相关论文: Augmenting Vision Language Pretraining by Learning…

We study visual representation learning from a structural and topological perspective. We begin from a single hypothesis: that visual understanding presupposes a semantic language for vision, in which many perceptual observations correspond…

Vision-language models, while effective in general domains and showing strong performance in diverse multi-modal applications like visual question-answering (VQA), struggle to maintain the same level of effectiveness in more specialized…

Our understanding of the visual world is centered around various concept axes, characterizing different aspects of visual entities. While different concept axes can be easily specified by language, e.g. color, the exact visual nuances along…

Visual Question Answering (VQA) attracts much attention from both industry and academia. As a multi-modality task, it is challenging since it requires not only visual and textual understanding, but also the ability to align cross-modality…

Shouldn't language and vision features be treated equally in vision-language (VL) tasks? Many VL approaches treat the language component as an afterthought, using simple language models that are either built upon fixed word embeddings…

This paper presents a comprehensive survey of vision-language (VL) intelligence from the perspective of time. This survey is inspired by the remarkable progress in both computer vision and natural language processing, and recent trends…

Text images contain both visual and linguistic information. However, existing pre-training techniques for text recognition mainly focus on either visual representation learning or linguistic knowledge learning. In this paper, we propose a…

The growing success of Vision-Language-Action (VLA) models stems from the promise that pretrained Vision-Language Models (VLMs) can endow agents with transferable world knowledge and vision-language (VL) grounding, laying a foundation for…

Recently introduced self-supervised methods for image representation learning provide on par or superior results to their fully supervised competitors, yet the corresponding efforts to explain the self-supervised approaches lag behind.…

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

Visual-Language Models (VLMs) have become a powerful tool for bridging the gap between visual and linguistic understanding. However, the conventional learning approaches for VLMs often suffer from limitations, such as the high resource…

The pre-trained vision-language model, exemplified by CLIP, advances zero-shot semantic segmentation by aligning visual features with class embeddings through a transformer decoder to generate semantic masks. Despite its effectiveness,…

Visual reasoning tasks such as visual question answering (VQA) require an interplay of visual perception with reasoning about the question semantics grounded in perception. However, recent advances in this area are still primarily driven by…

Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual input, defaulting to strong language priors. Our approach first…

The de-facto approach to many vision tasks is to start from pretrained visual representations, typically learned via supervised training on ImageNet. Recent methods have explored unsupervised pretraining to scale to vast quantities of…

Medical vision-and-language pre-training (Med-VLP) has received considerable attention owing to its applicability to extracting generic vision-and-language representations from medical images and texts. Most existing methods mainly contain…

Vector Quantization (VQ) is a method for discretizing latent representations and has become a major part of the deep learning toolkit. It has been theoretically and empirically shown that discretization of representations leads to improved…

Recent advances in visual-language machine learning models have demonstrated exceptional ability to use natural language and understand visual scenes by training on large, unstructured datasets. However, this training paradigm cannot…

Effective multimodal reasoning depends on the alignment of visual and linguistic representations, yet the mechanisms by which vision-language models (VLMs) achieve this alignment remain poorly understood. Following the LiMBeR framework, we…

With recent progress in joint modeling of visual and textual representations, Vision-Language Pretraining (VLP) has achieved impressive performance on many multimodal downstream tasks. However, the requirement for expensive annotations…