相关论文: VISREAS: Complex Visual Reasoning with Unanswerabl…

In the era of Vision-Language Models (VLMs), enhancing multimodal reasoning capabilities remains a critical challenge, particularly in handling ambiguous or complex visual inputs, where initial inferences often lead to hallucinations or…

In traditional Visual Question Generation (VQG), most images have multiple concepts (e.g. objects and categories) for which a question could be generated, but models are trained to mimic an arbitrary choice of concept as given in their…

This paper revisits visual representation in knowledge-based visual question answering (VQA) and demonstrates that using regional information in a better way can significantly improve the performance. While visual representation is…

The rapid advancement of vision-language models (VLMs) has established a new paradigm in video anomaly detection (VAD): leveraging VLMs to simultaneously detect anomalies and provide comprehendible explanations for the decisions. Existing…

Understanding realistic visual scene images together with language descriptions is a fundamental task towards generic visual understanding. Previous works have shown compelling comprehensive results by building hierarchical structures for…

Free-form and open-ended Visual Question Answering systems solve the problem of providing an accurate natural language answer to a question pertaining to an image. Current VQA systems do not evaluate if the posed question is relevant to the…

No published work on visual question answering (VQA) accounts for ambiguity regarding where the content described in the question is located in the image. To fill this gap, we introduce VQ-FocusAmbiguity, the first VQA dataset that visually…

Even though there has been tremendous progress in the field of Visual Question Answering, models today still tend to be inconsistent and brittle. To this end, we propose a model-independent cyclic framework which increases consistency and…

Visual question answering is the task of answering questions about images. We introduce the VizWiz-VQA-Grounding dataset, the first dataset that visually grounds answers to visual questions asked by people with visual impairments. We…

Medical Visual Question Answering (MedVQA) presents a significant opportunity to enhance diagnostic accuracy and healthcare delivery by leveraging artificial intelligence to interpret and answer questions based on medical images. In this…

We address a question answering task on real-world images that is set up as a Visual Turing Test. By combining latest advances in image representation and natural language processing, we propose Ask Your Neurons, a scalable, jointly…

Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground intermediate concepts, and perform multi-step logical inference.…

A user pointing their phone at a supermarket shelf and asking "Which soda has the least sugar?" poses a difficult challenge for current visual Al assistants. Such queries require not only object recognition, but explicit set-based reasoning…

Visual Commonsense Reasoning, which is regarded as one challenging task to pursue advanced visual scene comprehension, has been used to diagnose the reasoning ability of AI systems. However, reliable reasoning requires a good grasp of the…

Large Multimodal Models (LMMs) have made significant strides in visual question-answering for single images. Recent advancements like long-context LMMs have allowed them to ingest larger, or even multiple, images. However, the ability to…

Despite progress on general tasks, vision-language models (VLMs) still struggle with challenges that demand both fine-grained visual grounding and external knowledge, a synergy overlooked by existing benchmarks that evaluate these abilities…

Visual Question Answering (VQA) is a challenging task that requires the joint understanding of natural language and visual content. While early research primarily focused on recognizing objects and scene context, it often overlooked scene…

Social Intelligence Queries (Social-IQ) serve as the primary multimodal benchmark for evaluating a model's social intelligence level. While impressive multiple-choice question(MCQ) accuracy is achieved by current solutions, increasing…

Visual question answering is a task of predicting the answer to a question about an image. Given that different people can provide different answers to a visual question, we aim to better understand why with answer groundings. We introduce…

Latent reasoning enables reasoning over continuous hidden states rather than explicit tokens, avoiding the language bottleneck and inference overhead of chain-of-thought for medical VQA. However, existing methods suffer from modality…