Re-ID tasks with unparalleled efficacy. This paper provides a comprehensive review and in-depth analysis of the Transformer-based Re-ID. In categorizing existing works into Image/Video-Based Re-ID, Re-ID with limited data/annotations, Cross-Modal Re-ID, and Special Re-ID Scenarios, we thoroughly elucidate the advantages demonstrated by the Transformer in addressing a multitude of challenges across these domains. Considering the trending unsupervised Re-ID, we propose a new Transformer baseline, UntransReID, achieving state-of-the-art performance on both single/cross modal tasks. For the under-explored animal Re-ID, we devise a standardized experimental benchmark and conduct extensive experiments to explore the applicability of Transformer for this task and facilitate future research. Finally, we discuss some important yet under-investigated open issues in the large foundation model era, we believe it will serve as a new handbook for researchers in this field. A periodically updated website will be available at https://github.com/mangye16/ReID-Survey .

Pedestrian attribute recognition (PAR) aims to identify the attributes like gender, hat, and upper clothes color of a captured pedestrian, which is a challenging but practical research problem in security applications. One key consideration in PAR is that the uniform extracted features of the backbone cannot effectively fulfill the requirements for classifying each attribute. In the scope of the MMVRAC challenge, this paper introduces the Attribute-aware Multi-layer Projector (AMLP) to enhance the performance in the UAVHuman pedestrian attribute recognition benchmark. The AMLP transforms the uniform pedestrian feature into attribute-aware representation, thereby enhancing the subsequent prediction accuracy. Furthermore, we validate the validity of the AMLP and develop a strong pipeline for PAR based on sufficient experiments, which validates the effectiveness of various commonly employed modules used to improve PAR, such as data augmentation, label smoothing or dropout.

Wildlife ReID involves utilizing visual technology to identify specific individuals of wild animals in different scenarios, holding significant importance for wildlife conservation, ecological research, and environmental monitoring. Existing wildlife ReID methods are predominantly tailored to specific species, exhibiting limited applicability. Although some approaches leverage extensively studied person ReID techniques, they struggle to address the unique challenges posed by wildlife. Therefore, in this paper, we present a unified, multi-species general framework for wildlife ReID. Given that high-frequency information is a consistent representation of unique features in various species, significantly aiding in identifying contours and details such as fur textures, we propose the Adaptive High-Frequency Transformer model with the goal of enhancing high-frequency information learning. To mitigate the inevitable high-frequency interference in the wilderness environment, we introduce an object-aware high-frequency selection strategy to adaptively capture more valuable high-frequency components. Notably, we unify the experimental settings of multiple wildlife datasets for ReID, achieving superior performance over state-of-the-art ReID methods. In domain generalization scenarios, our approach demonstrates robust generalization to unknown species. Code is available at https://github.com/JigglypuffStitch/AdaFreq.git .

Recognizing a target of interest from the UAVs is much more challenging than the existing object re-identification tasks across multiple city cameras. The images taken by the UAVs usually suffer from significant size difference when generating the object bounding boxes and uncertain rotation variations. Existing methods are usually designed for city cameras, incapable of handing the rotation issue in UAV scenarios. A straightforward solution is to perform the image-level rotation augmentation, but it would cause loss of useful information when inputting the powerful vision transformer as patches. This motivates us to simulate the rotation operation at the patch feature level, proposing a novel rotation invariant vision transformer (RotTrans). This strategy builds on high-level features with the help of the specificity of the vision transformer structure, which enhances the robustness against large rotation differences. In addition, we design invariance constraint to establish the relationship between the original feature and the rotated features, achieving stronger rotation invariance. Our proposed transformer tested on the latest UAV datasets greatly outperforms the current state-of-the-arts, which is 5.9% and 4.8% higher than the highest mAP and Rank1. Notably, our model also performs competitively for the person re-identification task on traditional city cameras. In particular, our solution wins the first place in the UAV-based person re-recognition track in the Multi-Modal Video Reasoning and Analyzing Competition held in ICCV 2021. Code is available at https://github.com/whucsy/RotTrans.