相关论文: Countering Multi-modal Representation Collapse thr…

We aim to develop a fundamental understanding of modality collapse, a recently observed empirical phenomenon wherein models trained for multimodal fusion tend to rely only on a subset of the modalities, ignoring the rest. We show that…

Many vision-related tasks benefit from reasoning over multiple modalities to leverage complementary views of data in an attempt to learn robust embedding spaces. Most deep learning-based methods rely on a late fusion technique whereby…

How to perform effective information fusion of different modalities is a core factor in boosting the performance of RGBT tracking. This paper presents a novel deep fusion algorithm based on the representations from an end-to-end trained…

Multiple object tracking (MOT) is a significant task in achieving autonomous driving. Traditional works attempt to complete this task, either based on point clouds (PC) collected by LiDAR, or based on images captured from cameras. However,…

The vast increase in amount and complexity of digital content led to a wide interest in ad-hoc retrieval systems in recent years. Complementary, the existence of heterogeneous data sources and retrieval models stimulated the proliferation…

Learning multi-modal representations is an essential step towards real-world robotic applications, and various multi-modal fusion models have been developed for this purpose. However, we observe that existing models, whose objectives are…

This paper presents an investigation into the estimation of optical and scene flow using RGBD information in scenarios where the RGB modality is affected by noise or captured in dark environments. Existing methods typically rely solely on…

Multimodal sentiment analysis remains a challenging task due to the inherent heterogeneity across modalities. Such heterogeneity often manifests as asynchronous signals, imbalanced information between modalities, and interference from…

Deep learning-based image fusion approaches have obtained wide attention in recent years, achieving promising performance in terms of visual perception. However, the fusion module in the current deep learning-based methods suffers from two…

Monocular depth estimation from RGB images plays a pivotal role in 3D vision. However, its accuracy can deteriorate in challenging environments such as nighttime or adverse weather conditions. While long-wave infrared cameras offer stable…

We address the problem of multi-modal object tracking in video and explore various options of fusing the complementary information conveyed by the visible (RGB) and thermal infrared (TIR) modalities including pixel-level, feature-level and…

Multimodal object detection has attracted significant attention in both academia and industry for its enhanced robustness. Although numerous studies have focused on improving modality fusion strategies, most neglect fusion degradation, and…

Generative recommendation systems have achieved significant advances by leveraging semantic IDs to represent items. However, existing approaches that tokenize each modality independently face two critical limitations: (1) redundancy across…

With the development of depth sensors in recent years, RGBD object tracking has received significant attention. Compared with the traditional RGB object tracking, the addition of the depth modality can effectively solve the target and…

This paper proposes a learning model, based on rank-fusion graphs, for general applicability in multimodal prediction tasks, such as multimodal regression and image classification. Rank-fusion graphs encode information from multiple…

Cross-modal image-text retrieval is challenging because of the diverse possible associations between content from different modalities. Traditional methods learn a single-vector embedding to represent semantics of each sample, but struggle…

Existing RGB-Event detection methods process the low-information regions of both modalities (background in images and non-event regions in event data) uniformly during feature extraction and fusion, resulting in high computational costs and…

Focus based methods have shown promising results for the task of depth estimation. However, most existing focus based depth estimation approaches depend on maximal sharpness of the focal stack. Out of focus information in the focal stack…

Effectively integrating diverse sensory modalities is crucial for robotic manipulation. However, the typical approach of feature concatenation is often suboptimal: dominant modalities such as vision can overwhelm sparse but critical signals…

Scaling recommendation models is a central challenge in recommender systems. Recently, RankMixer has emerged as an effective solution, operating on a unified token representation and alternating between token mixing and per-token…