Related papers: VisualBERT: A Simple and Performant Baseline for V…

Visual grounding is a common vision task that involves grounding descriptive sentences to the corresponding regions of an image. Most existing methods use independent image-text encoding and apply complex hand-crafted modules or…

In this paper, we introduce ActBERT for self-supervised learning of joint video-text representations from unlabeled data. First, we leverage global action information to catalyze the mutual interactions between linguistic texts and local…

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…

Despite recent advances in Vision-Language Models (VLMs), they may over-rely on visual language priors existing in their training data rather than true visual reasoning. To investigate this, we introduce ViLP, a benchmark featuring…

Current large vision-language models (LVLMs) typically rely on text-only reasoning based on a single-pass visual encoding, which often leads to loss of fine-grained visual information. Recently the proposal of ''thinking with images''…

In this work, we present the Textless Vision-Language Transformer (TVLT), where homogeneous transformer blocks take raw visual and audio inputs for vision-and-language representation learning with minimal modality-specific design, and do…

Transformer-based models are widely used in natural language understanding (NLU) tasks, and multimodal transformers have been effective in visual-language tasks. This study explores distilling visual information from pretrained multimodal…

Large-scale pretraining and task-specific fine-tuning is now the standard methodology for many tasks in computer vision and natural language processing. Recently, a multitude of methods have been proposed for pretraining vision and language…

Knowledge is acquired by humans through experience, and no boundary is set between the kinds of knowledge or skill levels we can achieve on different tasks at the same time. When it comes to Neural Networks, that is not the case. The…

Large language models can produce powerful contextual representations that lead to improvements across many NLP tasks. Since these models are typically guided by a sequence of learned self attention mechanisms and may comprise undesired…

Visual grounding is a task to locate the target indicated by a natural language expression. Existing methods extend the generic object detection framework to this problem. They base the visual grounding on the features from pre-generated…

Humans learn language by listening, speaking, writing, reading, and also, via interaction with the multimodal real world. Existing language pre-training frameworks show the effectiveness of text-only self-supervision while we explore the…

We present a novel task and dataset for evaluating the ability of vision and language models to conduct visio-linguistic compositional reasoning, which we call Winoground. Given two images and two captions, the goal is to match them…

Human language is grounded on multimodal knowledge including visual knowledge like colors, sizes, and shapes. However, current large-scale pre-trained language models rely on text-only self-supervised training with massive text data, which…

We present a pre-training approach for vision and language transformer models, which is based on a mixture of diverse tasks. We explore both the use of image-text captioning data in pre-training, which does not need additional supervision,…

Self-supervised vision-and-language pretraining (VLP) aims to learn transferable multi-modal representations from large-scale image-text data and to achieve strong performances on a broad scope of vision-language tasks after finetuning.…

Vision-language pre-training (VLP) methods are blossoming recently, and its crucial goal is to jointly learn visual and textual features via a transformer-based architecture, demonstrating promising improvements on a variety of…

Large language models such as BERT and the GPT series started a paradigm shift that calls for building general-purpose models via pre-training on large datasets, followed by fine-tuning on task-specific datasets. There is now a plethora of…

The recent success of transformer models in language, such as BERT, has motivated the use of such architectures for multi-modal feature learning and tasks. However, most multi-modal variants (e.g., ViLBERT) have limited themselves to…

The ability to learn from large unlabeled corpora has allowed neural language models to advance the frontier in natural language understanding. However, existing self-supervision techniques operate at the word form level, which serves as a…