Related papers: CPCL: Cross-Modal Prototypical Contrastive Learnin…

We focus on a relatively unexplored learning paradigm known as {\em Online Unsupervised Continual Learning} (O-UCL), where an agent receives a non-stationary, unlabeled data stream and progressively learns to identify an increasing number…

With growing public safety demands, text-based person anomaly search has emerged as a critical task, aiming to retrieve individuals with abnormal behaviors via natural language descriptions. Unlike conventional person search, this task…

This paper proposes the ViT Token Constraint and Multi-scale Memory bank (TCMM) method to address the patch noises and feature inconsistency in unsupervised person re-identification works. Many excellent methods use ViT features to obtain…

Contrastive learning and self-supervised techniques have gained prevalence in computer vision for the past few years. It is essential for medical image analysis, which is often notorious for its lack of annotations. Most existing…

Language-image pre-training is an effective technique for learning powerful representations in general domains. However, when directly turning to person representation learning, these general pre-training methods suffer from unsatisfactory…

Multi-modal contrastive learning (MMCL) has recently garnered considerable interest due to its superior performance in visual tasks, achieved by embedding multi-modal data, such as visual-language pairs. However, there still lack…

Technological advances facilitate the ability to acquire multimodal data, posing a challenge for recognition systems while also providing an opportunity to use the heterogeneous nature of the information to increase the generalization…

Learning medical visual representations directly from paired images and reports through multimodal self-supervised learning has emerged as a novel and efficient approach to digital diagnosis in recent years. However, existing models suffer…

Convolutional Dictionary Learning (CDL) has emerged as a powerful approach for signal representation by learning translation-invariant features through convolution operations. While existing CDL methods are predominantly designed and used…

With rapid advancements in depth sensors and deep learning, skeleton-based person re-identification (re-ID) models have recently achieved remarkable progress with many advantages. Most existing solutions learn single-level skeleton features…

Learning a deep model from small data is yet an opening and challenging problem. We focus on one-shot classification by deep learning approach based on a small quantity of training samples. We proposed a novel deep learning approach named…

Multiview clustering (MVC) aims to reveal the underlying structure of multiview data by categorizing data samples into clusters. Deep learning-based methods exhibit strong feature learning capabilities on large-scale datasets. For most…

The burgeoning presence of multimodal content-sharing platforms propels the development of personalized recommender systems. Previous works usually suffer from data sparsity and cold-start problems, and may fail to adequately explore…

Continual learning (CL) breaks off the one-way training manner and enables a model to adapt to new data, semantics and tasks continuously. However, current CL methods mainly focus on single tasks. Besides, CL models are plagued by…

Contrastive learning (CL) aims to learn useful representation without relying on expert annotations in the context of medical image segmentation. Existing approaches mainly contrast a single positive vector (i.e., an augmentation of the…

Fine-tuning vision-language models (VLMs) with abundant unlabeled data recently has attracted increasing attention. Existing methods that resort to the pseudolabeling strategy would suffer from heavily incorrect hard pseudolabels when VLMs…

Fonts convey different impressions to readers. These impressions often come from the font shapes. However, the correlation between fonts and their impression is weak and unstable because impressions are subjective. To capture such weak and…

Despite the availability of a huge amount of video data accompanied by descriptive texts, it is not always easy to exploit the information contained in natural language in order to automatically recognize video concepts. Towards this goal,…

Recent advances in vision language models (VLM) have been driven by contrastive models such as CLIP, which learn to associate visual information with their corresponding text descriptions. However, these models have limitations in…

Learning common subspace is prevalent way in cross-modal retrieval to solve the problem of data from different modalities having inconsistent distributions and representations that cannot be directly compared. Previous cross-modal retrieval…