相关论文: UNITER: UNiversal Image-TExt Representation Learni…

The relations expressed in user queries are vital for cross-modal information retrieval. Relation-focused cross-modal retrieval aims to retrieve information that corresponds to these relations, enabling effective retrieval across different…

Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained…

We present MetricBERT, a BERT-based model that learns to embed text under a well-defined similarity metric while simultaneously adhering to the ``traditional'' masked-language task. We focus on downstream tasks of learning similarities for…

We present a simple yet effective end-to-end Video-language Pre-training (VidLP) framework, Masked Contrastive Video-language Pretraining (MAC), for video-text retrieval tasks. Our MAC aims to reduce video representation's spatial and…

We present Emu, a Transformer-based multimodal foundation model, which can seamlessly generate images and texts in multimodal context. This omnivore model can take in any single-modality or multimodal data input indiscriminately (e.g.,…

Word Representations form the core component for almost all advanced Natural Language Processing (NLP) applications such as text mining, question-answering, and text summarization, etc. Over the last two decades, immense research is…

Universal Multimodal Retrieval (UMR) aims to map different modalities (e.g., visual and textual) into a shared embedding space for multi-modal retrieval. Existing UMR methods can be broadly divided into two categories: early-fusion…

To mimic human vision with the way of recognizing the diverse and open world, foundation vision models are much critical. While recent techniques of self-supervised learning show the promising potentiality of this mission, we argue that…

Recently a number of studies demonstrated impressive performance on diverse vision-language multi-modal tasks such as image captioning and visual question answering by extending the BERT architecture with multi-modal pre-training…

Word embeddings, i.e., semantically meaningful vector representation of words, are largely influenced by the distributional hypothesis "You shall know a word by the company it keeps" (Harris, 1954), whereas modern prediction-based neural…

Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we propose a Scalable Multilingual…

Most existing vision-language pre-training (VLP) approaches adopt cross-modal masked language modeling (CMLM) to learn vision-language associations. However, we find that CMLM is insufficient for this purpose according to our observations:…

Multi-modal retrieval has seen tremendous progress with the development of vision-language models. However, further improving these models require additional labelled data which is a huge manual effort. In this paper, we propose a framework…

Pre-trained sequence-to-sequence models have significantly improved Neural Machine Translation (NMT). Different from prior works where pre-trained models usually adopt an unidirectional decoder, this paper demonstrates that pre-training a…

In this work, we present an information-theoretic framework that formulates cross-lingual language model pre-training as maximizing mutual information between multilingual-multi-granularity texts. The unified view helps us to better…

The development of language models have moved from encoder-decoder to decoder-only designs. In addition, we observe that the two most popular multimodal tasks, the generative and contrastive tasks, are nontrivial to accommodate in one…

We propose VisualBERT, a simple and flexible framework for modeling a broad range of vision-and-language tasks. VisualBERT consists of a stack of Transformer layers that implicitly align elements of an input text and regions in an…

While most conversational AI systems focus on textual dialogue only, conditioning utterances on visual context (when it's available) can lead to more realistic conversations. Unfortunately, a major challenge for incorporating visual context…

Contrastive Language-Image Pre-training (CLIP) has shown impressive performance in aligning visual and textual representations. Recent studies have extended this paradigm to 3D vision to improve scene understanding for autonomous driving. A…

Universal Multimodal embedding models built on Multimodal Large Language Models (MLLMs) have traditionally employed contrastive learning, which aligns representations of query-target pairs across different modalities. Yet, despite its…