Related papers: DCER: Dual-Stage Compression and Energy-Based Reco…
Multimodal learning faces two major challenges: modality imbalance and data noise, which significantly affect the robustness and generalization ability of models. Existing methods achieve modality balance by suppressing dominant modalities,…
Multimodal learning often encounters the under-optimized problem and may have worse performance than unimodal learning. Existing methods attribute this problem to the imbalanced learning between modalities and rebalance them through…
Multimodal Sentiment Analysis (MSA) aims to predict sentiment from language, acoustic, and visual data in videos. However, imbalanced unimodal performance often leads to suboptimal fused representations. Existing approaches typically adopt…
Recent advances in computing such as the massively parallel GPUs (Graphical Processing Units),coupled with the need to store and deliver large quantities of digital data especially images, has brought a number of challenges for Computer…
Multi-modal learning has made significant advances across diverse pattern recognition applications. However, handling missing modalities, especially under imbalanced missing rates, remains a major challenge. This imbalance triggers a…
Vision is often used as a complementary modality for audio speech recognition (ASR), especially in the noisy environment where performance of solo audio modality significantly deteriorates. After combining visual modality, ASR is upgraded…
Physics-based models often involve large systems of parametrized partial differential equations, where design parameters control various properties. However, high-fidelity simulations of such systems on large domains or with high grid…
This work aims to improve fuel chamber injectors' performance in turbofan engines, thus implying improved performance and reduction of pollutants. This requires the development of models that allow real-time prediction and improvement of…
A new method for multimodal sensor fusion is introduced. The technique relies on a two-stage process. In the first stage, a multimodal generative model is constructed from unlabelled training data. In the second stage, the generative model…
Two-level domain decomposition (DD) methods are very powerful techniques for the efficient numerical solution of partial differential equations (PDEs). A two-level domain decomposition method requires two main components: a one-level…
Body-conduction microphone signals (BMS) bypass airborne sound, providing strong noise resistance. However, a complementary modality is required to compensate for the inherent loss of high-frequency information. In this study, we propose a…
Performing magnetic resonance imaging (MRI) reconstruction from under-sampled k-space data can accelerate the procedure to acquire MRI scans and reduce patients' discomfort. The reconstruction problem is usually formulated as a denoising…
Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…
Context-aware compression techniques have gained increasing attention as model sizes continue to grow, introducing computational bottlenecks that hinder efficient deployment. A structured encoding approach was proposed to selectively…
A central problem in building effective sound event detection systems is the lack of high-quality, strongly annotated sound event datasets. For this reason, Task 4 of the DCASE 2024 challenge proposes learning from two heterogeneous…
LiDAR-based perception is central to autonomous driving and robotics, yet raw point clouds remain highly vulnerable to noise, occlusion, and adversarial corruptions. Autoencoders offer a natural framework for denoising and reconstruction,…
Semantic communication is emerging as a key enabler for distributed edge intelligence due to its capability to convey task-relevant meaning. However, achieving communication-efficient training and robust inference over wireless links…
Current Audio-Visual Source Separation methods primarily adopt two design strategies. The first strategy involves fusing audio and visual features at the bottleneck layer of the encoder, followed by processing the fused features through the…
Recent studies have focused on utilizing multi-modal data to develop robust models for facial Action Unit (AU) detection. However, the heterogeneity of multi-modal data poses challenges in learning effective representations. One such…
Semantic communications for multi-modal data can transmit task-relevant information efficiently over noisy and bandwidth-limited channels. However, a key challenge is to simultaneously compress inter-modal redundancy and improve semantic…