相关论文: XM-ALIGN: Unified Cross-Modal Embedding Alignment …

Contrastive Vision-Language Models (VLMs) have demonstrated strong zero-shot capabilities. However, their cross-modal alignment remains biased toward English due to limited multilingual multimodal data. Recent multilingual extensions have…

In this paper, we tackle the problem of handling narrowband and wideband speech by building a single acoustic model (AM), also called mixed bandwidth AM. In the proposed approach, an auxiliary input feature is used to provide the bandwidth…

Audio-visual learning suffers from modality misalignment caused by off-screen sources and background clutter, and current methods usually amplify irrelevant regions or moments, leading to unstable training and degraded representation…

In this paper, we propose a visual embedding approach to improving embedding aware speech enhancement (EASE) by synchronizing visual lip frames at the phone and place of articulation levels. We first extract visual embedding from lip frames…

Large Language Models (LLMs) demonstrate strong capabilities in broad knowledge representation, yet they are inherently deficient in pixel-level perceptual understanding. Although the Segment Anything Model (SAM) represents a significant…

In this paper, we propose a new approach to learn multimodal multilingual embeddings for matching images and their relevant captions in two languages. We combine two existing objective functions to make images and captions close in a joint…

Multimodal hateful content detection is a challenging task that requires complex reasoning across visual and textual modalities. Therefore, creating a meaningful multimodal representation that effectively captures the interplay between…

The eXtended Finite Element Method (XFEM) is used to solve interface problems with an unfitted mesh. We present an implementation of the XFEM in the FEM-library deal.II. The main parts of the implementation are (i) the appropriate…

Visual neural decoding aims to extract and interpret original visual experiences directly from human brain activity. Recent studies have demonstrated the feasibility of decoding visual semantic categories from electroencephalography (EEG)…

Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource…

In recent years, Multimodal Emotion Recognition (MER) has made substantial progress. Nevertheless, most existing approaches neglect the semantic inconsistencies that may arise across modalities, such as conflicting emotional cues between…

Multimodal Large Language Models advance multimodal representation learning by acquiring transferable semantic embeddings, thereby substantially enhancing performance across a range of vision-language tasks, including cross-modal retrieval,…

This paper proposes a Learnable Multiplicative absolute position Embedding based Conformer (LMEC). It contains a kernelized linear attention (LA) module called LMLA to solve the time-consuming problem for long sequence speech recognition as…

The rapid advancement of Multimodal Large Language Models (MLLMs) has extended CLIP-based frameworks to produce powerful, universal embeddings for retrieval tasks. However, existing methods primarily focus on natural images, offering…

Vision-language models (VLMs) have made significant strides in cross-modal understanding through large-scale paired datasets. However, in fashion domain, datasets often exhibit a disparity between the information conveyed in image and text.…

Multi-modal embeddings form the foundation for vision-language models, such as CLIP embeddings, the most widely used text-image embeddings. However, these embeddings are vulnerable to subtle misalignment of cross-modal features, resulting…

The explosion of visual content available online underscores the requirement for an accurate machine assessor to robustly evaluate scores across diverse types of visual contents. While recent studies have demonstrated the exceptional…

In recent years, pre-trained visual-linguistic models have demonstrated tremendous potential, becoming a crucial foundational framework for numerous downstream tasks. However, the information density between text and images is not uniformly…

Vision-language models have been key to the development of open-vocabulary 2D semantic segmentation. Lifting these models from 2D images to 3D scenes, however, remains a challenging problem. Existing approaches typically back-project and…

Effective human-robot interaction requires emotionally rich multimodal expressions, yet most humanoid robots lack coordinated speech, facial expressions, and gestures. Meanwhile, real-world deployment demands on-device solutions that can…