Related papers: TextME: Bridging Unseen Modalities Through Text De…
Representation learning of textual networks poses a significant challenge as it involves capturing amalgamated information from two modalities: (i) underlying network structure, and (ii) node textual attributes. For this, most existing…
Current language models have been criticised for learning language from text alone without connection between words and their meaning. Consequently, multimodal training has been proposed as a way for creating models with better language…
Despite an exciting new wave of multimodal machine learning models, current approaches still struggle to interpret the complex contextual relationships between the different modalities present in videos. Going beyond existing methods that…
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…
Semantic retrieval of remote sensing (RS) images is a critical task fundamentally challenged by the \textquote{semantic gap}, the discrepancy between a model's low-level visual features and high-level human concepts. While large…
The capability to jointly process multi-modal information is becoming an essential task. However, the limited number of paired multi-modal data and the large computational requirements in multi-modal learning hinder the development. We…
Many contrastive learning based models have achieved advanced performance in image-text matching tasks. The key of these models lies in analyzing the correlation between image-text pairs, which involves cross-modal interaction of embeddings…
Multimodal foundation models aim to create a unified representation space that abstracts away from surface features like language syntax or modality differences. To investigate this, we study the internal representations of three recent…
Cross-modal generalization aims to learn a shared discrete representation space from multimodal pairs, enabling knowledge transfer across unannotated modalities. However, achieving a unified representation for all modality pairs requires…
The success of vision-language models is primarily attributed to effective alignment across modalities such as vision and language. However, modality gaps persist in existing alignment algorithms and appear necessary for human perception as…
Pre-trained vision-language models have notably accelerated progress of open-world concept recognition. Their impressive zero-shot ability has recently been transferred to multi-label image classification via prompt tuning, enabling to…
Information extraction, e.g., attribute value extraction, has been extensively studied and formulated based only on text. However, many attributes can benefit from image-based extraction, like color, shape, pattern, among others. The visual…
Despite their success, unsupervised domain adaptation methods for semantic segmentation primarily focus on adaptation between image domains and do not utilize other abundant visual modalities like depth, infrared and event. This limitation…
Multimodal deep learning systems which employ multiple modalities like text, image, audio, video, etc., are showing better performance in comparison with individual modalities (i.e., unimodal) systems. Multimodal machine learning involves…
We present LMFusion, a framework for empowering pretrained text-only large language models (LLMs) with multimodal generative capabilities, enabling them to understand and generate both text and images in arbitrary sequences. LMFusion…
Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pure-text queries. In real-world scenarios, language also…
The last year has seen astonishing progress in text-prompted image generation premised on the idea of a cross-modal representation space in which the text and image domains are represented jointly. In ASR, this idea has found application as…
Pre-trained multi-modal Vision-Language Models like CLIP are widely used off-the-shelf for a variety of applications. In this paper, we show that the common practice of individually exploiting the text or image encoders of these powerful…
Despite the recent achievements made in the multi-modal emotion recognition task, two problems still exist and have not been well investigated: 1) the relationship between different emotion categories are not utilized, which leads to…
Unsupervised domain adaptation (UDA) enables models trained on a labeled source domain to handle new unlabeled domains. Recently, pre-trained vision-language models (VLMs) have demonstrated promising zero-shot performance by leveraging…