Related papers: X-LXMERT: Paint, Caption and Answer Questions with…

Vision-and-language reasoning requires an understanding of visual concepts, language semantics, and, most importantly, the alignment and relationships between these two modalities. We thus propose the LXMERT (Learning Cross-Modality Encoder…

While many BERT-based cross-modal pre-trained models produce excellent results on downstream understanding tasks like image-text retrieval and VQA, they cannot be applied to generation tasks directly. In this paper, we propose XGPT, a new…

Joint image-text embedding is the bedrock for most Vision-and-Language (V+L) tasks, where multimodality inputs are simultaneously processed for joint visual and textual understanding. In this paper, we introduce UNITER, a UNiversal…

We study the joint learning of image-to-text and text-to-image generations, which are naturally bi-directional tasks. Typical existing works design two separate task-specific models for each task, which impose expensive design efforts. In…

We propose Pixel-BERT to align image pixels with text by deep multi-modal transformers that jointly learn visual and language embedding in a unified end-to-end framework. We aim to build a more accurate and thorough connection between image…

Recent advancements in Multimodal Large Language Models (MLLMs) have revolutionized the field of vision-language understanding by integrating visual perception capabilities into Large Language Models (LLMs). The prevailing trend in this…

We investigate the reasoning ability of pretrained vision and language (V&L) models in two tasks that require multimodal integration: (1) discriminating a correct image-sentence pair from an incorrect one, and (2) counting entities in an…

In-context generation is a key component of large language models' (LLMs) open-task generalization capability. By leveraging a few examples as context, LLMs can perform both in-domain and out-of-domain tasks. Recent advancements in…

Visual captioning aims to generate textual descriptions given images or videos. Traditionally, image captioning models are trained on human annotated datasets such as Flickr30k and MS-COCO, which are limited in size and diversity. This…

Combining the visual modality with pretrained language models has been surprisingly effective for simple descriptive tasks such as image captioning. More general text generation however remains elusive. We take a step back and ask: How do…

Humans have an incredible ability to process and understand information from multiple sources such as images, video, text, and speech. Recent success of deep neural networks has enabled us to develop algorithms which give machines the…

Large-scale pretrained models such as LXMERT are becoming popular for learning cross-modal representations on text-image pairs for vision-language tasks. According to the lottery ticket hypothesis, NLP and computer vision models contain…

Recent advances in Large Multi-modal Models (LMMs) have demonstrated their remarkable success as general-purpose multi-modal assistants, with particular focuses on holistic image- and video-language understanding. Conversely, less attention…

Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. In the cross-modal setting, tokens in the sentence are masked at random, and the model predicts the masked tokens given the image and the text. In…

In this paper, we introduce a new vision-language pre-trained model -- ImageBERT -- for image-text joint embedding. Our model is a Transformer-based model, which takes different modalities as input and models the relationship between them.…

The dominant probing approaches rely on the zero-shot performance of image-text matching tasks to gain a finer-grained understanding of the representations learned by recent multimodal image-language transformer models. The evaluation is…

Recent work showed the possibility of building open-vocabulary large language models (LLMs) that directly operate on pixel representations. These models are implemented as autoencoders that reconstruct masked patches of rendered text.…

Multi-modal Large Language Models (MLLMs) have introduced a novel dimension to document understanding, i.e., they endow large language models with visual comprehension capabilities; however, how to design a suitable image-text pre-training…

Joint image-text embedding extracted from medical images and associated contextual reports is the bedrock for most biomedical vision-and-language (V+L) tasks, including medical visual question answering, clinical image-text retrieval,…

While (large) language models have significantly improved over the last years, they still struggle to sensibly process long sequences found, e.g., in books, due to the quadratic scaling of the underlying attention mechanism. To address…