Related papers: Contrastive Multi-Modal Hypergraph Reasoning for 3…

Multi-modal Contrastive Representation learning aims to encode different modalities into a semantically aligned shared space. This paradigm shows remarkable generalization ability on numerous downstream tasks across various modalities.…

Group Re-identification (G-ReID) faces greater complexity than individual Re-identification (ReID) due to challenges like mutual occlusion, dynamic member interactions, and evolving group structures. Prior graph-based approaches have aimed…

3D human mesh recovery from monocular RGB images aims to estimate anatomically plausible 3D human models for downstream applications, but remains challenging under partial or severe occlusions. Regression-based methods are efficient yet…

Hypergraphs provide a superior modeling framework for representing complex multidimensional relationships in the context of real-world interactions that often occur in groups, overcoming the limitations of traditional homogeneous graphs.…

Understanding dark scenes based on multi-modal image data is challenging, as both the visible and auxiliary modalities provide limited semantic information for the task. Previous methods focus on fusing the two modalities but neglect the…

Contrastive learning has emerged as a promising paradigm for 3D open-world understanding, i.e., aligning point cloud representation to image and text embedding space individually. In this paper, we introduce MixCon3D, a simple yet effective…

Graph clustering is essential in graph analysis for revealing structural patterns and node communities. Despite recent advances in self-supervised contrastive learning that have improved clustering via structural and attribute signals,…

This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty modeling and typically regress a single estimate for a given…

With the widespread use of mobile devices and the rapid growth of micro-video platforms such as TikTok and Kwai, the demand for personalized micro-video recommendation systems has significantly increased. Micro-videos typically contain…

Multimodal learning seeks to integrate information from heterogeneous sources, where signals may be shared across modalities, specific to individual modalities, or emerge only through their interaction. While self-supervised multimodal…

Advances in Deep Learning have recently made it possible to recover full 3D meshes of human poses from individual images. However, extension of this notion to videos for recovering temporally coherent poses still remains unexplored. A major…

Social relations are often used to improve recommendation quality when user-item interaction data is sparse in recommender systems. Most existing social recommendation models exploit pairwise relations to mine potential user preferences.…

Robotic detection of people in crowded and/or cluttered human-centered environments including hospitals, long-term care, stores and airports is challenging as people can become occluded by other people or objects, and deform due to…

Crowd counting models in highly congested areas confront two main challenges: weak localization ability and difficulty in differentiating between foreground and background, leading to inaccurate estimations. The reason is that objects in…

Contrastive self-supervised learning has recently benefited fMRI classification with inductive biases. Its weak label reliance prevents overfitting on small medical datasets and tackles the high intraclass variances. Nonetheless, existing…

Human mesh recovery can be approached using either regression-based or optimization-based methods. Regression models achieve high pose accuracy but struggle with model-to-image alignment due to the lack of explicit 2D-3D correspondences. In…

Establishing structure-property linkages in polycrystalline materials requires representative two- (2D) and three- (3D) dimensional microstructural inputs for full-field simulations. A core objective of microstructure characterization and…

In recent years, the use of edge information provided by knowledge graphs together with the advantages of higher-order connectivity in graph neural networks for recommendation systems has become an important research direction. However,…

Implementing cross-modal hashing between 2D images and 3D point-cloud data is a growing concern in real-world retrieval systems. Simply applying existing cross-modal approaches to this new task fails to adequately capture latent multi-modal…

This paper focuses on spatially consistent hundreds of human pose and shape reconstruction from a single large-scene image with various human scales under arbitrary camera FoVs (Fields of View). Due to the small and highly varying 2D human…