58 datasets found

A dataset for visual spatial relationship classification (VSRC) with nine well-defined spatial relations.

The Winoground dataset consists of 400 items, each containing two image-caption pairs (I0, C0), (I1, C1).

The VQA 1.0 dataset is a large-scale dataset for visual question answering, containing 15,000 images with 50,000 questions.

The VQA dataset is a large-scale visual question answering dataset that consists of pairs of images that require natural language answers.

Visual Question Answering (VQA) has achieved great success thanks to the fast development of deep neural networks (DNN). On the other hand, the data augmentation, as one of the...

A collection of datasets for visual question answering, including MovieQA, TVQA, AVSD, EQA, and Embodied QA.

Visual Spatial Reasoning (VSR) is a controlled probing dataset for testing vision-language models' capabilities of recognizing and reasoning about spatial relations in natural...

We use the VQA v2.0 dataset for the evaluation of our proposed joint model, where the answers are balanced in order to minimize the effectiveness of learning dataset priors.

The GQA dataset is a visual question answering dataset that characterizes in compositional question answering and visual reasoning about real-world images.

The TGIF-QA dataset consists of 165165 QA pairs chosen from 71741 animated GIFs. To evaluate the spatiotemporal reasoning ability at the video level, TGIF-QA dataset designs...

This paper proposes VQA-CP v2, a standard OOD benchmark in VQA.

This paper investigates whether a VLP can be compressed and debiased simultaneously by searching sparse and robust subnetworks.

The Conceptual Captions 12M (CC-12M) dataset consists of 12 million diverse and high-quality images paired with descriptive captions and titles.

The dataset used in the paper is Sort-of-CLEVR, a visual question answering dataset.

The dataset used in the paper is VQA-CP v2 and VQA 2.0, which are two standard datasets for visual question answering.

The Meta-VQA dataset is a modification of the VQA v2.0 dataset for Visual-Question-Answering, composed of 1234 unique tasks (questions), split into 870 training tasks and 373...

The CLEVR dataset is a dataset for visual question answering, where each image is annotated with a question.

The Visual7W dataset is a visual question answering dataset, which consists of images and corresponding questions.

Visual Question Answering (VQA) has achieved great success thanks to the fast development of deep neural networks (DNN). On the other hand, the data augmentation, as one of the...

The extended RSVQAxBEN dataset is an extension of the RSVQAxBEN dataset, including all the spectral bands of Sentinel-2 images with 10m and 20m spatial resolution.