Related papers: COREVQA: A Crowd Observation and Reasoning Entailm…
Large Vision-Language Models (LVLMs), despite their recent success, are hardly comprehensively tested for their cognitive abilities. Inspired by the prevalent use of the Cookie Theft task in human cognitive tests, we propose a novel…
Visual understanding requires interpreting both natural scenes and the textual information that appears within them, motivating tasks such as Visual Question Answering (VQA). However, current VQA benchmarks overlook scenarios with visually…
Complex Visual Question Answering (Complex VQA) tasks, which demand sophisticated multi-modal reasoning and external knowledge integration, present significant challenges for existing large vision-language models (LVLMs) often limited by…
Visual Commonsense Reasoning (VCR), deemed as one challenging extension of the Visual Question Answering (VQA), endeavors to pursue a more high-level visual comprehension. It is composed of two indispensable processes: question answering…
Visual question answering on document images that contain textual, visual, and layout information, called document VQA, has received much attention recently. Although many datasets have been proposed for developing document VQA systems,…
Recent advancements in deep learning have led to the development of powerful language models (LMs) that excel in various tasks. Despite these achievements, there is still room for improvement, particularly in enhancing reasoning abilities…
Acquiring high-quality knowledge is a central focus in Knowledge-Based Visual Question Answering (KB-VQA). Recent methods use large language models (LLMs) as knowledge engines for answering. These methods generally employ image captions as…
Vision language models can now generate long-form answers to questions about images - long-form visual question answers (LFVQA). We contribute VizWiz-LF, a dataset of long-form answers to visual questions posed by blind and low vision (BLV)…
State-of-the-art vision-language models (VLMs) score impressively on video benchmarks yet stumble on basic visual reasoning tasks involving spatial relations, navigation, and object selection that a preschooler solves easily. We hypothesize…
Video Question Answering (VideoQA) has made significant strides by leveraging multimodal learning to align visual and textual modalities. However, current benchmarks overwhelmingly focus on questions answerable through explicit visual…
We present an empirical study of active learning for Visual Question Answering, where a deep VQA model selects informative question-image pairs from a pool and queries an oracle for answers to maximally improve its performance under a…
Visual Question Answering (VQA) is an evolving research field aimed at enabling machines to answer questions about visual content by integrating image and language processing techniques such as feature extraction, object detection, text…
We study the Knowledge-Based visual question-answering problem, for which given a question, the models need to ground it into the visual modality to find the answer. Although many recent works use question-dependent captioners to verbalize…
Multimodal Large Language Models (MLLMs) demonstrate remarkable fluency in understanding visual scenes, yet they exhibit a critical lack in a fundamental cognitive skill: object counting. This blind spot severely limits their reliability in…
Visual Question Answering (VQA) is the task of taking as input an image and a free-form natural language question about the image, and producing an accurate answer. In this work we view VQA as a "feature extraction" module to extract image…
We present M$^3$-VQA, a novel knowledge-based Visual Question Answering (VQA) benchmark, to enhance the evaluation of multimodal large language models (MLLMs) in fine-grained multimodal entity understanding and complex multi-hop reasoning.…
Large Vision-Language Models (LVLMs) increasingly rely on retrieval to answer knowledge-intensive multimodal questions. Existing benchmarks overlook conflicts between visual and textual evidence and the importance of generating deflections…
Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information. Despite their exceptional performance on visual understanding benchmarks, measuring their ability to reason abstractly…
Visual reasoning over structured data such as tables is a critical capability for modern vision-language models (VLMs), yet current benchmarks remain limited in scale, diversity, or reasoning depth, especially when it comes to rendered…
In visual question answering (VQA) context, users often pose ambiguous questions to visual language models (VLMs) due to varying expression habits. Existing research addresses such ambiguities primarily by rephrasing questions. These…