Related papers: Understanding Video Scenes through Text: Insights …
While existing video benchmarks largely consider specialized downstream tasks like retrieval or question-answering (QA), contemporary multimodal AI systems must be capable of well-rounded common-sense reasoning akin to human visual…
Video text-based visual question answering (Video TextVQA) task aims to answer questions about videos by leveraging the visual text appearing within the videos. This task poses significant challenges, requiring models to accurately perceive…
Visual question answering (VQA) refers to the problem where, given an image and a natural language question about the image, a correct natural language answer has to be generated. A VQA model has to demonstrate both the visual understanding…
Cross-modal learning of video and text plays a key role in Video Question Answering (VideoQA). In this paper, we propose a visual-text attention mechanism to utilize the Contrastive Language-Image Pre-training (CLIP) trained on lots of…
Existing video understanding datasets mostly focus on human interactions, with little attention being paid to the "in the wild" settings, where the videos are recorded outdoors. We propose WILDQA, a video understanding dataset of videos…
Text-level discourse parsing aims to unmask how two sentences in the text are related to each other. We propose the task of Visual Discourse Parsing, which requires understanding discourse relations among scenes in a video. Here we use the…
The ideal form of Visual Question Answering requires understanding, grounding and reasoning in the joint space of vision and language and serves as a proxy for the AI task of scene understanding. However, most existing VQA benchmarks are…
We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark to advance video understanding from describing to explaining the temporal actions. Based on the dataset, we set up multi-choice and open-ended QA tasks…
We present a new dataset for Visual Question Answering (VQA) on document images called DocVQA. The dataset consists of 50,000 questions defined on 12,000+ document images. Detailed analysis of the dataset in comparison with similar datasets…
Visual texts embedded in videos carry rich semantic information, which is crucial for both holistic video understanding and fine-grained reasoning about local human actions. However, existing video understanding benchmarks largely overlook…
Despite remarkable recent progress, existing long-form VideoQA datasets fall short of meeting the criteria for genuine long-form video understanding. This is primarily due to the use of short videos for question curation, and the reliance…
Video text-based visual question answering (Video TextVQA) aims to answer questions by reasoning over visual textual content appearing in videos. Despite the strong multimodal video understanding capabilities of recent Video-LLMs, their…
Inspired by recent trends in vision and language learning, we explore applications of attention mechanisms for visio-lingual fusion within an application to story-based video understanding. Like other video-based QA tasks, video story…
Visual Question Answering (VQA) concerns providing answers to Natural Language questions about images. Several deep neural network approaches have been proposed to model the task in an end-to-end fashion. Whereas the task is grounded in…
Visual Question Answering (VQA) and Image Captioning (CAP), which are among the most popular vision-language tasks, have analogous scene-text versions that require reasoning from the text in the image. Despite their obvious resemblance, the…
Video text-based visual question answering (Video TextVQA) aims to answer questions by explicitly reading and reasoning about the text involved in a video. Most works in this field follow a frame-level framework which suffers from redundant…
Recent advancements in video-language understanding have been established on the foundation of image-text models, resulting in promising outcomes due to the shared knowledge between images and videos. However, video-language understanding…
Mathematical reasoning in real-world video settings presents a fundamentally different challenge than in static images or text. It requires interpreting fine-grained visual information, accurately reading handwritten or digital text, and…
Instructional videos provide detailed how-to guides for various tasks, with viewers often posing questions regarding the content. Addressing these questions is vital for comprehending the content, yet receiving immediate answers is…
Visual question answering (or VQA) is a new and exciting problem that combines natural language processing and computer vision techniques. We present a survey of the various datasets and models that have been used to tackle this task. The…