58 datasets found

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.

The dataset for the SMART-101 challenge consists of 101 unique puzzles that require a mix of several elementary skills, including arithmetic, algebra, and spatial reasoning,...

The CLEVR-CoGenT dataset is a dataset for visual question answering, where the questions consist on comparing the position of two objects.

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 High Quality Image Text Pairs (HQITP-134M) dataset consists of 134 million diverse and high-quality images paired with descriptive captions and titles.

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 dataset used in the paper is a collection of images and corresponding referring expressions.

Visual ChatGPT is a system that integrates different Visual Foundation Models to understand visual information and generation corresponding answers.

The Super-CLEVR dataset contains synthetic scenes of randomly placed vehicles from 5 categories (car, plane, bicycle, motorbike, bus) with various attributes (color, material,...

The Super-CLEVR-3D dataset contains questions explicitly querying 3D understanding including object parts, 3D poses, and occlusions.

VQAvs is a dataset for visual question answering, containing questions answerable using visual images.

VQA-CPv1 and VQA-CPv2 are datasets for visual question answering, containing questions answerable using visual images.

Visual question answering is a multimodal task that requires the joint comprehension of visual and textual information. The proposed approach utilizes object attributes to...