37 datasets found

The VQAv2 dataset, containing open-ended questions on 265k images, with 5.4 questions per image on average.

The TallyQA dataset is a large-scale open-ended visual counting dataset, which is well-suited to study statistical shortcuts.

The CLEVR-Humans dataset consists of 32,164 questions asked by humans, containing words and reasoning steps that were unseen in CLEVR.

The dataset is used for image captioning and visual question answering.

Visual question answering dataset

The VQA-CPv2 dataset is used to study the robustness of VQA methods against linguistic biases.

The VQA-CP dataset is a split of the VQA dataset, designed to test generalization skills across changes in the answer distribution between the training and the test sets.

GQA-OOD is a benchmark dedicated to the out-of-domain VQA evaluation.

GQA is a new dataset for real-world visual reasoning and compositional question answering.

The OK-VQA dataset is a visual question answering benchmark requiring external knowledge.

FVQA is a fact-based visual question answering dataset, containing 2190 images and 5826 (question, answer) pairs, with supporting facts selected from knowledge bases.

The Visual7W dataset for Visual Question Answering (VQA). The dataset contains 7,000 images with 7,000 queries.

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...

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.