Related papers: MoColl: Agent-Based Specific and General Model Col…

Knowledge-based visual question answering (VQA) involves questions that require world knowledge beyond the image to yield the correct answer. Large language models (LMs) like GPT-3 are particularly helpful for this task because of their…

Large Vision-Language Models (LVLMs) integrate image encoders with Large Language Models (LLMs) to process multi-modal inputs and perform complex visual tasks. However, they often generate hallucinations by describing non-existent objects…

Concept Bottleneck Models (CBMs) decompose image classification into a process governed by interpretable, human-readable concepts. Recent advances in CBMs have used Large Language Models (LLMs) to generate candidate concepts. However, a…

Large Language Models (LLMs) have achieved impressive results in knowledge-based Visual Question Answering (VQA). However existing methods still have challenges: the inability to use external tools autonomously, and the inability to work in…

Automatically generating a natural language description of an image is a task close to the heart of image understanding. In this paper, we present a multi-model neural network method closely related to the human visual system that…

A remarkable ability of human beings resides in compositional reasoning, i.e., the capacity to make "infinite use of finite means". However, current large vision-language foundation models (VLMs) fall short of such compositional abilities…

We introduce a new multi-modal task for computer systems, posed as a combined vision-language comprehension challenge: identifying the most suitable text describing a scene, given several similar options. Accomplishing the task entails…

Generating informative and knowledge-rich image captions remains a challenge for many existing captioning models, which often produce generic descriptions that lack specificity and contextual depth. To address this limitation, we propose…

This technical report provides extra details of the deep multimodal similarity model (DMSM) which was proposed in (Fang et al. 2015, arXiv:1411.4952). The model is trained via maximizing global semantic similarity between images and their…

This paper presents a novel approach for automatically generating image descriptions: visual detectors, language models, and multimodal similarity models learnt directly from a dataset of image captions. We use multiple instance learning to…

Radiology visual question answering (RVQA) provides precise answers to questions about chest X-ray images, alleviating radiologists' workload. While recent methods based on multimodal large language models (MLLMs) and retrieval-augmented…

Textbook Question Answering (TQA) is a complex multimodal task to infer answers given large context descriptions and abundant diagrams. Compared with Visual Question Answering (VQA), TQA contains a large number of uncommon terminologies and…

Do we still need to represent objects explicitly in multimodal large language models (MLLMs)? To one extreme, pre-trained encoders convert images into visual tokens, with which objects and spatiotemporal relationships may be implicitly…

Understanding images and text together is an important aspect of cognition and building advanced Artificial Intelligence (AI) systems. As a community, we have achieved good benchmarks over language and vision domains separately, however…

The Controllable Image Captioning Agent (CapAgent) is an innovative system designed to bridge the gap between user simplicity and professional-level outputs in image captioning tasks. CapAgent automatically transforms user-provided simple…

Multimodal large language models (MLLMs) have achieved rapid progress, yet their scaling behavior remains less clearly characterized and often less predictable than that of text-only LLMs. Increasing model size and task diversity often…

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…

The advent of vision-language pre-training techniques enhanced substantial progress in the development of models for image captioning. However, these models frequently produce generic captions and may omit semantically important image…

State-of-the-art approaches for image captioning require supervised training data consisting of captions with paired image data. These methods are typically unable to use unsupervised data such as textual data with no corresponding images,…

Image captioning has long been regarded as a fundamental task in visual understanding. Recently, however, few large vision-language model (LVLM) research discusses model's image captioning performance because of the outdated short-caption…