Related papers: Bridging Text and Crystal Structures: Literature-d…

Contrastively trained vision-language models have achieved remarkable progress in vision and language representation learning, leading to state-of-the-art models for various downstream multimodal tasks. However, recent research has…

Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…

Recent years have witnessed the fast development of large-scale pre-training frameworks that can extract multi-modal representations in a unified form and achieve promising performances when transferred to downstream tasks. Nevertheless,…

Materials property predictions have improved from advances in machine learning algorithms, delivering materials discoveries and novel insights through data-driven models of structure-property relationships. Nearly all available models rely…

Text embedding models play a crucial role in natural language processing, particularly in information retrieval, and their importance is further highlighted with the recent utilization of RAG (Retrieval- Augmented Generation). This study…

In natural language processing (NLP) of spoken languages, word embeddings have been shown to be a useful method to encode the meaning of words. Sign languages are visual languages, which require sign embeddings to capture the visual and…

Property prediction accuracy has long been a key parameter of machine learning in materials informatics. Accordingly, advanced models showing state-of-the-art performance turn into highly parameterized black boxes missing interpretability.…

Free-style text is still one of the common ways in which data is registered in real environments, like legal procedures and medical records. Because of that, there have been significant efforts in the area of natural language processing to…

Fonts convey different impressions to readers. These impressions often come from the font shapes. However, the correlation between fonts and their impression is weak and unstable because impressions are subjective. To capture such weak and…

The prediction of crystal properties plays a crucial role in the crystal design process. Current methods for predicting crystal properties focus on modeling crystal structures using graph neural networks (GNNs). Although GNNs are powerful,…

We propose Domain-Conditioned Meta-Contrastive Learning, a framework for improving the cross-domain generalization of vision-language models. While contrastive models such as CLIP achieve strong performance through large-scale training,…

The generation of plausible crystal structures is often the first step in predicting the structure and properties of a material from its chemical composition. Quickly generating and predicting inorganic crystal structures is important for…

This paper presents CLaSP, a novel model for retrieving time-series signals using natural language queries that describe signal characteristics. The ability to search time-series signals based on descriptive queries is essential in domains…

Contrastive learning has been frequently investigated to learn effective representations for text clustering tasks. While existing contrastive learning-based text clustering methods only focus on modeling instance-wise semantic similarity…

Contrastive learning (CL) is a popular technique for self-supervised learning (SSL) of visual representations. It uses pairs of augmentations of unlabeled training examples to define a classification task for pretext learning of a deep…

Misleading text detection on social media platforms is a critical research area, as these texts can lead to public misunderstanding, social panic and even economic losses. This paper proposes a novel framework - CL-ISR (Contrastive Learning…

Existing computer vision research in artwork struggles with artwork's fine-grained attributes recognition and lack of curated annotated datasets due to their costly creation. To the best of our knowledge, we are one of the first methods to…

Cross-modal retrieval (CMR) has been extensively applied in various domains, such as multimedia search engines and recommendation systems. Most existing CMR methods focus on image-to-text retrieval, whereas audio-to-text retrieval, a less…

Contrastive vision-language models, such as CLIP, have garnered considerable attention for various downstream tasks, mainly due to the remarkable ability of the learned features for generalization. However, the features they learned often…

Understanding how objects relate to each other in space is fundamental to scene understanding, yet most contrastive pre-training approaches only model pairwise relationships, leaving richer compositional and multi-hop interactions largely…