Related papers: Unsupervised Visual Sense Disambiguation for Verbs…

Detecting visual relationships, i.e. <Subject, Predicate, Object> triplets, is a challenging Scene Understanding task approached in the past via linguistic priors or spatial information in a single feature branch. We introduce a new deeply…

Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures…

Self-supervised learning is a machine learning approach that generates implicit labels by learning underlined patterns and extracting discriminative features from unlabeled data without manual labelling. Contrastive learning introduces the…

Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotations for thousands of categories at a large scale. We…

Recent work shows that documents from encyclopedias serve as helpful auxiliary information for zero-shot learning. Existing methods align the entire semantics of a document with corresponding images to transfer knowledge. However, they…

In this paper we introduce vSTS, a new dataset for measuring textual similarity of sentences using multimodal information. The dataset is comprised by images along with its respectively textual captions. We describe the dataset both…

Cross-lingual word embeddings (CLWE) have been proven useful in many cross-lingual tasks. However, most existing approaches to learn CLWE including the ones with contextual embeddings are sense agnostic. In this work, we propose a novel…

Image representations are often evaluated through disjointed, task-specific protocols, leading to a fragmented understanding of model capabilities. For instance, it is unclear whether an image embedding model adept at clustering images is…

In this paper, we present a new approach for word sense disambiguation (WSD) using an exemplar-based learning algorithm. This approach integrates a diverse set of knowledge sources to disambiguate word sense, including part of speech of…

We present a novel online algorithm that learns the essence of each dimension in word embeddings by minimizing the within-group distance of contextualized embedding groups. Three state-of-the-art neural-based language models are used,…

Recent approaches to word sense disambiguation (WSD) utilize encodings of the sense gloss (definition), in addition to the input context, to improve performance. In this work we demonstrate that this approach can be adapted for use in…

CLIP has demonstrated exceptional image-text matching capabilities due to its training on contrastive learning tasks. Past research has suggested that whereas CLIP effectively matches text to images when the matching can be achieved just by…

Pre-trained contextual language models are ubiquitously employed for language understanding tasks, but are unsuitable for resource-constrained systems. Noncontextual word embeddings are an efficient alternative in these settings. Such…

Zero-shot learning (ZSL) highly depends on a good semantic embedding to connect the seen and unseen classes. Recently, distributed word embeddings (DWE) pre-trained from large text corpus have become a popular choice to draw such a…

Visual embedding models excel at zero-shot tasks like visual retrieval and classification. However, these models cannot be used for tasks that contain ambiguity or require user instruction. These tasks necessitate an embedding model which…

Multimodal sentence embedding models typically leverage image-caption pairs in addition to textual data during training. However, such pairs often contain noise, including redundant or irrelevant information on either the image or caption…

Embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering. Recently, there has been a surge of interest in developing universal text embedding models that can…

Contextual embeddings represent a new generation of semantic representations learned from Neural Language Modelling (NLM) that addresses the issue of meaning conflation hampering traditional word embeddings. In this work, we show that…

Due to the lack of extensive precisely-annotated multi-label data in real word, semi-supervised multi-label learning (SSMLL) has gradually gained attention. Abundant knowledge embedded in vision-language models (VLMs) pre-trained on…

Sentence embeddings are an important component of many natural language processing (NLP) systems. Like word embeddings, sentence embeddings are typically learned on large text corpora and then transferred to various downstream tasks, such…