Related papers: Learning to Answer Visual Questions from Web Video…
Significant progress has been made in the field of video question answering (VideoQA) thanks to deep learning and large-scale pretraining. Despite the presence of sophisticated model structures and powerful video-text foundation models,…
We present Q-ViD, a simple approach for video question answering (video QA), that unlike prior methods, which are based on complex architectures, computationally expensive pipelines or use closed models like GPTs, Q-ViD relies on a single…
Self-evolution offers a promising path for improving reasoning models without relying on intensive human annotation. However, extending this paradigm to video understanding remains underexplored and challenging: videos are long, dynamic,…
In the realm of multimodal tasks, Visual Question Answering (VQA) plays a crucial role by addressing natural language questions grounded in visual content. Knowledge-Based Visual Question Answering (KBVQA) advances this concept by adding…
The advancement of Large Vision Language Models (LVLMs) has significantly improved multimodal understanding, yet challenges remain in video reasoning tasks due to the scarcity of high-quality, large-scale datasets. Existing video…
We propose the inverse problem of Visual question answering (iVQA), and explore its suitability as a benchmark for visuo-linguistic understanding. The iVQA task is to generate a question that corresponds to a given image and answer pair.…
Question Answering (QA) systems require a large amount of annotated data which is costly and time-consuming to gather. Converting datasets of existing QA benchmarks are challenging due to different formats and complexities. To address these…
Generating videos from text is a challenging task due to its high computational requirements for training and infinite possible answers for evaluation. Existing works typically experiment on simple or small datasets, where the…
Generating natural language questions from visual scenes, known as Visual Question Generation (VQG), has been explored in the recent past where large amounts of meticulously labeled data provide the training corpus. However, in practice, it…
Long-form videos that span across wide temporal intervals are highly information redundant and contain multiple distinct events or entities that are often loosely related. Therefore, when performing long-form video question answering…
Transfer learning is an important step to extract meaningful features and overcome the data limitation in the medical Visual Question Answering (VQA) task. However, most of the existing medical VQA methods rely on external data for transfer…
We propose ReKV, a novel training-free approach that enables efficient streaming video question-answering (StreamingVQA), by seamlessly integrating with existing Video Large Language Models (Video-LLMs). Traditional VideoQA systems struggle…
Modern machine learning methods require significant amounts of labelled data, making the preparation process time-consuming and resource-intensive. In this paper, we propose to consider the process of prototyping a tool for annotating and…
Transformer-based architectures have recently demonstrated remarkable performance in the Visual Question Answering (VQA) task. However, such models are likely to disregard crucial visual cues and often rely on multimodal shortcuts and…
Creation of large-scale databases for Visual Question Answering tasks pertaining to the text data in a scene (text-VQA) involves skilful human annotation, which is tedious and challenging. With the advent of foundation models that handle…
Most existing approaches to Visual Question Answering (VQA) answer questions directly, however, people usually decompose a complex question into a sequence of simple sub questions and finally obtain the answer to the original question after…
Despite rapid advancements in video generation models, aligning their outputs with complex user intent remains challenging. Existing test-time optimization methods are typically either computationally expensive or require white-box access…
Visual Question Answering (VQA) is a challenging task of predicting the answer to a question about the content of an image. Prior works directly evaluate the answering models by simply calculating the accuracy of predicted answers. However,…
The multimodal task of Visual Question Answering (VQA) encompassing elements of Computer Vision (CV) and Natural Language Processing (NLP), aims to generate answers to questions on any visual input. Over time, the scope of VQA has expanded…
Reasoning over sports videos for question answering is an important task with numerous applications, such as player training and information retrieval. However, this task has not been explored due to the lack of relevant datasets and the…