相关论文: M$^5$L: Multi-Modal Multi-Margin Metric Learning f…

RGBT tracking has been widely used in various fields such as robotics, surveillance processing, and autonomous driving. Existing RGBT trackers fully explore the spatial information between the template and the search region and locate the…

We explore the potential of large-scale noisily labeled data to enhance feature learning by pretraining semantic segmentation models within a multi-modal framework for geospatial applications. We propose a novel Cross-modal Sample Selection…

We explore learning pixelwise correspondences between images of deformable objects in different configurations. Traditional correspondence matching approaches such as SIFT, SURF, and ORB can fail to provide sufficient contextual information…

Multimodal learning with incomplete modality is practical and challenging. Recently, researchers have focused on enhancing the robustness of pre-trained MultiModal Transformers (MMTs) under missing modality conditions by applying learnable…

In recent years, the remarkable success of deep neural networks (DNNs) in computer vision is largely due to large-scale, high-quality labeled datasets. Training directly on real-world datasets with label noise may result in overfitting. The…

Training of large-scale models is both computationally intensive and often constrained by the availability of labeled data. Model merging offers a compelling alternative by directly integrating the weights of multiple source models without…

Multimodal recommendation has emerged as a promising solution to alleviate the cold-start and sparsity problems in collaborative filtering by incorporating rich content information, such as product images and textual descriptions. However,…

Incorrectly labelled training data are frustratingly ubiquitous in both benchmark and specially curated datasets. Such mislabelling clearly adversely affects the performance and generalizability of models trained through supervised learning…

Multi-label learning in the presence of missing labels (MLML) is a challenging problem. Existing methods mainly focus on the design of network structures or training schemes, which increase the complexity of implementation. This work seeks…

Multi-spectral imagery is a valuable input signal for Remote Sensing applications, such as land-use and land-cover classification and environmental monitoring. However, generalist Large Multi-modal Models (LMMs) are typically trained on RGB…

Gait recognition aims at identifying the pedestrians at a long distance by their biometric gait patterns. It is inherently challenging due to the various covariates and the properties of silhouettes (textureless and colorless), which result…

Visible-modal object tracking gives rise to a series of downstream multi-modal tracking tributaries. To inherit the powerful representations of the foundation model, a natural modus operandi for multi-modal tracking is full fine-tuning on…

Model-Agnostic Meta-Learning (MAML) is one of the most successful meta-learning techniques for few-shot learning. It uses gradient descent to learn commonalities between various tasks, enabling the model to learn the meta-initialization of…

The development of federated learning (FL) methods, which aim to learn from distributed databases (i.e., clients) without accessing data on clients, has recently attracted great attention. Most of these methods assume that the clients are…

The task of building footprint segmentation has been well-studied in the context of remote sensing (RS) as it provides valuable information in many aspects, however, difficulties brought by the nature of RS images such as variations in the…

Deep multimodal learning has shown remarkable success by leveraging contrastive learning to capture explicit one-to-one relations across modalities. However, real-world data often exhibits shared relations beyond simple pairwise…

To overcome the imbalanced multimodal learning problem, where models prefer the training of specific modalities, existing methods propose to control the training of uni-modal encoders from different perspectives, taking the inter-modal…

Multimodal Domain Generalization (MMDG) leverages the complementary strengths of multiple modalities to enhance model generalization on unseen domains. A central challenge in multimodal learning is optimization imbalance, where modalities…

Multi-modal recommender systems (MMRS) have gained significant attention due to their ability to leverage information from various modalities to enhance recommendation quality. However, existing negative sampling techniques often struggle…

Due to its complexity, graph learning-based multi-modal integration and classification is one of the most challenging obstacles for disease prediction. To effectively offset the negative impact between modalities in the process of…