The MIT-States dataset has 245 object classes, 115 attribute classes and ∼53K images. There is a wide range of objects (e.g., fish, persimmon, room) and attributes (e.g., mossy, deflated, dirty). On average, each object instance is modified by one of the 9 attributes it affords.
64 PAPERS • 4 BENCHMARKS
Structured3D is a large-scale photo-realistic dataset containing 3.5K house designs (a) created by professional designers with a variety of ground truth 3D structure annotations (b) and generate photo-realistic 2D images (c). The dataset consists of rendering images and corresponding ground truth annotations (e.g., semantic, albedo, depth, surface normal, layout) under different lighting and furniture configurations.
64 PAPERS • 1 BENCHMARK
VQA-RAD consists of 3,515 question–answer pairs on 315 radiology images.
Birdsnap is a large bird dataset consisting of 49,829 images from 500 bird species with 47,386 images used for training and 2,443 images used for testing.
63 PAPERS • 1 BENCHMARK
The Cross-Age Celebrity Dataset (CACD) contains 163,446 images from 2,000 celebrities collected from the Internet. The images are collected from search engines using celebrity name and year (2004-2013) as keywords. Therefore, it is possible to estimate the ages of the celebrities on the images by simply subtract the birth year from the year of which the photo was taken.
The Mall is a dataset for crowd counting and profiling research. Its images are collected from publicly accessible webcam. It mainly includes 2,000 video frames, and the head position of every pedestrian in all frames is annotated. A total of more than 60,000 pedestrians are annotated in this dataset.
Contains 145k captions for 28k images. The dataset challenges a model to recognize text, relate it to its visual context, and decide what part of the text to copy or paraphrase, requiring spatial, semantic, and visual reasoning between multiple text tokens and visual entities, such as objects.
The CAD-60 and CAD-120 data sets comprise of RGB-D video sequences of humans performing activities which are recording using the Microsoft Kinect sensor. Being able to detect human activities is important for making personal assistant robots useful in performing assistive tasks. The CAD dataset comprises twelve different activities (composed of several sub-activities) performed by four people in different environments, such as a kitchen, a living room, and office, etc.
62 PAPERS • 1 BENCHMARK
Few-Shot Object Detection Dataset (FSOD) is a high-diverse dataset specifically designed for few-shot object detection and intrinsically designed to evaluate thegenerality of a model on novel categories.
62 PAPERS • NO BENCHMARKS YET
Recipe1M+ is a dataset which contains one million structured cooking recipes with 13M associated images.
62 PAPERS • 3 BENCHMARKS
Semantic3D is a point cloud dataset of scanned outdoor scenes with over 3 billion points. It contains 15 training and 15 test scenes annotated with 8 class labels. This large labelled 3D point cloud data set of natural covers a range of diverse urban scenes: churches, streets, railroad tracks, squares, villages, soccer fields, castles to name just a few. The point clouds provided are scanned statically with state-of-the-art equipment and contain very fine details.
A large-scale multi-object tracking dataset for human tracking in occlusion, frequent crossover, uniform appearance and diverse body gestures. It is proposed to emphasize the importance of motion analysis in multi-object tracking instead of mainly appearance-matching-based diagram.
61 PAPERS • 1 BENCHMARK
We present the MSP-IMPROV corpus, a multimodal emotional database, where the goal is to have control over lexical content and emotion while also promoting naturalness in the recordings. Studies on emotion perception often require stimuli with fixed lexical content, but that convey different emotions. These stimuli can also serve as an instrument to understand how emotion modulates speech at the phoneme level, in a manner that controls for coarticulation. Such audiovisual data are not easily available from natural recordings. A common solution is to record actors reading sentences that portray different emotions, which may not produce natural behaviors. We propose an alternative approach in which we define hypothetical scenarios for each sentence that are carefully designed to elicit a particular emotion. Two actors improvise these emotion-specific situations, leading them to utter contextualized, non-read renditions of sentences that have fixed lexical content and convey different emot
61 PAPERS • 2 BENCHMARKS
The PlantVillage dataset consists of 54303 healthy and unhealthy leaf images divided into 38 categories by species and disease.
VeRi-776 is a vehicle re-identification dataset which contains 49,357 images of 776 vehicles from 20 cameras. The dataset is collected in the real traffic scenario, which is close to the setting of CityFlow. The dataset contains bounding boxes, types, colors and brands.
VisDrone is a large-scale benchmark with carefully annotated ground-truth for various important computer vision tasks, to make vision meet drones. The VisDrone2019 dataset is collected by the AISKYEYE team at Lab of Machine Learning and Data Mining, Tianjin University, China. The benchmark dataset consists of 288 video clips formed by 261,908 frames and 10,209 static images, captured by various drone-mounted cameras, covering a wide range of aspects including location (taken from 14 different cities separated by thousands of kilometers in China), environment (urban and country), objects (pedestrian, vehicles, bicycles, etc.), and density (sparse and crowded scenes). Note that, the dataset was collected using various drone platforms (i.e., drones with different models), in different scenarios, and under various weather and lighting conditions. These frames are manually annotated with more than 2.6 million bounding boxes of targets of frequent interests, such as pedestrians, cars, bicycl
The Car Parking Lot Dataset (CARPK) contains nearly 90,000 cars from 4 different parking lots collected by means of drone (PHANTOM 3 PROFESSIONAL). The images are collected with the drone-view at approximate 40 meters height. The image set is annotated by bounding box per car. All labeled bounding boxes have been well recorded with the top-left points and the bottom-right points. It is supporting object counting, object localizing, and further investigations with the annotation format in bounding boxes.
60 PAPERS • 1 BENCHMARK
ETH is a dataset for pedestrian detection. The testing set contains 1,804 images in three video clips. The dataset is captured from a stereo rig mounted on car, with a resolution of 640 x 480 (bayered), and a framerate of 13--14 FPS.
59 PAPERS • 5 BENCHMARKS
For many fundamental scene understanding tasks, it is difficult or impossible to obtain per-pixel ground truth labels from real images. Hypersim is a photorealistic synthetic dataset for holistic indoor scene understanding. It contains 77,400 images of 461 indoor scenes with detailed per-pixel labels and corresponding ground truth geometry.
59 PAPERS • 1 BENCHMARK
The LIP (Look into Person) dataset is a large-scale dataset focusing on semantic understanding of a person. It contains 50,000 images with elaborated pixel-wise annotations of 19 semantic human part labels and 2D human poses with 16 key points. The images are collected from real-world scenarios and the subjects appear with challenging poses and view, heavy occlusions, various appearances and low resolution.
The MMI Facial Expression Database consists of over 2900 videos and high-resolution still images of 75 subjects. It is fully annotated for the presence of AUs in videos (event coding), and partially coded on frame-level, indicating for each frame whether an AU is in either the neutral, onset, apex or offset phase. A small part was annotated for audio-visual laughters.
As far as we know, there only exists one large camouflaged object testing dataset, the COD10K, while the sizes of other testing datasets are less than 300. We then contribute another camouflaged object testing dataset, namely NC4K, which includes 4,121 images downloaded from the Internet. The new testing dataset can be used to evaluate the generalization ability of existing models.
Occluded REID is an occluded person dataset captured by mobile cameras, consisting of 2,000 images of 200 occluded persons (see Fig. (c)). Each identity has 5 full-body person images and 5 occluded person images with different types of occlusion.
InLoc is a dataset with reference 6DoF poses for large-scale indoor localization. Query photographs are captured by mobile phones at a different time than the reference 3D map, thus presenting a realistic indoor localization scenario.
58 PAPERS • NO BENCHMARKS YET
SPair-71k contains 70,958 image pairs with diverse variations in viewpoint and scale. Compared to previous datasets, it is significantly larger in number and contains more accurate and richer annotations.
58 PAPERS • 2 BENCHMARKS
COCO-QA is a dataset for visual question answering. It consists of:
57 PAPERS • NO BENCHMARKS YET
The O-Haze dataset contains 35 hazy images (size 2833×4657 pixels) for training. It has 5 hazy images for validation along with their corresponding ground truth images.
57 PAPERS • 1 BENCHMARK
SceneNN is an RGB-D scene dataset consisting of more than 100 indoor scenes. The scenes are captured at various places, e.g., offices, dormitory, classrooms, pantry, etc., from University of Massachusetts Boston and Singapore University of Technology and Design. All scenes are reconstructed into triangle meshes and have per-vertex and per-pixel annotation. The dataset is additionally enriched with fine-grained information such as axis-aligned bounding boxes, oriented bounding boxes, and object poses.
iSAID contains 655,451 object instances for 15 categories across 2,806 high-resolution images. The images of iSAID is the same as the DOTA-v1.0 dataset, which are manily collected from the Google Earth, some are taken by satellite JL-1, the others are taken by satellite GF-2 of the China Centre for Resources Satellite Data and Application.
57 PAPERS • 3 BENCHMARKS
Aff-Wild2 is an extension of the Aff-Wild dataset for affect recognition. It approximately doubles the number of included video frames and the number of subjects; thus, improving the variability of the included behaviors and of the involved persons.
56 PAPERS • 1 BENCHMARK
Diode Dense Indoor/Outdoor DEpth (DIODE) is the first standard dataset for monocular depth estimation comprising diverse indoor and outdoor scenes acquired with the same hardware setup. The training set consists of 8574 indoor and 16884 outdoor samples from 20 scans each. The validation set contains 325 indoor and 446 outdoor samples with each set from 10 different scans. The ground truth density for the indoor training and validation splits are approximately 99.54% and 99%, respectively. The density of the outdoor sets are naturally lower with 67.19% for training and 78.33% for validation subsets. The indoor and outdoor ranges for the dataset are 50m and 300m, respectively.
56 PAPERS • 2 BENCHMARKS
The Static Facial Expressions in the Wild (SFEW) dataset is a dataset for facial expression recognition. It was created by selecting static frames from the AFEW database by computing key frames based on facial point clustering. The most commonly used version, SFEW 2.0, was the benchmarking data for the SReco sub-challenge in EmotiW 2015. SFEW 2.0 has been divided into three sets: Train (958 samples), Val (436 samples) and Test (372 samples). Each of the images is assigned to one of seven expression categories, i.e., anger, disgust, fear, neutral, happiness, sadness, and surprise. The expression labels of the training and validation sets are publicly available, whereas those of the testing set are held back by the challenge organizer.
Winoground is a dataset for evaluating the ability of vision and language models to conduct visio-linguistic compositional reasoning. Given two images and two captions, the goal is to match them correctly -- but crucially, both captions contain a completely identical set of words, only in a different order. The dataset was carefully hand-curated by expert annotators and is labeled with a rich set of fine-grained tags to assist in analyzing model performance.
CASIA-MFSD is a dataset for face anti-spoofing. It contains 50 subjects, and 12 videos for each subject under different resolutions and light conditions. Three different spoof attacks are designed: replay, warp print and cut print attacks. The database contains 600 video recordings, in which 240 videos of 20 subjects are used for training and 360 videos of 30 subjects for testing.
55 PAPERS • 1 BENCHMARK
PASCAL-Part is a set of additional annotations for PASCAL VOC 2010. It goes beyond the original PASCAL object detection task by providing segmentation masks for each body part of the object. For categories that do not have a consistent set of parts (e.g., boat), it provides the silhouette annotation.
55 PAPERS • 4 BENCHMARKS
The Places365 dataset is a scene recognition dataset. It is composed of 10 million images comprising 434 scene classes. There are two versions of the dataset: Places365-Standard with 1.8 million train and 36000 validation images from K=365 scene classes, and Places365-Challenge-2016, in which the size of the training set is increased up to 6.2 million extra images, including 69 new scene classes (leading to a total of 8 million train images from 434 scene classes).
55 PAPERS • 8 BENCHMARKS
This dataset contains 21,889 outfits from polyvore.com, in which 17,316 are for training, 1,497 for validation and 3,076 for testing.
55 PAPERS • 3 BENCHMARKS
AGORA is a synthetic human dataset with high realism and accurate ground truth. It consists of around 14K training and 3K test images by rendering between 5 and 15 people per image using either image-based lighting or rendered 3D environments, taking care to make the images physically plausible and photoreal. In total, AGORA contains 173K individual person crops. AGORA provides (1) SMPL/SMPL-X parameters and (2) segmentation masks for each subject in images.
54 PAPERS • 4 BENCHMARKS
DDAD is a new autonomous driving benchmark from TRI (Toyota Research Institute) for long range (up to 250m) and dense depth estimation in challenging and diverse urban conditions. It contains monocular videos and accurate ground-truth depth (across a full 360 degree field of view) generated from high-density LiDARs mounted on a fleet of self-driving cars operating in a cross-continental setting. DDAD contains scenes from urban settings in the United States (San Francisco, Bay Area, Cambridge, Detroit, Ann Arbor) and Japan (Tokyo, Odaiba).
54 PAPERS • 1 BENCHMARK
The Salient Person dataset (SIP) contains 929 salient person samples with different poses and illumination conditions.
We introduce here a new database called UBFC-rPPG (stands for Univ. Bourgogne Franche-Comté Remote PhotoPlethysmoGraphy) comprising two datasets that are focused specifically on rPPG analysis. The UBFC-RPPG database was created using a custom C++ application for video acquisition with a simple low cost webcam (Logitech C920 HD Pro) at 30fps with a resolution of 640x480 in uncompressed 8-bit RGB format. A CMS50E transmissive pulse oximeter was used to obtain the ground truth PPG data comprising the PPG waveform as well as the PPG heart rates. During the recording, the subject sits in front of the camera (about 1m away from the camera) with his/her face visible. All experiments are conducted indoors with a varying amount of sunlight and indoor illumination. The link to download the complete video dataset is available on request. A basic Matlab implementation can also be provided to read ground truth data acquired with a pulse oximeter.
The UTD-MHAD dataset consists of 27 different actions performed by 8 subjects. Each subject repeated the action for 4 times, resulting in 861 action sequences in total. The RGB, depth, skeleton and the inertial sensor signals were recorded.
54 PAPERS • 2 BENCHMARKS
Composition-1K is a large-scale image matting dataset including 49300 training images and 1000 testing images.
53 PAPERS • 1 BENCHMARK
The Wireframe dataset consists of 5,462 images (5,000 for training, 462 for test) of indoor and outdoor man-made scenes.
53 PAPERS • 2 BENCHMARKS
EmoryNLP comprises 97 episodes, 897 scenes, and 12,606 utterances, where each utterance is annotated with one of the seven emotions borrowed from the six primary emotions in the Willcox (1982)’s feeling wheel, sad, mad, scared, powerful, peaceful, joyful, and a default emotion of neutral.
52 PAPERS • 1 BENCHMARK
FaceScape dataset provides 3D face models, parametric models and multi-view images in large-scale and high-quality. The camera parameters, the age and gender of the subjects are also included. The data have been released to public for non-commercial research purpose.
We propose Localized Narratives, a new form of multimodal image annotations connecting vision and language. We ask annotators to describe an image with their voice while simultaneously hovering their mouse over the region they are describing. Since the voice and the mouse pointer are synchronized, we can localize every single word in the description. This dense visual grounding takes the form of a mouse trace segment per word and is unique to our data. We annotated 849k images with Localized Narratives: the whole COCO, Flickr30k, and ADE20K datasets, and 671k images of Open Images, all of which we make publicly available. We provide an extensive analysis of these annotations showing they are diverse, accurate, and efficient to produce. We also demonstrate their utility on the application of controlled image captioning.
52 PAPERS • 5 BENCHMARKS
MINC is a large-scale, open dataset of materials in the wild.
52 PAPERS • NO BENCHMARKS YET