Related papers: Cross-Model Cross-Stream Learning for Self-Supervi…

Cross-modal retrieval has become a highlighted research topic for retrieval across multimedia data such as image and text. A two-stage learning framework is widely adopted by most existing methods based on Deep Neural Network (DNN): The…

Multi-view clustering has shown to be an effective method for analyzing underlying patterns in multi-view data. The performance of clustering can be improved by learning the consistency and complementarity between multi-view features,…

Skeleton sequence representation learning has shown great advantages for action recognition due to its promising ability to model human joints and topology. However, the current methods usually require sufficient labeled data for training…

Contrastive Learning (CL), a leading paradigm in Self-Supervised Learning (SSL), typically relies on pairs of data views generated through augmentation. While multiple augmentations per instance (more than two) improve generalization in…

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality…

Previous work on action representation learning focused on global representations for short video clips. In contrast, many practical applications, such as video alignment, strongly demand learning the intensive representation of long…

Multi-domain learning (MDL) refers to simultaneously constructing a model or a set of models on datasets collected from different domains. Conventional approaches emphasize domain-shared information extraction and domain-private information…

Co-Salient Object Detection (CoSOD) aims at detecting common salient objects within a group of relevant source images. Most of the latest works employ the attention mechanism for finding common objects. To achieve accurate CoSOD results…

Continual Learning (CL) investigates how to train Deep Networks on a stream of tasks without incurring forgetting. CL settings proposed in literature assume that every incoming example is paired with ground-truth annotations. However, this…

Spatial and temporal stream model has gained great success in video action recognition. Most existing works pay more attention to designing effective features fusion methods, which train the two-stream model in a separate way. However, it's…

Language-supervised vision models have recently attracted great attention in computer vision. A common approach to build such models is to use contrastive learning on paired data across the two modalities, as exemplified by Contrastive…

Extracting image semantics effectively and assigning corresponding labels to multiple objects or attributes for natural images is challenging due to the complex scene contents and confusing label dependencies. Recent works have focused on…

Session-based recommendation, which aims to predict the next item of users' interest as per an existing sequence interaction of items, has attracted growing applications of Contrastive Learning (CL) with improved user and item…

Activity cliffs, which refer to pairs of molecules that are structurally similar but show significant differences in their potency, can lead to model representation collapse and make the model challenging to distinguish them. Our research…

We propose a novel clustering approach for point-cloud segmentation based on supervised contrastive metric learning (CML). Rather than predicting cluster assignments or object-centric variables, the method learns a latent representation in…

This paper introduces a novel approach named CrossVideo, which aims to enhance self-supervised cross-modal contrastive learning in the field of point cloud video understanding. Traditional supervised learning methods encounter limitations…

To extract robust and generalizable skeleton action recognition features, large amounts of well-curated data are typically required, which is a challenging task hindered by annotation and computation costs. Therefore, unsupervised…

Self-Supervised Learning (SSL) is a paradigm that leverages unlabeled data for model training. Empirical studies show that SSL can achieve promising performance in distribution shift scenarios, where the downstream and training…

In this paper, we address a highly challenging yet critical task: unsupervised long-term person re-identification with clothes change. Existing unsupervised person re-id methods are mainly designed for short-term scenarios and usually rely…

In this paper we address the problem of learning robust cross-domain representations for sketch-based image retrieval (SBIR). While most SBIR approaches focus on extracting low- and mid-level descriptors for direct feature matching, recent…