全球最全计算机视觉资料（0：|软件|数据集|挑战赛|创业公司）

目标检测和深度学习

Software

1. Caffe [http://caffe.berkeleyvision.org/]
2. PyTorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration [https://github.com/pytorch/pytorch]
3. CNTK - Microsoft Cognitive Toolkit [https://github.com/Microsoft/CNTK]
4. Theano [http://deeplearning.net/software/theano/]
5. cuda-convnet [https://code.google.com/p/cuda-convnet2/]
6. DeepLearnToolbox [https://github.com/rasmusbergpalm/DeepLearnToolbox]
7. Deepnet [https://github.com/nitishsrivastava/deepnet]
8. Deeppy [https://github.com/andersbll/deeppy]
9. JavaNN [https://github.com/ivan-vasilev/neuralnetworks]
10. hebel [https://github.com/hannes-brt/hebel]
11. Mocha.jl [https://github.com/pluskid/Mocha.jl]
12. OpenDL [https://github.com/guoding83128/OpenDL]
13. cuDNN [https://developer.nvidia.com/cuDNN]
14. MGL [http://melisgl.github.io/mgl-pax-world/mgl-manual.html]
15. Knet.jl [https://github.com/denizyuret/Knet.jl]
16. Nvidia DIGITS - a web app based on Caffe [https://github.com/NVIDIA/DIGITS]
17. Neon - Python based Deep Learning Framework [https://github.com/NervanaSystems/neon]
18. . Keras - Theano based Deep Learning Library [http://keras.io]
19. . Chainer - A flexible framework of neural networks for deep learning [http://chainer.org/]
20. RNNLIB - A recurrent neural network library [http://sourceforge.net/p/rnnl/wiki/Home/]
21. Brainstorm - Fast, flexible and fun neural networks. [https://github.com/IDSIA/brainstorm]
22. Tensorflow - Open source software library for numerical computation using data flow graphs [https://github.com/tensorflow/tensorflow]
23. DMTK - Microsoft Distributed Machine Learning Tookit [https://github.com/Microsoft/DMTK]
24. Scikit Flow - Simplified interface for TensorFlow [mimicking Scikit Learn] [https://github.com/google/skflow]
25. MXnet - Lightweight, Portable, Flexible Distributed/Mobile Deep Learning framework [https://github.com/dmlc/mxnet/]
26. Apache SINGA - A General Distributed Deep Learning Platform [http://singa.incubator.apache.org/]
27. DSSTNE - Amazon's library for building Deep Learning models [https://github.com/amznlabs/amazon-dsstne]
28. SyntaxNet - Google's syntactic parser - A TensorFlow dependency library [https://github.com/tensorflow/models/tree/master/syntaxnet]
29. mlpack - A scalable Machine Learning library [http://mlpack.org/]
30. Paddle - PArallel Distributed Deep LEarning by Baidu [https://github.com/baidu/paddle]
31. NeuPy - Theano based Python library for ANN and Deep Learning [http://neupy.com]
32. Sonnet - a library for constructing neural networks by Google's DeepMind [https://github.com/deepmind/sonnet]

Datasets

Detection

1. PASCAL VOC 2009 dataset Classification/Detection Competitions, Segmentation Competition, Person Layout Taster Competition datasets
2. LabelMe dataset LabelMe is a web-based image annotation tool that allows researchers to label images and share the annotations with the rest of the community. If you use the database, we only ask that you contribute to it, from time to time, by using the labeling tool.
3. BioID Face Detection Database
4. 1521 images with human faces, recorded under natural conditions, i.e. varying illumination and complex background. The eye positions have been set manually.
5. CMU/VASC & PIE Face dataset
6. Yale Face dataset
7. Caltech Cars, Motorcycles, Airplanes, Faces, Leaves, Backgrounds
8. Caltech 101 Pictures of objects belonging to 101 categories
9. Caltech 256 Pictures of objects belonging to 256 categories
10. Daimler Pedestrian Detection Benchmark 15,560 pedestrian and non-pedestrian samples (image cut-outs) and 6744 additional full images not containing pedestrians for bootstrapping. The test set contains more than 21,790 images with 56,492 pedestrian labels (fully visible or partially occluded), captured from a vehicle in urban traffic.
11. MIT Pedestrian dataset CVC Pedestrian Datasets
12. CVC Pedestrian Datasets CBCL Pedestrian Database
13. MIT Face dataset CBCL Face Database
14. MIT Car dataset CBCL Car Database
15. MIT Street dataset CBCL Street Database
16. INRIA Person Data Set A large set of marked up images of standing or walking people
17. INRIA car dataset A set of car and non-car images taken in a parking lot nearby INRIA
18. INRIA horse dataset A set of horse and non-horse images
19. H3D Dataset 3D skeletons and segmented regions for 1000 people in images
20. HRI RoadTraffic dataset A large-scale vehicle detection dataset
21. BelgaLogos 10000 images of natural scenes, with 37 different logos, and 2695 logos instances, annotated with a bounding box.
22. FlickrBelgaLogos 10000 images of natural scenes grabbed on Flickr, with 2695 logos instances cut and pasted from the BelgaLogos dataset.
23. FlickrLogos-32 The dataset FlickrLogos-32 contains photos depicting logos and is meant for the evaluation of multi-class logo detection/recognition as well as logo retrieval methods on real-world images. It consists of 8240 images downloaded from Flickr.
24. TME Motorway Dataset 30000+ frames with vehicle rear annotation and classification (car and trucks) on motorway/highway sequences. Annotation semi-automatically generated using laser-scanner data. Distance estimation and consistent target ID over time available.
25. PHOS (Color Image Database for illumination invariant feature selection) Phos is a color image database of 15 scenes captured under different illumination conditions. More particularly, every scene of the database contains 15 different images: 9 images captured under various strengths of uniform illumination, and 6 images under different degrees of non-uniform illumination. The images contain objects of different shape, color and texture and can be used for illumination invariant feature detection and selection.
26. CaliforniaND: An Annotated Dataset For Near-Duplicate Detection In Personal Photo Collections California-ND contains 701 photos taken directly from a real user's personal photo collection, including many challenging non-identical near-duplicate cases, without the use of artificial image transformations. The dataset is annotated by 10 different subjects, including the photographer, regarding near duplicates.
27. USPTO Algorithm Challenge, Detecting Figures and Part Labels in Patents Contains drawing pages from US patents with manually labeled figure and part labels.
28. Abnormal Objects Dataset Contains 6 object categories similar to object categories in Pascal VOC that are suitable for studying the abnormalities stemming from objects.
29. Human detection and tracking using RGB-D camera Collected in a clothing store. Captured with Kinect (640*480, about 30fps)
30. Multi-Task Facial Landmark (MTFL) dataset This dataset contains 12,995 face images collected from the Internet. The images are annotated with (1) five facial landmarks, (2) attributes of gender, smiling, wearing glasses, and head pose.
31. WIDER FACE: A Face Detection Benchmark WIDER FACE dataset is a face detection benchmark dataset with images selected from the publicly available WIDER dataset. It contains 32,203 images and 393,703 face annotations.
32. PIROPO Database: People in Indoor ROoms with Perspective and Omnidirectional cameras Multiple sequences recorded in two different indoor rooms, using both omnidirectional and perspective cameras, containing people in a variety of situations (people walking, standing, and sitting). Both annotated and non-annotated sequences are provided, where ground truth is point-based. In total, more than 100,000 annotated frames are available.

Classification

1. PASCAL VOC 2009 dataset Classification/Detection Competitions, Segmentation Competition, Person Layout Taster Competition datasets
2. Caltech Cars, Motorcycles, Airplanes, Faces, Leaves, Backgrounds
3. Caltech 101 Pictures of objects belonging to 101 categories
4. Caltech 256 Pictures of objects belonging to 256 categories
5. ETHZ Shape Classes A dataset for testing object class detection algorithms. It contains 255 test images and features five diverse shape-based classes (apple logos, bottles, giraffes, mugs, and swans).
6. Flower classification data sets 17 Flower Category Dataset
7. Animals with attributes A dataset for Attribute Based Classification. It consists of 30475 images of 50 animals classes with six pre-extracted feature representations for each image.
8. Stanford Dogs Dataset Dataset of 20,580 images of 120 dog breeds with bounding-box annotation, for fine-grained image categorization.
9. Video classification USAA dataset The USAA dataset includes 8 different semantic class videos which are home videos of social occassions which feature activities of group of people. It contains around 100 videos for training and testing respectively. Each video is labeled by 69 attributes. The 69 attributes can be broken down into five broad classes: actions, objects, scenes, sounds, and camera movement.
10. McGill Real-World Face Video Database This database contains 18000 video frames of 640x480 resolution from 60 video sequences, each of which recorded from a different subject (31 female and 29 male).
11. e-Lab Video Data Set Video data sets to train machines to recognise objects in our environment. e-VDS35 has 35 classes and a total of 2050 videos of roughly 10 seconds each.

Recognition

1. Face and Gesture Recognition Working Group FGnet Face and Gesture Recognition Working Group FGnet
2. Feret Face and Gesture Recognition Working Group FGnet
3. PUT face 9971 images of 100 people
4. Labeled Faces in the Wild A database of face photographs designed for studying the problem of unconstrained face recognition
5. Urban scene recognition Traffic Lights Recognition, Lara's public benchmarks.
6. PubFig: Public Figures Face Database The PubFig database is a large, real-world face dataset consisting of 58,797 images of 200 people collected from the internet. Unlike most other existing face datasets, these images are taken in completely uncontrolled situations with non-cooperative subjects.
7. YouTube Faces The data set contains 3,425 videos of 1,595 different people. The shortest clip duration is 48 frames, the longest clip is 6,070 frames, and the average length of a video clip is 181.3 frames.
8. MSRC-12: Kinect gesture data set The Microsoft Research Cambridge-12 Kinect gesture data set consists of sequences of human movements, represented as body-part locations, and the associated gesture to be recognized by the system.
9. QMUL underGround Re-IDentification (GRID) Dataset This dataset contains 250 pedestrian image pairs + 775 additional images captured in a busy underground station for the research on person re-identification.
10. Person identification in TV series Face tracks, features and shot boundaries from our latest CVPR 2013 paper. It is obtained from 6 episodes of Buffy the Vampire Slayer and 6 episodes of Big Bang Theory.
11. ChokePoint Dataset ChokePoint is a video dataset designed for experiments in person identification/verification under real-world surveillance conditions. The dataset consists of 25 subjects (19 male and 6 female) in portal 1 and 29 subjects (23 male and 6 female) in portal 2.
12. Hieroglyph Dataset Ancient Egyptian Hieroglyph Dataset.
13. Rijksmuseum Challenge Dataset: Visual Recognition for Art Dataset Over 110,000 photographic reproductions of the artworks exhibited in the Rijksmuseum (Amsterdam, the Netherlands). Offers four automatic visual recognition challenges consisting of predicting the artist, type, material and creation year. Includes a set of baseline features, and offer a baseline based on state-of-the-art image features encoded with the Fisher vector.
14. The OU-ISIR Gait Database, Treadmill Dataset Treadmill gait datasets composed of 34 subjects with 9 speed variations, 68 subjects with 68 subjects, and 185 subjects with various degrees of gait fluctuations.
15. The OU-ISIR Gait Database, Large Population Dataset Large population gait datasets composed of 4,016 subjects.
16. Pedestrian Attribute Recognition At Far Distance Large-scale PEdesTrian Attribute (PETA) dataset, covering more than 60 attributes (e.g. gender, age range, hair style, casual/formal) on 19000 images.
17. FaceScrub Face Dataset The FaceScrub dataset is a real-world face dataset comprising 107,818 face images of 530 male and female celebrities detected in images retrieved from the Internet. The images are taken under real-world situations (uncontrolled conditions). Name and gender annotations of the faces are included.
18. Depth-Based Person Identification Depth-Based Person Identification from Top View Dataset.

Tracking

1. Dataset-AMP: Luka Čehovin Zajc; Alan Lukežič; Aleš Leonardis; Matej Kristan. "Beyond Standard Benchmarks: Parameterizing Performance Evaluation in Visual Object Tracking." ICCV (2017). [paper]
2. Dataset-Nfs: Hamed Kiani Galoogahi, Ashton Fagg, Chen Huang, Deva Ramanan and Simon Lucey. "Need for Speed: A Benchmark for Higher Frame Rate Object Tracking." ICCV (2017) [paper] [supp] [project]
3. Dataset-DTB70: Siyi Li, Dit-Yan Yeung. "Visual Object Tracking for Unmanned Aerial Vehicles: A Benchmark and New Motion Models." AAAI (2017) [paper] [project] [dataset]
4. Dataset-UAV123: Matthias Mueller, Neil Smith and Bernard Ghanem. "A Benchmark and Simulator for UAV Tracking." ECCV (2016) [paper] [project] [dataset]
5. Dataset-TColor-128: Pengpeng Liang, Erik Blasch, Haibin Ling. "Encoding color information for visual tracking: Algorithms and benchmark." TIP (2015) [paper] [project] [dataset]
6. Dataset-NUS-PRO: Annan Li, Min Lin, Yi Wu, Ming-Hsuan Yang, and Shuicheng Yan. "NUS-PRO: A New Visual Tracking Challenge." PAMI (2015) [paper] [project] [Data_360(code:bf28)] [Data_baidu]] [View_360(code:515a)][View_baidu]]
7. Dataset-PTB: Shuran Song and Jianxiong Xiao. "Tracking Revisited using RGBD Camera: Unified Benchmark and Baselines." ICCV (2013) [paper] [project] [5 validation] [95 evaluation]
8. Dataset-ALOV300+: Arnold W. M. Smeulders, Dung M. Chu, Rita Cucchiara, Simone Calderara, Afshin Dehghan, Mubarak Shah. "Visual Tracking: An Experimental Survey." PAMI (2014) [paper] [project] Mirror Link:ALOV300++ Dataset Mirror Link:ALOV300++ Groundtruth
9. OTB2013: Wu, Yi, Jongwoo Lim, and Minghsuan Yang. "Online Object Tracking: A Benchmark." CVPR (2013). [paper]
10. OTB2015: Wu, Yi, Jongwoo Lim, and Minghsuan Yang. "Object Tracking Benchmark." TPAMI (2015). [paper] [project]
11. Dataset-VOT: [project]
12. [VOT13_paper_ICCV(http://www.votchallenge.net/vot2013/Download/vot_2013_paper.pdfThe)] Visual Object Tracking VOT2013 challenge results
13. [VOT14_paper_ECCV]The Visual Object Tracking VOT2014 challenge results
14. [VOT15_paper_ICCV]The Visual Object Tracking VOT2015 challenge results
15. [VOT16_paper_ECCV]The Visual Object Tracking VOT2016 challenge results
16. [VOT17_paper_ECCV]The Visual Object Tracking VOT2017 challenge results

Segmentation

1. Image Segmentation with A Bounding Box Prior dataset Ground truth database of 50 images with: Data, Segmentation, Labelling - Lasso, Labelling - Rectangle
2. PASCAL VOC 2009 dataset Classification/Detection Competitions, Segmentation Competition, Person Layout Taster Competition datasets
3. Motion Segmentation and OBJCUT data Cows for object segmentation, Five video sequences for motion segmentation
4. Geometric Context Dataset Geometric Context Dataset: pixel labels for seven geometric classes for 300 images
5. Crowd Segmentation Dataset This dataset contains videos of crowds and other high density moving objects. The videos are collected mainly from the BBC Motion Gallery and Getty Images website. The videos are shared only for the research purposes. Please consult the terms and conditions of use of these videos from the respective websites.
6. CMU-Cornell iCoseg Dataset Contains hand-labelled pixel annotations for 38 groups of images, each group containing a common foreground. Approximately 17 images per group, 643 images total.
7. Segmentation evaluation database 200 gray level images along with ground truth segmentations
8. The Berkeley Segmentation Dataset and Benchmark Image segmentation and boundary detection. Grayscale and color segmentations for 300 images, the images are divided into a training set of 200 images, and a test set of 100 images.
9. Weizmann horses 328 side-view color images of horses that were manually segmented. The images were randomly collected from the WWW.
10. Saliency-based video segmentation with sequentially updated priors 10 videos as inputs, and segmented image sequences as ground-truth
11. Daimler Urban Segmentation Dataset The dataset consists of video sequences recorded in urban traffic. The dataset consists of 5000 rectified stereo image pairs. 500 frames come with pixel-level semantic class annotations into 5 classes: ground, building, vehicle, pedestrian, sky. Dense disparity maps are provided as a reference.
12. DAVIS: Densely Annotated VIdeo Segmentation A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation.

Foreground/Background

1. Wallflower Dataset For evaluating background modelling algorithms
2. Foreground/Background Microsoft Cambridge Dataset Foreground/Background segmentation and Stereo dataset from Microsoft Cambridge
3. Stuttgart Artificial Background Subtraction Dataset The SABS (Stuttgart Artificial Background Subtraction) dataset is an artificial dataset for pixel-wise evaluation of background models.
4. Image Alpha Matting Dataset Image Alpha Matting Dataset.
5. LASIESTA: Labeled and Annotated Sequences for Integral Evaluation of SegmenTation Algorithms LASIESTA is composed by many real indoor and outdoor sequences organized in diferent categories, each of one covering a specific challenge in moving object detection strategies.

Saliency Detection (source)

1. AIM 120 Images / 20 Observers (Neil D. B. Bruce and John K. Tsotsos 2005).
2. LeMeur 27 Images / 40 Observers (O. Le Meur, P. Le Callet, D. Barba and D. Thoreau 2006).
3. Kootstra 100 Images / 31 Observers (Kootstra, G., Nederveen, A. and de Boer, B. 2008).
4. DOVES 101 Images / 29 Observers (van der Linde, I., Rajashekar, U., Bovik, A.C., Cormack, L.K. 2009).
5. Ehinger 912 Images / 14 Observers (Krista A. Ehinger, Barbara Hidalgo-Sotelo, Antonio Torralba and Aude Oliva 2009).
6. NUSEF 758 Images / 75 Observers (R. Subramanian, H. Katti, N. Sebe1, M. Kankanhalli and T-S. Chua 2010).
7. JianLi 235 Images / 19 Observers (Jian Li, Martin D. Levine, Xiangjing An and Hangen He 2011).
8. Extended Complex Scene Saliency Dataset (ECSSD) ECSSD contains 1000 natural images with complex foreground or background. For each image, the ground truth mask of salient object(s) is provided.

Video Surveillance

1. CAVIAR For the CAVIAR project a number of video clips were recorded acting out the different scenarios of interest. These include people walking alone, meeting with others, window shopping, entering and exitting shops, fighting and passing out and last, but not least, leaving a package in a public place.
2. ViSOR ViSOR contains a large set of multimedia data and the corresponding annotations.
3. CUHK Crowd Dataset 474 video clips from 215 crowded scenes, with ground truth on group detection and video classes.?
4. TImes Square Intersection (TISI) Dataset A busy outdoor dataset for research on visual surveillance.
5. Educational Resource Centre (ERCe) Dataset An indoor dataset collected from a university campus for physical event understanding of long video streams.
6. PIROPO Database: People in Indoor ROoms with Perspective and Omnidirectional cameras Multiple sequences recorded in two different indoor rooms, using both omnidirectional and perspective cameras, containing people in a variety of situations (people walking, standing, and sitting). Both annotated and non-annotated sequences are provided, where ground truth is point-based. In total, more than 100,000 annotated frames are available.

Multiview

1. 3D Photography Dataset Multiview stereo data sets: a set of images
2. Multi-view Visual Geometry group's data set Dinosaur, Model House, Corridor, Aerial views, Valbonne Church, Raglan Castle, Kapel sequence
3. Oxford reconstruction data set (building reconstruction) Oxford colleges
4. Multi-View Stereo dataset (Vision Middlebury) Temple, Dino
5. Multi-View Stereo for Community Photo Collections Venus de Milo, Duomo in Pisa, Notre Dame de Paris
6. IS-3D Data Dataset provided by Center for Machine Perception
7. CVLab dataset CVLab dense multi-view stereo image database
8. 3D Objects on Turntable Objects viewed from 144 calibrated viewpoints under 3 different lighting conditions
9. Object Recognition in Probabilistic 3D Scenes Images from 19 sites collected from a helicopter flying around Providence, RI. USA. The imagery contains approximately a full circle around each site.
10. Multiple cameras fall dataset 24 scenarios recorded with 8 IP video cameras. The first 22 first scenarios contain a fall and confounding events, the last 2 ones contain only confounding events.
11. CMP Extreme View Dataset 15 wide baseline stereo image pairs with large viewpoint change, provided ground truth homographies.
12. KTH Multiview Football Dataset II This dataset consists of 8000+ images of professional footballers during a match of the Allsvenskan league. It consists of two parts: one with ground truth pose in 2D and one with ground truth pose in both 2D and 3D.
13. Disney Research light field datasets This dataset includes: camera calibration information, raw input images we have captured, radially undistorted, rectified, and cropped images, depth maps resulting from our reconstruction and propagation algorithm, depth maps computed at each available view by the reconstruction algorithm without the propagation applied.
14. CMU Panoptic Studio Dataset Multiple people social interaction dataset captured by 500+ synchronized video cameras, with 3D full body skeletons and calibration data.
15. 4D Light Field Dataset 24 synthetic scenes. Available data per scene: 9x9 input images (512x512x3) , ground truth (disparity and depth), camera parameters, disparity ranges, evaluation masks.

Action

1. UCF Sports Action Dataset This dataset consists of a set of actions collected from various sports which are typically featured on broadcast television channels such as the BBC and ESPN. The video sequences were obtained from a wide range of stock footage websites including BBC Motion gallery, and GettyImages.
2. UCF Aerial Action Dataset This dataset features video sequences that were obtained using a R/C-controlled blimp equipped with an HD camera mounted on a gimbal.The collection represents a diverse pool of actions featured at different heights and aerial viewpoints. Multiple instances of each action were recorded at different flying altitudes which ranged from 400-450 feet and were performed by different actors.
3. UCF YouTube Action Dataset It contains 11 action categories collected from YouTube.
4. Weizmann action recognition Walk, Run, Jump, Gallop sideways, Bend, One-hand wave, Two-hands wave, Jump in place, Jumping Jack, Skip.
5. UCF50 UCF50 is an action recognition dataset with 50 action categories, consisting of realistic videos taken from YouTube.
6. ASLAN The Action Similarity Labeling (ASLAN) Challenge.
7. MSR Action Recognition Datasets The dataset was captured by a Kinect device. There are 12 dynamic American Sign Language (ASL) gestures, and 10 people. Each person performs each gesture 2-3 times.
8. KTH Recognition of human actions Contains six types of human actions (walking, jogging, running, boxing, hand waving and hand clapping) performed several times by 25 subjects in four different scenarios: outdoors, outdoors with scale variation, outdoors with different clothes and indoors.
9. Hollywood-2 Human Actions and Scenes dataset Hollywood-2 datset contains 12 classes of human actions and 10 classes of scenes distributed over 3669 video clips and approximately 20.1 hours of video in total.
10. Collective Activity Dataset This dataset contains 5 different collective activities : crossing, walking, waiting, talking, and queueing and 44 short video sequences some of which were recorded by consumer hand-held digital camera with varying view point.
11. Olympic Sports Dataset The Olympic Sports Dataset contains YouTube videos of athletes practicing different sports.
12. SDHA 2010 Surveillance-type videos
13. VIRAT Video Dataset The dataset is designed to be realistic, natural and challenging for video surveillance domains in terms of its resolution, background clutter, diversity in scenes, and human activity/event categories than existing action recognition datasets.
14. HMDB: A Large Video Database for Human Motion Recognition Collected from various sources, mostly from movies, and a small proportion from public databases, YouTube and Google videos. The dataset contains 6849 clips divided into 51 action categories, each containing a minimum of 101 clips.
15. Stanford 40 Actions Dataset Dataset of 9,532 images of humans performing 40 different actions, annotated with bounding-boxes.
16. 50Salads dataset Fully annotated dataset of RGB-D video data and data from accelerometers attached to kitchen objects capturing 25 people preparing two mixed salads each (4.5h of annotated data). Annotated activities correspond to steps in the recipe and include phase (pre-/ core-/ post) and the ingredient acted upon.
17. Penn Sports Action The dataset contains 2326 video sequences of 15 different sport actions and human body joint annotations for all sequences.
18. CVRR-HANDS 3D A Kinect dataset for hand detection in naturalistic driving settings as well as a challenging 19 dynamic hand gesture recognition dataset for human machine interfaces.
19. TUM Kitchen Data Set Observations of several subjects setting a table in different ways. Contains videos, motion capture data, RFID tag readings,...
20. TUM Breakfast Actions Dataset
21. This dataset comprises of 10 actions related to breakfast preparation, performed by 52 different individuals in 18 different kitchens.
22. MPII Cooking Activities Dataset Cooking Activities dataset.
23. GTEA Gaze+ Dataset This dataset consists of seven meal-preparation activities, each performed by 10 subjects. Subjects perform the activities based on the given cooking recipes.
24. UTD-MHAD: multimodal human action recogniton dataset The dataset consists of four temporally synchronized data modalities. These modalities include RGB videos, depth videos, skeleton positions, and inertial signals (3-axis acceleration and 3-axis angular velocity) from a Kinect RGB-D camera and a wearable inertial sensor for a comprehensive set of 27 human actions.

Human pose/Expression

1. AFEW (Acted Facial Expressions In The Wild)/SFEW (Static Facial Expressions In The Wild) Dynamic temporal facial expressions data corpus consisting of close to real world environment extracted from movies.
2. Expression in-the-Wild (ExpW) Dataset Contains 91,793 faces manually labeled with expressions. Each of the face images was manually annotated as one of the seven basic expression categories.
3. ETHZ CALVIN Dataset CALVIN research group datasets
4. HandNet (annotated depth images of articulating hands) This dataset includes 214971 annotated depth images of hands captured by a RealSense RGBD sensor of hand poses. Annotations: per pixel classes, 6D fingertip pose, heatmap. Images -> Train: 202198, Test: 10000, Validation: 2773. Recorded at GIP Lab, Technion.
5. 3D Human Pose Estimation Depth videos + ground truth human poses from 2 viewpoints to improve 3D human pose estimation.

Medical

1. VIP Laparoscopic / Endoscopic Dataset Collection of endoscopic and laparoscopic (mono/stereo) videos and images
2. Mouse Embryo Tracking Database DB Contains 100 examples with the uncompressed frames, up to the 10th frame after the appearance of the 8th cell; a text file with the trajectories of all the cells, from appearance to division; a movie file showing the trajectories of the cells.
3. FIRE Fundus Image Registration Dataset 134 retinal image pairs and ground truth for registration.

Misc

1. Zurich Buildings Database ZuBuD Image Database contains over 1005 images about Zurich city building.
2. Color Name Data Sets
3. Mall dataset The mall dataset was collected from a publicly accessible webcam for crowd counting and activity profiling research.
4. QMUL Junction Dataset A busy traffic dataset for research on activity analysis and behaviour understanding.
5. Miracl-VC1 Miracl-VC1 is a lip-reading dataset including both depth and color images. Fifteen speakers positioned in the frustum of a MS Kinect sensor and utter ten times a set of ten words and ten phrases.
6. NYU Symmetry Database The mirror symmetry database contains 176 single-symmetry and 63 multiple-symmetry images (.png files) with accompanying ground-truth annotations (.mat files).
7. RGB-W: When Vision Meets Wireless Data with the wireless signal emitted by individuals' cell phones, referred to as RGB-W.

Challenge

1. Microsoft COCO Image Captioning Challenge [https://competitions.codalab.org/competitions/3221]
2. ImageNet Large Scale Visual Recognition Challenge [http://www.image-net.org/]
3. COCO 2017 Detection Challenge [http://cocodataset.org/#detections-challenge2017]
4. Visual Domain Adaptation (VisDA2017) Segmentation Challenge [https://competitions.codalab.org/competitions/17054]
5. The PASCAL Visual Object Classes Homepage [http://host.robots.ox.ac.uk/pascal/VOC/]
6. YouTube-8M Large-Scale Video Understanding [https://research.google.com/youtube8m/workshop.html]
7. joint COCO and Places Challenge [https://places-coco2017.github.io/]
8. Places Challenge 2017: Deep Scene Understanding is held jointly with COCO Challenge at ICCV'17 [http://placeschallenge.csail.mit.edu/]
9. COCO Challenges. [http://cocodataset.org/#home]
10. VQA Challenge 2017 [http://visualqa.org/]
11. The Joint Video and Language Understanding Workshop: MovieQA and The Large Scale Movie Description Challenge (LSMDC), at ICCV 2017 [https://sites.google.com/site/describingmovies/challenge]
12. Microsoft Multimedia Challenge (2017) [http://ms-multimedia-challenge.com/2017/challenge]
13. MOTChallenge: The Multiple Object Tracking Benchmark [https://motchallenge.net/]
14. Visual Domain Adaptation Challenge [http://ai.bu.edu/visda-2017/]
15. MegaFace and MF2: Million-Scale Face Recognition [http://megaface.cs.washington.edu/]
16. Facial Keypoints Detection [https://www.kaggle.com/c/facial-keypoints-detection]
17. The VOT challenges Visual Object Tracking [http://www.votchallenge.net/]
18. Large-scale Scene Understanding Challenge. SCENE CLASSIFICATION, SEGMENTATION, SALIENCY PREDICTION [http://lsun.cs.princeton.edu/2017/]
19. AI Challenger·全球AI挑战赛 图像中文描述，人体骨骼关键点，场景分类 [https://challenger.ai/]
20. 2016上海BOT大数据应用大赛 [http://www.zhishu51.com/Activity/bot]

创业公司

1. 旷视科技：让机器看懂世界 [https://megvii.com/]
2. 云从科技：源自计算机视觉之父的人脸识别技术 [http://www.cloudwalk.cn/]
3. 格林深瞳：让计算机看懂世界 [http://www.deepglint.com/]
4. 北京陌上花科技有限公司：人工智能计算机视觉引擎 [http://www.dressplus.cn/]
5. 依图科技：与您一起构建计算机视觉的未来 [http://www.yitutech.com/]
6. 码隆科技：最时尚的人工智能 [https://www.malong.com/]
7. Linkface脸云科技：全球领先的人脸识别技术服务 [https://www.linkface.cn/]
8. 速感科技：让机器人认识世界，用机器人改变世界 [http://www.qfeeltech.com/]
9. 图森： 中国自动驾驶商业化领跑者 [http://www.tusimple.com/]
10. Sense TIme商汤科技：教会计算机看懂这个世界 [https://www.sensetime.com/]
11. 图普科技：专注于图像识别 [https://us.tuputech.com/?from=gz]
12. 亮风台： 专注增强现实，引领人机交互 [https://www.hiscene.com/]
13. 中科视拓 ： 知人识面辨万物，开源赋能共发展 [http://www.seetatech.com/]
14. 中科奥森:双目深度学习: 让生活和社会更安全 [http://www.authenmetric.com/]
15. 银河水滴：全球领先的步态识别技术 [http://www.watrix.cc/y1.html]