The MS COCO (Microsoft Common Objects in Context) dataset is a large-scale object detection, segmentation, key-point detection, and captioning dataset. The dataset consists of 328K images.
10,085 PAPERS • 92 BENCHMARKS
The MNIST database (Modified National Institute of Standards and Technology database) is a large collection of handwritten digits. It has a training set of 60,000 examples, and a test set of 10,000 examples. It is a subset of a larger NIST Special Database 3 (digits written by employees of the United States Census Bureau) and Special Database 1 (digits written by high school students) which contain monochrome images of handwritten digits. The digits have been size-normalized and centered in a fixed-size image. The original black and white (bilevel) images from NIST were size normalized to fit in a 20x20 pixel box while preserving their aspect ratio. The resulting images contain grey levels as a result of the anti-aliasing technique used by the normalization algorithm. the images were centered in a 28x28 image by computing the center of mass of the pixels, and translating the image so as to position this point at the center of the 28x28 field.
6,965 PAPERS • 52 BENCHMARKS
Automatic image captioning is the task of producing a natural-language utterance (usually a sentence) that correctly reflects the visual content of an image. Up to this point, the resource most used for this task was the MS-COCO dataset, containing around 120,000 images and 5-way image-caption annotations (produced by paid annotators).
311 PAPERS • 2 BENCHMARKS
Outside Knowledge Visual Question Answering (OK-VQA) includes more than 14,000 questions that require external knowledge to answer.
255 PAPERS • 2 BENCHMARKS
TextVQA is a dataset to benchmark visual reasoning based on text in images. TextVQA requires models to read and reason about text in images to answer questions about them. Specifically, models need to incorporate a new modality of text present in the images and reason over it to answer TextVQA questions.
196 PAPERS • 2 BENCHMARKS
Visual Dialog (VisDial) dataset contains human annotated questions based on images of MS COCO dataset. This dataset was developed by pairing two subjects on Amazon Mechanical Turk to chat about an image. One person was assigned the job of a ‘questioner’ and the other person acted as an ‘answerer’. The questioner sees only the text description of an image (i.e., an image caption from MS COCO dataset) and the original image remains hidden to the questioner. Their task is to ask questions about this hidden image to “imagine the scene better”. The answerer sees the image, caption and answers the questions asked by the questioner. The two of them can continue the conversation by asking and answering questions for 10 rounds at max.
144 PAPERS • 6 BENCHMARKS
Science Question Answering (ScienceQA) is a new benchmark that consists of 21,208 multimodal multiple choice questions with diverse science topics and annotations of their answers with corresponding lectures and explanations. Out of the questions in ScienceQA, 10,332 (48.7%) have an image context, 10,220 (48.2%) have a text context, and 6,532 (30.8%) have both. Most questions are annotated with grounded lectures (83.9%) and detailed explanations (90.5%). The lecture and explanation provide general external knowledge and specific reasons, respectively, for arriving at the correct answer. To the best of our knowledge, ScienceQA is the first large-scale multimodal dataset that annotates lectures and explanations for the answers.
138 PAPERS • 1 BENCHMARK
SHAPES is a dataset of synthetic images designed to benchmark systems for understanding of spatial and logical relations among multiple objects. The dataset consists of complex questions about arrangements of colored shapes. The questions are built around compositions of concepts and relations, e.g. Is there a red shape above a circle? or Is a red shape blue?. Questions contain between two and four attributes, object types, or relationships. There are 244 questions and 15,616 images in total, with all questions having a yes and no answer (and corresponding supporting image). This eliminates the risk of learning biases.
111 PAPERS • 1 BENCHMARK
DocVQA consists of 50,000 questions defined on 12,000+ document images.
108 PAPERS • 2 BENCHMARKS
RAVEN consists of 1,120,000 images and 70,000 RPM (Raven's Progressive Matrices) problems, equally distributed in 7 distinct figure configurations.
80 PAPERS • NO BENCHMARKS YET
GuessWhat?! is a large-scale dataset consisting of 150K human-played games with a total of 800K visual question-answer pairs on 66K images.
73 PAPERS • NO BENCHMARKS YET
ST-VQA aims to highlight the importance of exploiting high-level semantic information present in images as textual cues in the VQA process.
72 PAPERS • NO BENCHMARKS YET
COCO-QA is a dataset for visual question answering. It consists of:
57 PAPERS • NO BENCHMARKS YET
DAQUAR (DAtaset for QUestion Answering on Real-world images) is a dataset of human question answer pairs about images.
51 PAPERS • NO BENCHMARKS YET
AI2 Diagrams (AI2D) is a dataset of over 5000 grade school science diagrams with over 150000 rich annotations, their ground truth syntactic parses, and more than 15000 corresponding multiple choice questions.
43 PAPERS • 1 BENCHMARK
FigureQA is a visual reasoning corpus of over one million question-answer pairs grounded in over 100,000 images. The images are synthetic, scientific-style figures from five classes: line plots, dot-line plots, vertical and horizontal bar graphs, and pie charts.
38 PAPERS • 1 BENCHMARK
The Image Paragraph Captioning dataset allows researchers to benchmark their progress in generating paragraphs that tell a story about an image. The dataset contains 19,561 images from the Visual Genome dataset. Each image contains one paragraph. The training/val/test sets contains 14,575/2,487/2,489 images.
30 PAPERS • 2 BENCHMARKS
DVQA is a synthetic question-answering dataset on images of bar-charts.
29 PAPERS • 1 BENCHMARK
PathVQA consists of 32,799 open-ended questions from 4,998 pathology images where each question is manually checked to ensure correctness.
27 PAPERS • 1 BENCHMARK
VQA-HAT (Human ATtention) is a dataset to evaluate the informative regions of an image depending on the question being asked about it. The dataset consists of human visual attention maps over the images in the original VQA dataset. It contains more than 60k attention maps.
26 PAPERS • NO BENCHMARKS YET
PlotQA is a VQA dataset with 28.9 million question-answer pairs grounded over 224,377 plots on data from real-world sources and questions based on crowd-sourced question templates. Existing synthetic datasets (FigureQA, DVQA) for reasoning over plots do not contain variability in data labels, real-valued data, or complex reasoning questions. Consequently, proposed models for these datasets do not fully address the challenge of reasoning over plots. In particular, they assume that the answer comes either from a small fixed size vocabulary or from a bounding box within the image. However, in practice this is an unrealistic assumption because many questions require reasoning and thus have real valued answers which appear neither in a small fixed size vocabulary nor in the image. In this work, we aim to bridge this gap between existing datasets and real world plots by introducing PlotQA. Further, 80.76% of the out-of-vocabulary (OOV) questions in PlotQA have answers that are not in a fixed
25 PAPERS • 5 BENCHMARKS
MathVista is a consolidated Mathematical reasoning benchmark within Visual contexts. It consists of three newly created datasets, IQTest, FunctionQA, and PaperQA, which address the missing visual domains and are tailored to evaluate logical reasoning on puzzle test figures, algebraic reasoning over functional plots, and scientific reasoning with academic paper figures, respectively. It also incorporates 9 MathQA datasets and 19 VQA datasets from the literature, which significantly enrich the diversity and complexity of visual perception and mathematical reasoning challenges within our benchmark. In total, MathVista includes 6,141 examples collected from 31 different datasets.
23 PAPERS • NO BENCHMARKS YET
RecipeQA is a dataset for multimodal comprehension of cooking recipes. It consists of over 36K question-answer pairs automatically generated from approximately 20K unique recipes with step-by-step instructions and images. Each question in RecipeQA involves multiple modalities such as titles, descriptions or images, and working towards an answer requires (i) joint understanding of images and text, (ii) capturing the temporal flow of events, and (iii) making sense of procedural knowledge.
23 PAPERS • 1 BENCHMARK
A new large-scale geometry problem-solving dataset - 3,002 multi-choice geometry problems - dense annotations in formal language for the diagrams and text - 27,213 annotated diagram logic forms (literals) - 6,293 annotated text logic forms (literals)
18 PAPERS • 1 BENCHMARK
Video-and-Language Inference is the task of joint multimodal understanding of video and text. Given a video clip with aligned subtitles as premise, paired with a natural language hypothesis based on the video content, a model needs to infer whether the hypothesis is entailed or contradicted by the given video clip. The Violin dataset is a dataset for this task which consists of 95,322 video-hypothesis pairs from 15,887 video clips, spanning over 582 hours of video. These video clips contain rich content with diverse temporal dynamics, event shifts, and people interactions, collected from two sources: (i) popular TV shows, and (ii) movie clips from YouTube channels.
17 PAPERS • NO BENCHMARKS YET
CLEVR-Ref+ is a synthetic diagnostic dataset for referring expression comprehension. The precise locations and attributes of the objects are readily available, and the referring expressions are automatically associated with functional programs. The synthetic nature allows control over dataset bias (through sampling strategy), and the modular programs enable intermediate reasoning ground truth without human annotators.
16 PAPERS • 2 BENCHMARKS
QED is a linguistically principled framework for explanations in question answering. Given a question and a passage, QED represents an explanation of the answer as a combination of discrete, human-interpretable steps: sentence selection := identification of a sentence implying an answer to the question referential equality := identification of noun phrases in the question and the answer sentence that refer to the same thing predicate entailment := confirmation that the predicate in the sentence entails the predicate in the question once referential equalities are abstracted away. The QED dataset is an expert-annotated dataset of QED explanations build upon a subset of the Google Natural Questions dataset.
14 PAPERS • 1 BENCHMARK
SQA3D is a dataset for embodied scene understanding, where an agent needs to comprehend the scene it situates from an first person's perspective and answer questions. The questions are designed to be situated, embodied and knowledge-intensive. We offer three different modalities to represent a 3D scene: 3D scan, egocentric video and BEV picture.
13 PAPERS • 2 BENCHMARKS
Visual Madlibs is a dataset consisting of 360,001 focused natural language descriptions for 10,738 images. This dataset is collected using automatically produced fill-in-the-blank templates designed to gather targeted descriptions about: people and objects, their appearances, activities, and interactions, as well as inferences about the general scene or its broader context.
13 PAPERS • NO BENCHMARKS YET
CLEVR-Dialog is a large diagnostic dataset for studying multi-round reasoning in visual dialog. Specifically, that authors construct a dialog grammar that is grounded in the scene graphs of the images from the CLEVR dataset. This combination results in a dataset where all aspects of the visual dialog are fully annotated. In total, CLEVR-Dialog contains 5 instances of 10-round dialogs for about 85k CLEVR images, totaling to 4.25M question-answer pairs.
10 PAPERS • NO BENCHMARKS YET
FM-IQA is a question-answering dataset containing over 150,000 images and 310,000 freestyle Chinese question-answer pairs and their English translations.
We propose the first question-answering dataset driven by STEM theorems. We annotated 800 QA pairs covering 350+ theorems spanning across Math, EE&CS, Physics and Finance. The dataset is collected by human experts with very high quality. We provide the dataset as a new benchmark to test the limit of large language models to apply theorems to solve challenging university-level questions. We provide a pipeline in the following to prompt LLMs and evaluate their outputs with WolframAlpha.
10 PAPERS • 1 BENCHMARK
DIOR-RSVG is a large-scale benchmark dataset of remote sensing data (RSVG). It aims to localize the referred objects in remote sensing (RS) images with the guidance of natural language. This new dataset includes image/expression/box triplets for training and evaluating visual grounding models.
7 PAPERS • NO BENCHMARKS YET
DUDE is formulated as an instance of Document Question Answering (DocQA) to evaluate how well current solutions deal with multi-page documents, if they can navigate and reason over the layout, and if they can generalize these skills to different document types and domains. Since we cannot provide question-answer pairs about, e.g., ticked checkboxes, on each document instance or document type, the challenge presented by DUDE is characterized equally as a Multi-Domain Long-Tailed Recognition problem
The VNHSGE (VietNamese High School Graduation Examination) dataset, developed exclusively for evaluating large language models (LLMs), is introduced in this article. The dataset, which covers nine subjects, was generated from the Vietnamese National High School Graduation Examination and comparable tests. 300 literary essays have been included, and there are over 19,000 multiple-choice questions on a range of topics. The dataset assesses LLMs in multitasking situations such as question answering, text generation, reading comprehension, visual question answering, and more by including both textual data and accompanying images. Using ChatGPT and BingChat, we evaluated LLMs on the VNHSGE dataset and contrasted their performance with that of Vietnamese students to see how well they performed. The results show that ChatGPT and BingChat both perform at a human level in a number of areas, including literature, English, history, geography, and civics education. They still have space to grow, t
7 PAPERS • 9 BENCHMARKS
IQUAD is a dataset for Visual Question Answering in interactive environments. It is built upon AI2-THOR, a simulated photo-realistic environment of configurable indoor scenes with interactive object. IQUAD V1 has 75,000 questions, each paired with a unique scene configuration.
6 PAPERS • NO BENCHMARKS YET
PDFVQA: A New Dataset for Real-World VQA on PDF Documents
3 PAPERS • NO BENCHMARKS YET
CLEVR-Math is a multi-modal math word problems dataset consisting of simple math word problems involving addition/subtraction, represented partly by a textual description and partly by an image illustrating the scenario. These word problems requires a combination of language, visual and mathematical reasoning.
2 PAPERS • NO BENCHMARKS YET
General-purpose Visual Understanding Evaluation (G-VUE) is a comprehensive benchmark covering the full spectrum of visual cognitive abilities with four functional domains -- Perceive, Ground, Reason, and Act. The four domains are embodied in 11 carefully curated tasks, from 3D reconstruction to visual reasoning and manipulation.
Visual Beliefs is a dataset of abstract scenes to study visual beliefs. The dataset consists of 8-frame scenes, and in each scene a person has a mistaken belief. The dataset can be used for two tasks: predicting who is mistaken and predicting when are they mistaken.
A large-scale dataset that links the assessment of image quality issues to two practical vision tasks: image captioning and visual question answering.
CUHK-QA is a dataset for natural language-based person search using iterative questioning.
1 PAPER • NO BENCHMARKS YET
ChiQA is a dataset designed for visual question answering tasks that not only measures the relatedness but also measures the answerability, which demands more fine-grained vision and language reasoning. It contains more than 40K questions and more than 200K question-images pairs. The questions are real-world image-independent queries that are more various and unbiased.
TinySocial is a dataset to enable research on Social Visual Question Answering.
The Visual Discriminative Question Generation (VDQG) dataset contains 11202 ambiguous image pairs collected from Visual Genome. Each image pair is annotated with 4.6 discriminative questions and 5.9 non-discriminative questions on average.
VQA 360° is a dataset for visual question answering on 360° images containing around 17,000 real-world image-question-answer triplets for a variety of question types.
VTQA is a dataset containing open-ended questions about image-text pairs. This dataset requires the model to align multimedia representations of the same entity to implement multi-hop reasoning between image and text and finally use natural language to answer the question. The aim of this dataset is to develop and benchmark models that are capable of multimedia entity alignment, multi-step reasoning and open-ended answer generation. VTQA dataset consists of 10,238 image-text pairs and 27,317 questions. The images are real images from MSCOCO dataset, containing a variety of entities. The annotators are required to first annotate relevant text according to the image, and then ask questions based on the image-text pair, and finally answer the question open-ended.
The simply-CLEVR dataset aims to provide a benchmark dataset that can be used for transparent quantitative evaluation of explanation methods (aka heatmaps/XAI methods). It is made of simple Visual Question Answering (VQA) questions, which are derived from the original CLEVR task, and where each question is accompanied by two Ground Truth Masks that serve as a basis for evaluating explanations on the input image.