Related papers: Learning Progressive Modality-shared Transformers …
Recent advancements in deep learning have enabled the development of generalizable models that achieve state-of-the-art performance across various imaging tasks. Vision Transformer (ViT)-based architectures, in particular, have demonstrated…
Due to the ever-growing diversity of the data source, multi-modality feature learning has attracted more and more attention. However, most of these methods are designed by jointly learning feature representation from multi-modalities that…
Identifying the same individual across different scenes is an important yet difficult task in intelligent video surveillance. Its main difficulty lies in how to preserve similarity of the same person against large appearance and structure…
Fine-grained visual recognition is to classify objects with visually similar appearances into subcategories, which has made great progress with the development of deep CNNs. However, handling subtle differences between different…
Video-based Person Re-IDentification (VPReID) aims to retrieve the same person from videos captured by non-overlapping cameras. At extreme far distances, VPReID is highly challenging due to severe resolution degradation, drastic viewpoint…
Person re-identification (Re-ID) aims to match identities across non-overlapping camera views. Researchers have proposed many supervised Re-ID models which require quantities of cross-view pairwise labelled data. This limits their…
Person re-identification (ReID) aims to match people across multiple non-overlapping video cameras deployed at different locations. To address this challenging problem, many metric learning approaches have been proposed, among which triplet…
Multi-modal vehicle Re-Identification (ReID) aims to leverage complementary information from RGB, Near Infrared (NIR), and Thermal Infrared (TIR) modalities to retrieve the same vehicle. The challenges of multi-modal vehicle ReID arise from…
Lifelong person Re-IDentification (LReID) aims to match the same person employing continuously collected individual data from different scenarios. To achieve continuous all-day person matching across day and night, Visible-Infrared Lifelong…
Real-world object re-identification (ReID) systems often face modality inconsistencies, where query and gallery images come from different sensors (e.g., RGB, NIR, TIR). However, most existing methods assume modality-matched conditions,…
Person re-identification (ReID) aims to retrieve images of a target person from the gallery set, with wide applications in medical rehabilitation and public security. However, traditional person ReID models are typically uni-modal,…
Deep Metric Learning (DML) methods have been proven relevant for visual similarity learning. However, they sometimes lack generalization properties because they are trained often using an inappropriate sample selection strategy or due to…
Learning multi-modal representations is an essential step towards real-world robotic applications, and various multi-modal fusion models have been developed for this purpose. However, we observe that existing models, whose objectives are…
Semi-supervised learning has emerged as a widely adopted technique in the field of medical image segmentation. The existing works either focuses on the construction of consistency constraints or the generation of pseudo labels to provide…
Extracting robust feature representation is one of the key challenges in object re-identification (ReID). Although convolution neural network (CNN)-based methods have achieved great success, they only process one local neighborhood at a…
Image features from a small local region often give strong evidence in person re-identification task. However, CNN suffers from paying too much attention on the most salient local areas, thus ignoring other discriminative clues, e.g., hair,…
Visible-infrared person re-identification (VI-ReID) aims to match specific pedestrian images from different modalities. Although suffering an extra modality discrepancy, existing methods still follow the softmax loss training paradigm,…
RGB-Infrared person re-identification (RGB-IR Re-ID) aims to match persons from heterogeneous images captured by visible and thermal cameras, which is of great significance in the surveillance system under poor light conditions. Facing…
This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images. Conventional deep metric learning methods produce confident semantic distances between images regardless of the…
Lifelong person re-identification (LReID) aims to learn from varying domains to obtain a unified person retrieval model. Existing LReID approaches typically focus on learning from scratch or a visual classification-pretrained model, while…