Related papers: SOLAR: Self-supervised Joint Learning for Symmetri…

Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we propose a Scalable Multilingual…

The Contrastive Language-Image Pre-training (CLIP) framework has become a widely used approach for multimodal representation learning, particularly in image-text retrieval and clustering. However, its efficacy is constrained by three key…

Understanding human instructions and accomplishing Vision-Language Navigation tasks in unknown environments is essential for robots. However, existing modular approaches heavily rely on the quality of training data and often exhibit poor…

Generating multi-contrasts/modal MRI of the same anatomy enriches diagnostic information but is limited in practice due to excessive data acquisition time. In this paper, we propose a novel deep-learning model for joint reconstruction and…

Text-to-Image Retrieval (T2IR) is a highly valuable task that aims to match a given textual query to images in a gallery. Existing benchmarks primarily focus on textual queries describing overall image semantics or foreground salient…

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated significant potential in recommendation systems. However, the effective application of MLLMs to multimodal sequential recommendation remains unexplored: A)…

In recent years, semi-supervised learning has been widely explored and shows excellent data efficiency for 2D data. There is an emerging need to improve data efficiency for 3D tasks due to the scarcity of labeled 3D data. This paper…

Medical image retrieval is essential for clinical decision-making and translational research, relying on discriminative visual representations. Yet, current methods remain fragmented, relying on separate architectures and training…

DNN-based cross-modal retrieval has become a research hotspot, by which users can search results across various modalities like image and text. However, existing methods mainly focus on the pairwise correlation and reconstruction error of…

In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…

Deep Metric Learning (DML) proposes to learn metric spaces which encode semantic similarities as embedding space distances. These spaces should be transferable to classes beyond those seen during training. Commonly, DML methods task…

When trying to answer complex questions, people often rely on multiple sources of information, such as visual, textual, and tabular data. Previous approaches to this problem have focused on designing input features or model structure in the…

Distance Metric Learning (DML) seeks to learn a discriminative embedding where similar examples are closer, and dissimilar examples are apart. In this paper, we address the problem of Semi-Supervised DML (SSDML) that tries to learn a metric…

Multi-view person association is a fundamental step towards multi-view analysis of human activities. Although the person re-identification features have been proven effective, they become unreliable in challenging scenes where persons share…

Supervised multi-modal learning involves mapping multiple modalities to a target label. Previous studies in this field have concentrated on capturing in isolation either the inter-modality dependencies (the relationships between different…

Densely annotating LiDAR point clouds is costly, which restrains the scalability of fully-supervised learning methods. In this work, we study the underexplored semi-supervised learning (SSL) in LiDAR segmentation. Our core idea is to…

Embedding models are a cornerstone of modern AI. Driven by Multimodal Large Language Models (MLLMs), they have made great progress in architecture and data curation, while the holistic paradigm is still limited to SSC, i.e., single input,…

Low-rank Multi-view Subspace Learning (LMvSL) has shown great potential in cross-view classification in recent years. Despite their empirical success, existing LMvSL based methods are incapable of well handling view discrepancy and…

Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A…

Sequential recommendation (SR) systems have evolved significantly over the past decade, transitioning from traditional collaborative filtering to deep learning approaches and, more recently, to large language models (LLMs). While the…