Related papers: Transferring Domain-Agnostic Knowledge in Video Qu…
Visual Question Answering (VQA) deep-learning systems tend to capture superficial statistical correlations in the training data because of strong language priors and fail to generalize to test data with a significantly different…
We introduce LingoQA, a novel dataset and benchmark for visual question answering in autonomous driving. The dataset contains 28K unique short video scenarios, and 419K annotations. Evaluating state-of-the-art vision-language models on our…
Learning transferable and domain adaptive feature representations from videos is important for video-relevant tasks such as action recognition. Existing video domain adaptation methods mainly rely on adversarial feature alignment, which has…
Ensuring safety in autonomous driving is a complex challenge requiring handling unknown objects and unforeseen driving scenarios. We develop multiscale video transformers capable of detecting unknown objects using only motion cues. Video…
Meta-learning provides a promising way for learning to efficiently learn and achieves great success in many applications. However, most meta-learning literature focuses on dealing with tasks from a same domain, making it brittle to…
A fundamental ability of humans is to utilize commonsense knowledge in language understanding and question answering. In recent years, many knowledge-enhanced Commonsense Question Answering (CQA) approaches have been proposed. However, it…
A source model trained on source data and a target model learned through unsupervised domain adaptation (UDA) usually encode different knowledge. To understand the adaptation process, we portray their knowledge difference with image…
Humans acquire knowledge through three cognitive stages: perceiving information, comprehending knowledge, and adapting knowledge to solve novel problems. Videos serve as an effective medium for this learning process, facilitating a…
Conventional VQA approaches primarily rely on question-answer (Q&A) pairs to learn the spatio-temporal dynamics of video content. However, most existing annotations are event-centric, which restricts the model's ability to capture the…
This paper presents a state-of-the-art model for visual question answering (VQA), which won the first place in the 2017 VQA Challenge. VQA is a task of significant importance for research in artificial intelligence, given its multimodal…
To date, visual question answering (VQA) (i.e., image QA and video QA) is still a holy grail in vision and language understanding, especially for video QA. Compared with image QA that focuses primarily on understanding the associations…
We present a novel mechanism to embed prior knowledge in a model for visual question answering. The open-set nature of the task is at odds with the ubiquitous approach of training of a fixed classifier. We show how to exploit additional…
Building benchmarks to systemically analyze different capabilities of video question answering (VideoQA) models is challenging yet crucial. Existing benchmarks often use non-compositional simple questions and suffer from language biases,…
Visual question answering (VQA) models are designed to demonstrate visual-textual reasoning capabilities. However, their real-world applicability is hindered by a lack of comprehensive benchmark datasets. Existing domain generalization…
The remarkable success of deep learning in various domains relies on the availability of large-scale annotated datasets. However, obtaining annotations is expensive and requires great effort, which is especially challenging for videos.…
DaNetQA, a new question-answering corpus, follows (Clark et. al, 2019) design: it comprises natural yes/no questions. Each question is paired with a paragraph from Wikipedia and an answer, derived from the paragraph. The task is to take…
Visual question answering requires a system to provide an accurate natural language answer given an image and a natural language question. However, it is widely recognized that previous generic VQA methods often exhibit a tendency to…
Video-Question-Answering (VideoQA) comprises the capturing of complex visual relation changes over time, remaining a challenge even for advanced Video Language Models (VLM), i.a., because of the need to represent the visual content to a…
Visual Question Answering (VQA) is challenging due to the complex cross-modal relations. It has received extensive attention from the research community. From the human perspective, to answer a visual question, one needs to read the…
Accurately estimating humans' subjective feedback on video fluency, e.g., motion consistency and frame continuity, is crucial for various applications like streaming and gaming. Yet, it has long been overlooked, as prior arts have focused…