相关论文: Aligning Visual and Lexical Semantics

Attention models are widely used in Vision-language (V-L) tasks to perform the visual-textual correlation. Humans perform such a correlation with a strong linguistic understanding of the visual world. However, even the best performing…

The "style trap" poses a significant challenge for Large Vision-Language Models (LVLMs), hindering robust semantic understanding across diverse visual styles, especially in in-context learning (ICL). Existing methods often fail to…

Visual Question Answering (VQA) is an extremely stimulating and challenging research area where Computer Vision (CV) and Natural Language Processig (NLP) have recently met. In image captioning and video summarization, the semantic…

The evaluation of text-generative vision-language models is a challenging yet crucial endeavor. By addressing the limitations of existing Visual Question Answering (VQA) benchmarks and proposing innovative evaluation methodologies, our…

The dream of instantly creating rich 360-degree panoramic worlds from text is rapidly becoming a reality, yet a crucial gap exists in our ability to reliably evaluate their semantic alignment. Contrastive Language-Image Pre-training (CLIP)…

The AI community has been pursuing algorithms known as artificial general intelligence (AGI) that apply to any kind of real-world problem. Recently, chat systems powered by large language models (LLMs) emerge and rapidly become a promising…

We propose to learn word embeddings from visual co-occurrences. Two words co-occur visually if both words apply to the same image or image region. Specifically, we extract four types of visual co-occurrences between object and attribute…

Vision-language models like CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions because of their training focus on short and concise captions. We present…

To bridge the gap between supervised semantic segmentation and real-world applications that acquires one model to recognize arbitrary new concepts, recent zero-shot segmentation attracts a lot of attention by exploring the relationships…

A system that enables blind or visually impaired users to access comics/manga would introduce a new medium of storytelling to this community. However, no such system currently exists. Generative vision-language models (VLMs) have shown…

In recent years, vision and language pre-training (VLP) models have advanced the state-of-the-art results in a variety of cross-modal downstream tasks. Aligning cross-modal semantics is claimed to be one of the essential capabilities of VLP…

We ask the question: to what extent can recent large-scale language and image generation models blend visual concepts? Given an arbitrary object, we identify a relevant object and generate a single-sentence description of the blend of the…

Attention mechanism has been used as an important component across Vision-and-Language(VL) tasks in order to bridge the semantic gap between visual and textual features. While attention has been widely used in VL tasks, it has not been…

How do vision-language (VL) transformer models ground verb phrases and do they integrate contextual and world knowledge in this process? We introduce the CV-Probes dataset, containing image-caption pairs involving verb phrases that require…

Vision-language models (VLMs) hold promise for enhancing visualization tools, but effective human-AI collaboration hinges on a shared perceptual understanding of visual content. Prior studies assessed VLM visualization literacy through…

Different from Visual Question Answering task that requires to answer only one question about an image, Visual Dialogue involves multiple questions which cover a broad range of visual content that could be related to any objects,…

Vision-Language Models like CLIP create aligned embedding spaces for text and images, making it possible for anyone to build a visual classifier by simply naming the classes they want to distinguish. However, a model that works well in one…

Recent studies show that deep vision-only and language-only models--trained on disjoint modalities--nonetheless project their inputs into a partially aligned representational space. Yet we still lack a clear picture of where in each network…

Recent work shows that documents from encyclopedias serve as helpful auxiliary information for zero-shot learning. Existing methods align the entire semantics of a document with corresponding images to transfer knowledge. However, they…

A challenge in advancing Visual-Language Models (VLMs) is determining whether their failures on abstract reasoning tasks, such as Bongard problems, stem from flawed perception or faulty top-down reasoning. To disentangle these factors, we…