Related papers: Dynamic Prototype Mask for Occluded Person Re-Iden…
Predictive Business Process Monitoring (PBPM) aims to forecast future outcomes of ongoing business processes. However, existing methods often lack flexibility to handle real-world challenges such as simultaneous events, class imbalance, and…
While deep learning-based image reconstruction methods have shown significant success in removing objects from pictures, they have yet to achieve acceptable results for attributing consistency to gender, ethnicity, expression, and other…
Unsupervised person re-identification (re-ID) has become an important topic due to its potential to resolve the scalability problem of supervised re-ID models. However, existing methods simply utilize pseudo labels from clustering for…
Deep neural networks (DNNs) and generative AI (GenAI) are increasingly vulnerable to backdoor attacks, where adversaries embed triggers into inputs to cause models to misclassify or misinterpret target labels. Beyond traditional…
We concentrate on a novel human-centric image synthesis task, that is, given only one reference facial photograph, it is expected to generate specific individual images with diverse head positions, poses, facial expressions, and…
Person Re-Identification (Re-Id) in occlusion scenarios is a challenging problem because a pedestrian can be partially occluded. The use of local information for feature extraction and matching is still necessary. Therefore, we propose a…
Diabetic retinopathy (DR) grading plays a critical role in early clinical intervention and vision preservation. Recent explorations predominantly focus on visual lesion feature extraction through data processing and domain decoupling…
In this work, we present a deep convolutional pyramid person matching network (PPMN) with specially designed Pyramid Matching Module to address the problem of person re-identification. The architecture takes a pair of RGB images as input,…
Diffusion Probabilistic Models (DPMs) have emerged as the de facto approach for high-fidelity image synthesis, operating diffusion processes on continuous VAE latent, which significantly differ from the text generation methods employed by…
Person re-identification is indeed a challenging visual recognition task due to the critical issues of human pose variation, human body occlusion, camera view variation, etc. To address this, most of the state-of-the-art approaches are…
Person re-identification consists in recognizing an individual that has already been observed over a network of cameras. It is a novel and challenging research topic in computer vision, for which no reference framework exists yet. Despite…
Face representation learning using datasets with a massive number of identities requires appropriate training methods. Softmax-based approach, currently the state-of-the-art in face recognition, in its usual "full softmax" form is not…
While self-supervised graph pretraining techniques have shown promising results in various domains, their application still experiences challenges of limited topology learning, human knowledge dependency, and incompetent multi-level…
Like masked language modeling (MLM) in natural language processing, masked image modeling (MIM) aims to extract valuable insights from image patches to enhance the feature extraction capabilities of the underlying deep neural network (DNN).…
Diffusion Probabilistic Models (DPMs) have recently demonstrated impressive results on various generative tasks.Despite its promises, the learned representations of pre-trained DPMs, however, have not been fully understood. In this paper,…
We present X-MDPT ($\underline{Cross}$-view $\underline{M}$asked $\underline{D}$iffusion $\underline{P}$rediction $\underline{T}$ransformers), a novel diffusion model designed for pose-guided human image generation. X-MDPT distinguishes…
Prompt tuning and adapter tuning have shown great potential in transferring pre-trained vision-language models (VLMs) to various downstream tasks. In this work, we design a new type of tuning method, termed as regularized mask tuning, which…
Human pose estimation aims to figure out the keypoints of all people in different scenes. Current approaches still face some challenges despite promising results. Existing top-down methods deal with a single person individually, without the…
For long time, person re-identification and image search are two separately studied tasks. However, for person re-identification, the effectiveness of local features and the "query-search" mode make it well posed for image search…
Supervised Person Re-identification (Person ReID) methods have achieved excellent performance when training and testing within one camera network. However, they usually suffer from considerable performance degradation when applied to…