相关论文: Towards Models that Can See and Read

We propose UniSeg3D, a unified 3D scene understanding framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary segmentation tasks within a single model. Most previous 3D segmentation approaches are…

The visual dialog task attempts to train an agent to answer multi-turn questions given an image, which requires the deep understanding of interactions between the image and dialog history. Existing researches tend to employ the…

The combination of visual and textual representations has produced excellent results in tasks such as image captioning and visual question answering, but the inference capabilities of multimodal representations are largely untested. In the…

Zero-shot scene understanding in real-world settings presents major challenges due to the complexity and variability of natural scenes, where models must recognize new objects, actions, and contexts without prior labeled examples. This work…

Paragraph-style image captions describe diverse aspects of an image as opposed to the more common single-sentence captions that only provide an abstract description of the image. These paragraph captions can hence contain substantial…

Scene text retrieval aims to localize and search all text instances from an image gallery, which are the same or similar to a given query text. Such a task is usually realized by matching a query text to the recognized words, outputted by…

Many visual scenes contain text that carries crucial information, and it is thus essential to understand text in images for downstream reasoning tasks. For example, a deep water label on a warning sign warns people about the danger in the…

Text-to-image multimodal tasks, generating/retrieving an image from a given text description, are extremely challenging tasks since raw text descriptions cover quite limited information in order to fully describe visually realistic images.…

In this paper, we explore the possibility of building a unified foundation model that can be adapted to both vision-only and text-only tasks. Starting from BERT and ViT, we design a unified transformer consisting of modality-specific…

Text-based visual question answering (VQA) requires to read and understand text in an image to correctly answer a given question. However, most current methods simply add optical character recognition (OCR) tokens extracted from the image…

Visual Question Answering (VQA) is of tremendous interest to the research community with important applications such as aiding visually impaired users and image-based search. In this work, we explore the use of scene graphs for solving the…

We present UniModel, a unified generative model that jointly supports visual understanding and visual generation within a single pixel-to-pixel diffusion framework. Our goal is to achieve unification along three axes: the model, the tasks,…

Multimodal tasks in the fashion domain have significant potential for e-commerce, but involve challenging vision-and-language learning problems - e.g., retrieving a fashion item given a reference image plus text feedback from a user. Prior…

Most existing vision-language pre-training methods focus on understanding tasks and use BERT-like objectives (masked language modeling and image-text matching) during pretraining. Although they perform well in many understanding downstream…

Foundational multimodal models pre-trained on large scale image-text pairs or video-text pairs or both have shown strong generalization abilities on downstream tasks. However unlike image-text models, pretraining video-text models is always…

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…

Pre-training visual and textual representations from large-scale image-text pairs is becoming a standard approach for many downstream vision-language tasks. The transformer-based models learn inter and intra-modal attention through a list…

We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first…

The intersection of vision and language is of major interest due to the increased focus on seamless integration between recognition and reasoning. Scene graphs (SGs) have emerged as a useful tool for multimodal image analysis, showing…

When humans perceive the world, they naturally integrate multiple audio-visual tasks within dynamic, real-world scenes. However, current works such as event localization, parsing, segmentation and question answering are mostly explored…