本项目由 ApacheCN 强力支持。
6月24 - 9月09, 2019 // Host by 天池 // Prize: $900,000
24 Jan - 25 July, 2019 // Host by Analytics Vidhya // Prize: INR 50,000
Note: You are expected to build a high performing recommendation engine using any framework of your choice. You are encouraged to use IBM Watson Studio Apache spark based Jupyter notebook.
Note: Following the success of the First WIDER Challenge Workshop, we organize a new round of challenge in conjunction with ICCV 2019. The challenge centers around the problem of precise localization of human faces and bodies, and accurate association of identities. It comprises of four tracks:
WIDER Face Detection, aims at soliciting new approaches to advance the state-of- the-art in face detection.
WIDER Pedestrian Detection, has the goal of gathering effective and efficient approaches to address the problem of pedestrian detection in unconstrained environments.
WIDER Cast Search by Portrait, presents an exciting challenge of searching cast across hundreds of movies.
WIDER Person Search by Language, aims to seek new approaches to search person by natural language.
交通数据 室内停车 公租房轮候 卫星遥感 文体公益活动 游客预约 道路积水 深圳图书馆进馆人次统计 龙岗区坂田街道交通流量 企业信用目录 坪山区民生诉求数据 坪山区河流域和易积水道路视频 光明区政府服务办事大厅预约
Note: Given the growing importance of the field and the potential societal impact in the medical domain or fair decision making, it is high time to bring disentanglement to the real-world:
Stage 1: Sim-to-real transfer learning - design representation learning algorithms on simulated data and transfer them to the real world.
Stage 2: Advancing disentangled representation learning to complicated physical objects.
05/01 - 07/30 2019 // Host by Biendata // Prize: ￥15,000
6月8日 - 9月, 2019 // Host by 睡前FUTURE.AI // Prize: 20,000元 x 2
Note: 全国高校大数据应用创新大赛”（以下简称大赛）是由教育部高等学校计算机类专业教学指导委员会、中国工程院中国工程科技知识中心和联合国教科文组织国际工程科技知识中心联合主办，复旦大学计算机学院承办，面向全国高校在校学生的，年度性大数据学科竞赛。 通用赛道：
May 27 - July 30, 2019 // Host by CodaLab // Prize: NaN
Note: DeepFashion2 (github) is a comprehensive fashion dataset. It contains 491K diverse images of 13 popular clothing categories from both commercial shopping stores and consumers. It totally has 801K clothing clothing items, where each item in an image is labeled with scale, occlusion, zoom-in, viewpoint, category, style, bounding box, dense landmarks and per-pixel mask.There are also 873K Commercial-Consumer clothes pairs.
The dataset is split into a training set (391K images), a validation set (34k images), and a test set (67k images).
Track 1 Clothes Landmark Estimation
Track 2 Clothes Retrieval
January 21 - July 31, 2019 // Host by crowdAI // Prize: 2 x travel grant
Note: In this challenge you will be provided with a dataset of RGB images of snakes, and their corresponding species (class). The goal is to train a classification model.
2019-09-03 至 2019-10-28 // Host by Kesci // Prize: 50万元人民币
2019-05-15 至 2019-10-31 // Host by 长风大数据平台 // Prize: ￥5万
2019-06-14 至 2019-09-20 // Host by 上海电信 // Prize: 40,000 元 x 2
Now - August 8, 2019 // Host by Kaggle // Prize: NaN
Note: Can you determine if two individuals are related?
7月1日 - 9月23日, 2019 // Host by Baidu AIstudio // Prize: ￥112,000
7月4-9月 2019 // Host by 中国移动 // Prize: 240,000 元
6月24 - 9月, 2019 // Host by 天池 // Prize: ￥十五万
7月5日 - 9月27日, 2019 // Host by Baidu AIstudio // Prize: ￥54,000
August, 13 - Oct 31, 2019 // Host by NeurIPS 2019 // Prize: $1,000USD
Note: Build the best AI bot to play reconnaissance blind chess, a challenge for making optimal decisions in the face of uncertainty. Reconnaissance blind chess is like chess except a player does not know where her opponent’s pieces are a priori. Rather, she can covertly sense a chosen 3x3 square of the board each turn and also learn partial information from captures.
Note: The goal of the SegTHOR challenge is to automatically segment 4 OAR: heart, aorta, trachea, esophagus. Participants will be provided with a training set 40 CT scans with manual segmentation. The test set will include 20 CT scans.
7月16 - 9月16, 2019 // Host by 天池 // Prize: ￥100000
Now - August 9, 2019 // Host by Kaggle // Prize: $10,000
Note: Experiment with creating puppy pics
Challenges and Opportunities in Automated Coding of COntentious Political Events (Cope 2019) @Euro CSS 2019
Note: We use English online news archives from India and China as data sources to create the training and test corpora. India and China are the source and the target countries respectively in our setting.
2019-06-01 至 2019-09-20 // Host by 中国科学院空间应用工程与技术中心 // Prize: ￥160000
7月05 - 9月25, 2019 // Host by 天池 // Prize: $25000 + $25000
- 15th of August 2019 // Host by ECML-PKDD 2019 // Prize: Eternal gratitude … or a bottle of wine.
Note: ARIEL, a mission to make the first large-scale survey of exoplanet atmospheres, has launched a global competition series to find innovative solutions for the interpretation and analysis of exoplanet data. You can find our press release here.
The first ARIEL Data Challenge invites professional and amateur data scientists around the world to use Machine Learning (ML) to remove noise from exoplanet observations caused by starspots and by instrumentation.
A second ARIEL Data Challenge that focuses on the retrieval of spectra from simulations of cloudy and cloud-free super-Earth and hot-Jupiter data was also launched today.
A further data analysis challenge to create pipelines for faster, more effective processing of the raw data gathered by the mission will be launched in June.
July 15, 2019 - Sep. 14, 2019 // Host by CodaLab // Prize: NaN
Note: The goal of this challenge is to probe how well current methods can recognize speakers from speech obtained ‘in the wild’. The challenge will consists of the following two tasks:
Audio only speaker verification - Fixed training data: This task requires that participants train only on the VoxCeleb2 dev dataset for which we have already released speaker verification labels. The dev dataset contains 1,092,009 utterances from 5,994 speakers.
Audio only speaker verification - Open training data: For the open training condition, participants can use the VoxCeleb datasets and any other data (including that which is not publicly released) except the challenge’s test data
July 4 - Aug 15 2019 // Host by CodaLab // Prize: NaN
Note: The 2nd 3DFAW Challenge evaluates 3D face reconstruction methods on a new large corpora of profile-to-profile face videos annotated with corresponding high-resolution 3D ground truth meshes. The corpora includes profile-to-profile videos obtained under a range of conditions:
high-definition in-the-lab video,
unconstrained video from an iPhone device
6月10日 - 8月2019年 // Host by SIGNATE // Prize: ¥2,300,000
Note: In 1970s, the Dunhuang Academy is established to systematically preserve the heritage. From the study, half of them suffer from corrosion and aging. Because the paintings are created by different artists from 10 centuries, it is non-trivial for manual restoration. And therefore, we release the first Dunhuang Challenge with 600 paintings, which enables an open and public attention in the research community on data driven e-heritage restoration.
This year, the academy is proposing to collaborate with Microsoft Research and other researchers over the world, aiming to solve the automatic restoration of the wall painting using computer vision and machine learning technology.
7月24日 - 9月21, 2019 // Host by 天池 // Prize: ￥300000
Note: The goal of MICCAI 2019 Challenge on accurate automated spinal curvature estimation and error correction from x-ray images is to investigate (semi-)automatic spinal curvature estimation algorithms and provide a standard evaluation framework with a set of x-ray images.
Note: This is round 2 of AutoCV: Image + Video! This is a 2-phase challenge, see the challenge rules for details. This is the FEED-BACK PHASE. The second phase (final blind-test phase) will be run from a separate submission site, to be announced after the end of the feed-back phase.
5月21日 - 10月14日, 2019 // Host by 讯飞开放平台 // Prize: 100万 RMB
Note: "iFLYTEK AI 开发者大赛"是由科大讯飞发起的顶尖人工智能竞赛平台，汇聚产学研各界力量，面向全球开发者发起数据算法及创新应用类挑战，推动人工智能前沿科学研究和创新成果转化，培育人工智能产业人才，助力人工智能生态建设。 2019 年，第二届 iFLYTEK AI 开发者大赛将继续开放科大讯飞优质大数据资源及人工智能核心技术，面向全球开发者发起数据算法及创新应用类挑战。
Note: Identify Pneumothorax disease in chest x-rays
Now - August 28, 2019 // Host by Kaggle // Prize: $30,000
Note: Can you measure the magnetic interactions between a pair of atoms?
Note: Advances in Image Manipulation workshop and challenges on image and video manipulation in conjunction with ICCV 2019.
AIM 2019 image manipulation challenges:
Bokeh Effect Challenge: Track 1 Fidelity;
Bokeh Effect Challenge: Track 2 Perceptual;
RAW-to-RGB Mapping Challenge: Track 1 Fidelity;
RAW-to-RGB Mapping Challenge: Track 2 Perceptual;
Real World Super-Resolution Challenge: Track 1 Same Domain;
Real World Super-Resolution Challenge: Track 2 Target Domain;
Demoireing Challenge: Track 1 Fidelity;
Demoireing Challenge: Track 2 Perceptual;
Constrained Super-Resolution Challenge: Track 1 Parameters optimization;
Constrained Super-Resolution Challenge: Track 2 Inference optimization;
Constrained Super-Resolution Challenge: Track 3 Fidelity optimization;
Extreme Super-Resolution Challenge: Track 1 Fidelity;
Extreme Super-Resolution Challenge: Track 2 Perceptual;
AIM 2019 video manipulation challenges:
Video Quality Mapping Challenge : Track 1 Supervised;
Video Quality Mapping Challenge : Track 2 Unsupervised;
Video Extreme Super-Resolution Challenge: Track 1 Fidelity;
Video Extreme Super-Resolution Challenge: Track 2 Perceptual;
Video Temporal Super-Resolution Challenge;
Note: Detect diabetic retinopathy to stop blindness before it’s too late
Note: The challenge data consists of a set of popular search queries and a fair size set of candidate documents. Challenge participants make a boolean relevant-or-not decision for each query-document pair. Human judgments are used to create labeled training and evaluation data for a subset of the query-document pairs. Evaluation of submissions will be based on the traditional F1 metric, incorporating components of both recall and precision.
06/28 - 08/31 2019 // Host by Biendata // Prize: 七万七千元
July 1st – Dec. 8th, 2019 // Host by NeurIPS 2019 // Prize: ~12,000USD
Note: Game of Drones is a multi-drone racing tournament conducted in the high-fidelity simulation environment AirSim. Participants will have the choice of three tiers: Planning only, Perception only, or Full Autonomous Racing. The aim is to combine challenges from adversarial planning and real-time perception and to encourage fusing learning- and model-based approaches.
2019-07-17 至 2019-09-30 // Host by 之江实验室 // Prize: 大赛总奖金池超过260万元
视频描述生成: 本赛题为视频描述（Video Caption）,视频描述的输入是一段视频，输出是描述视频主要故事的一段文本。
零样本目标检测: 零样本目标检测（zero-shot object detection）竞赛的任务是在已知类别上训练目标检测模型，但要求模型能够用于检测测试图片中未知类别的对象。
Note: The participants are encouraged to investigate neural network based methods (especially convolutional neural networks) with different network structures, in a hope of achieving the best quality with lightest network configuration for a good tradeoff of efficiency and complexity.
March 6 - November 3, 2019 // Host by CodaLab // Prize: NaN
Note: The 2019 Conference on Computational Language Learning (CoNLL) hosts a shared task (or ‘system bake-off’) on Cross-Framework Meaning Representation Parsing (MRP 2019).
The goal of the task is to advance data-driven parsing into graph-structured representations of sentence meaning.
Note: As a continuous effort to push forward the research on video object segmentation tasks, we plan to host a second workshop with a challenge based on the YouTube-VOS dataset, targeting at more diversified problem settings, i.e., we plan to provide two challenge tracks in this workshop.
Track 1: Video Object Segmentation
Track 2: Video Instance Segmentation
Note: Temporal localization of topics within video
Note: The goal of the challenge is to set up tasks for evaluating automatic algorithms on segmentation of organs-at-risk (OAR) and gross target volume (GTV) of tumors of two types of cancers, nasopharynx cancer and lung cancer, for radiation therapy planning. There are four tasks for evaluating the performance of the algorithms. Participants can choose to join all or either tasks according to their interests.
Task 1: Organ-at-risk segmentation from head & neck CT scans.
Task 2: Gross Target Volume segmentation of nasopharynx cancer.
Task 3: Organ-at-risk segmentation from chest CT scans.
Task 4: Gross Target Volume segmentation of lung cancer.
Note: In the absence of accurate gaze labels, we propose to advance the state of the art by carefully designing two challenges that combine human annotation of eye features with unlabeled data. These challenges focus on deeper understanding of the distribution underlying human eye state. We invite ML and CV researchers for participation.
Track-1 Semantic Segmentation challenge
Track-2 Synthetic Eye Generation challenge
May 16th - Sep 16th, 2019 // Host by CodaLab // Prize: NaN
Note: This competition is composed of two sub-challenges focusing on the two most widely used observing techniques: pupil tracking (angular differential imaging, ADI) and multi-spectral imaging combined with pupil tracking (multi-channel spectral differential imaging, ADI+mSDI).
06/25 - 09/25 2019 // Host by Biendata // Prize: ￥24,000元
The SG will provide participants with 5,000 structured desensitized ophthalmologic image set of patient’s age, sex, binocular color fundus photos and doctors’ diagnostic report.
The purpose of this challenge is to compare approaches of ophthalmic disease classification in color fundus images. Participant will have to submit classification results of eight categories for all the testing data. For every category, a classification probability (value from 0.0 to 1.0) denotes risk of a patient diagnosed with corresponding category.
该竞赛的目的是比较基于彩色眼底图像进行眼科疾病分类的不同方法。 参与者必须提交所有测试数据集的八个类别的分类结果。 对于每个类别，分类概率（值从0.0到1.0）表示患者被诊断为具有相应类别的可能性/风险。
Note: The main task of the competition is solving the ObtainDiamond environment. In this environment, the agent begins in a random starting location without any items, and is tasked with obtaining a diamond. This task can only be accomplished by navigating the complex item hierarchy of Minecraft.
Note: The goal of the challenge is to set up tasks for evaluating automatic algorithms on signet ring cell detection and colonoscopy tissue screening from digestive system pathological images. This will be the first challenge and first public dataset on signet ring cell detection and colonoscopy tissue screening. Releasing the large quantity of expert-level annotations on digestive-system pathological images will substantially advance the research on automatic pathological object detection and lesion segmentation.
Task 1: Signet ring cell detection.
Task 2: Colonoscopy tissue segmentation and classification.
2019-04-19 至 2020-03-21 // Host by 珠海市横琴新区金融服务中心 // Prize: ￥140万
Requirements Participants should write a report covering quantitative financial strategy theories 1) Model theoretical hypothesis and description of quantitive model 2) Data analysis 3) Strategy back testing results and performance analysis. According to the requirements of the competition, participants’ strategies will be back tested and paper traded during the required period. Evaluation and scoring will base on unified measurements including return, volatility, max drawdown of the strategies and so on. The determination of merits and evaluation of strategy back test and paper trading performance will be made according to market standards, while the robustness and innovation of the strategic logic will also be taken into consideration. Key criteria will include the rationality of the strategy, the creativeness of the model, the market adaptability of the testing strategy and the level of return and risk.
Note: Can you detect fraud from customer transactions?
Note: Outline segmentation masks of objects in images
Note: This year’s Open Images V5 release enabled the second Open Images Challenge to include the following 3 tracks:
Object detection track for detecting bounding boxes around object instances, relaunched from 2018.
Visual relationship detection track for detecting pairs of objects in particular relations, also relaunched from 2018.
Instance segmentation track [Link to be provided when launched on July 1], brand new for 2019.
Note: We are pleased to announce the 2019 Visual Domain Adaptation (VisDA2019) Challenge! It is well known that the success of machine learning methods on visual recognition tasks is highly dependent on access to large labeled datasets. Unfortunately, performance often drops significantly when the model is presented with data from a new deployment domain which it did not see in training, a problem known as dataset shift. The VisDA challenge aims to test domain adaptation methods’ ability to transfer source knowledge and adapt it to novel target domains.
This challenge includes two tracks:
Multi-Source Domain Adaptation Challenge
Semi-Supervised Domain Adaptation
7月1日-10月23日, 2019 // Host by DC 竞赛 // Prize: 100000
Note: 单帧图像超分辨率近年来备受关注。同样的图像，在经过不同超分辨率算法处理后，获得的图像质量也有所不同。在这个挑战中，参赛者需要对100张图片进行4倍超分辨率处理。比赛最终以PI (perceptual index)指标作为评判标准，PI值越小，表明图像质量越高，得分越高，分值高的团队获得优胜。
7月1日-10月23日, 2019 // Host by DC 竞赛 // Prize: 100000
Note: 将超分辨算法用于处理实时视频流时，模型的处理表现与运算性能，是一个两难的选择。为了追求较低复杂度，可能需要牺牲图像质量；为了追求较高质量的输出，导致设备资源占用过高，产生设备发烫、视频模糊卡顿等现象。该挑战主要考察算法模型的性能，参赛者需要对图像做2倍的超分辨率处理，算法复杂度控制在1GFLOPs之内，我们以SRCNN模型为baseline, 并采用PSNR、SSIM及运行时间来综合评估算法的性能，分值高者即获胜。
Note: The Tencent Quantum Lab has recently introduced a new molecular dataset, called Alchemy, to facilitate the development of new machine learning models useful for chemistry and materials science.
The dataset lists 12 quantum mechanical properties of 130,000+ organic molecules comprising up to 12 heavy atoms (C, N, O, S, F and Cl), sampled from the GDBMedChem database. These properties have been calculated using the open-source computational chemistry program Python-based Simulation of Chemistry Framework (PySCF).
Note: Fashion IQ is a new dataset we contribute to the research community to facilitate research on natural language based interactive image retrieval
June 1, 2018 - Dec 13, 2019 // Host by NeurIPS 2019 // Prize: NaN
Note: The competition consists of three different tasks. Contestants are free to submit entries for one, two, or all three tasks. Contestants are allowed to enter up to three models for each task, but will be ranked according to their top entry in each task. Entries can only be trained on the training data for the task they are entered in. No pre-training, or use of auxiliary data is allowed.
ImageNet Classification: The de facto standard dataset for image classification. The dataset is composed of 1,281,167 training images and 50,000 development images. Entries are required to achieve 75% top-1 accuracy on the public test set.
CIFAR-100 Classification: A widely popular image classification dataset of small images. The dataset is composed of 50,000 training images and 10,000 development images. Entries are required to achieve 80% top-1 accuracy on the test set.
WikiText-103 Language Modeling: A language modeling dataset that emphasizes long-term dependencies. Entries will perform the standard language modeling task, predicting the next token from the current one. The dataset is composed of 103 million training words, 217 thousand development words, and 245 thousand testing words. Entries should use the standard word-level vocabulary of 267,735 tokens. Entries are required to achieve a word-level perplexity below 35 on the test set.
2月28-12月28 2019 // Host by 杭州市人民政府 // Prize: TBA
中国移动专题赛: 赛题一：ETC便民服务群体挖掘; 赛题二：企业人才结构变化预测;
行业算法赛: 赛题一：楼盘精准推荐模型; 赛题二：社区独居老人识别与居民用能数据分析; 赛题三：移动办事服务的用户行为预测;
Note: As part of the Eighth Dialog System Technology Challenge (DSTC8), Microsoft Research and Tsinghua University are hosting a track intended to foster progress in two important aspects of dialog systems: dialog complexity and scaling to new domains. For this DSTC8 track, there are two tasks you can compete in (see below). The challenge runs from June 17, 2019 – October 6, 2019.
Participants will build an end-to-end multi-domain dialog system for tourist information desk settings.
Participants will develop fast adaptation methods for building a conversation model that generates appropriate domain-specific user responses to an incomplete dialog history.
Now - October 14, 2019 // Host by Kaggle // Prize: $15,000
Note: Opening the door to a thousand years of Japanese culture
June 5 - Oct 13, 2019 // Host by Grand Challenges // Prize: NaN
Note: As a vision CAI challenge at MICCAI, our aim is to provide a formal framework for evaluating the current state of the art, gather researchers in the field and provide high quality data with protocols for validating endoscopic vision algorithms.
EndoVis 2019 Sub-challenges:
Surgical Workflow and Skill Analysis
Stereo Correspondence and Reconstruction of Endoscopic Data
Note: You are provided with a human musculoskeletal model and a physics-based simulation environment, OpenSim.
There will be three tracks: 1) Best performance, 2) Novel ML solution, and 3) Novel biomechanical solution, where all the winners of each track will be awarded.
Note: Find a graph that has smallest diameter & average shortest path length given an order and a degree.
Graph Golf is an international competition of the order/degree problem since 2015. It is conducted with the goal of making a catalog of smallest-diameter graphs for every order/degree pair. Anyone in the world can take part in the competition by submitting a graph. Outstanding authors are awarded in CANDAR 2019, an international conference held in Nagasaki, Japan, in November 2019.
May 1 - Dec 1, 2019 // Host by NeurIPS 2019 // Prize: ~17,000USD + 2 resea. fellowships up to 12 months + compl. registrations
Note: Predict high resolution traffic flow volume, heading, and speed on a whole city map looking 15 minutes into the future! Kicking off a series of annual competitions, this year’s data is based on 100 billion probe points from 3 cities mapped in 5 minute intervals, showing trends across weekdays and seasonal effects. Improved traffic predictions are of great social, environmental, and economic value, while also advancing our general ability to capture the simple implicit rules underlying a complex system and model its future states.
Jul 31 - Oct 31, 2019 // Host by NeurIPS 2019 // Prize: $10,000USD
Note: A causal understanding of climatic interactions is of high societal relevance from identifying causes of extreme events to process understanding and weather forecasting. This competition comprises a number of multivariate time series datasets featuring major challenges of climate data from time delays and nonlinearity to nonstationarity and selection bias. The competition aims to open up new interdisciplinary research pathways by improving our scientific understanding of Earth’s climate, while also driving method development and benchmarking in the computer science community.
Apr 29 - Oct 31, 2019 // Host by NeurIPS 2019 // Prize: ~$10,000USD
Note: The AutoDL challenge aims taking the automate the design of deep learning (DL) methods to solve generic tasks. This is a challenge with “code submission”: machine learning algorithms are trained and tested on a challenge platform on data invisible to the participants. We target applications such as speech, image, video, and text, for which DL methods have had great success recently, to drive the community to work on automating the design of DL models. Raw data will be provided, formatted in a uniform tensor manner, to encourage participants to submit generic algorithms. We will impose restrictions on training time and resources to push the state-of-the-art further. We will provide a large number of pre-formatted public datasets and set up a repository of data exchange to enable meta-learning.
January - December, 2019 // Host by EvalAI // Prize: NaN
Note: The Animal-AI Olympics is an AI competition with tests inspired by animal cognition. Participants are given a small environment with just seven different classes of objects that can be placed inside. In each test, the agent needs to retrieve the food in the environment, but to do so there are obstacles to overcome, ramps to climb, boxes to push, and areas that must be avoided. The real challenge is that we don’t provide the tests in advance. It’s up to you to play with the environment and build interesting setups that can help create an agent that understands how the environment’s physics work and the affordances that it has. The final submission should be an agent capable of robust food retrieval behaviour similar to that of many kinds of animals. We know the animals can pass these tests, it’s time to see if AI can too. The Animal-AI Olympics is an AI competition with tests inspired by animal cognition. Participants are given a small environment with just seven different classes of objects that can be placed inside. In each test, the agent needs to retrieve the food in the environment, but to do so there are obstacles to overcome, ramps to climb, boxes to push, and areas that must be avoided. The real challenge is that we don’t provide the tests in advance. It’s up to you to play with the environment and build interesting setups that can help create an agent that understands how the environment’s physics work and the affordances that it has. The final submission should be an agent capable of robust food retrieval behaviour similar to that of many kinds of animals. We know the animals can pass these tests, it’s time to see if AI can too.
Nov 1 - Nov 7, 2019 // Host by NeurIPS 2019 // Prize: ~17,500USD
Note: Autonomous cars are expected to dramatically redefine the future of transportation. The 3D Perception system of the autonomous car is a critical keystone upon which high level autonomy functions depend. This competition is designed to help advance the state of the art in 3D object detection by focusing research on this topic in the context of autonomous cars, specifically by sharing the full modality of sensor data available to typical autonomous cars, and by providing access to a high fidelity HD map.
TBA – Nov 8, 2019 // Host by NeurIPS 2019 // Prize: ~15,000USD in Google Cloud Credits
Note: Pommerman: Train a team of communicative agents to play Bomberman in a partially observed setting. Compete against other teams.
April - December 2019 // Host by NeurIPS 2019 // Prize: $10,000+
Note: 基于Unity ML Agents Toolkit的动物认知-AI 挑战
This competition pits our best AI approaches against the animal kingdom to determine if the great successes of AI are now ready to compete with the great successes of evolution at their own game.
Note: The largest dataset in first-person (egocentric) vision; multi-faceted non-scripted recordings in native environments - i.e. the wearers’ homes, capturing all daily activities in the kitchen over multiple days.
April 4, 2018 - Feb. 1, 2020 // Host by Herox // Prize: $250,000
Note: Solvers, whether individuals or teams, will create innovative solutions and methods to produce forecasts to a set of more than 300 questions referred to as Individual Forecasting Problems (IFPs), released regularly over the course of the nine-month Challenge.
Oct 1, 2018 - Dec 11, 2019 // Host by EvalAI // Prize: NaN
Note: In this challenge, we evaluate model performance for three tasks, object detection, semantic segmentation and instance segmentation. You can participate all tasks or any one of them by choosing which results to be included in your submission.
TBA – Dec 11, 2019 // Host by NeurIPS 2019 // Prize: 3 mo. Internship @IBM res. Africa
Note: In the NeurIPS Live Malaria Challenge we are looking for participants to apply machine learning tools to determine novel solutions which could impact malaria policy in Sub Saharan Africa. Specifically, how should combinations of interventions be deployed under budget constraints to impact lives saved and the prevalence of the malaria parasite in a simulated environment.
2018年12月29日 - 2019年12月29日 // Host by Kesci // Prize: NaN
Note: 本练习赛的数据，选自UCI机器学习库中的「银行营销数据集(Bank Marketing Data Set)」
Note: Participants will be tasked to develop an automated method for analyzing histology patches extracted from whole slide images and assign a score reflecting cancer cellularity in each.
Note: This challenge proposes to develop machine learning based approaches so as to predict individuals’ comfort model using several time series of environmental data obtained from sensors in a large building. The objective is to learn a classifier that uses these time series as inputs to predict the associated comfort class computed as an average of the comfort classes of all individuals in the building, assumed to experience the same environmental conditions.
Note: The goal of Posos challenge is to predict for each question the associated intent.
Note: The challenge proposed by Owkin is a weakly-supervised binary classification problem : predict whether a patient has any metastase in its lymph node or not, given its slide.
Note: The goal of the challenge is to predict if a building will have an insurance claim during a certain period. You will have to predict a probability of having at least one claim over the insured period of a building.
Note: The challenge goal is to classify the brain activity state of an animal based on spiking activity patterns of its individual neurons.
Note: The problem is a prediction challenge that aims at helping the Company to build an optimal blend of quantitative strategies, given a set of such strategies.
Note: The goal of the challenge is to predict, based on the analysis of the correlation of a year of consumption and weather training data, the electricity consumption of two given sites for a test year.
Note: In this dataset, we try to predict whether or not a slow oscillation will be followed by another one in sham condition, i.e. without any stimulation.
Note: In order to provide air quality forecasts, Plume Labs has built a unique database with readings collected by monitoring stations all over the world. The problem we submit consists in predicting the PM10 readings of some air quality monitoring stations using the readings provided by the monitoring stations nearby as well as urban features.
Note: This challenge is about forecasting dynamic profiles values from their past values and all the components of Enedis’ Half hourly Electrical Balancing.
Note: The goal is to design an automatic Rubik’s analyzer that estimates the current length of the shortest path to the solution.
Note: The purpose of the challenge is to use a training set of 1 million prices to learn how to price a specific type of instruments described by 23 parameters by nonlinear interpolation on these prices.
Note: The goal of this challenge is to build an image classifier to assist physicians in the screening and diagnosis of esophageal cancer.
Note: The goal of this challenge is to predict the sign of the returns (= price change over some time interval) at the end of about 700 days for about 700 stocks.
March 7, 2019 - March 4, 2020 // Host by ISBI 2019 // Prize: NaN
Note: This will be a 2-year challenge.
We aim to host 3 sub-challenges evaluating our current ability to:
(1) predict unseen signal (signal representation; sub-challenge #1)
(2) estimate microstructural measures (signal modeling; sub-challenge #2)
(3) evaluate sensitivity and specificity of potential biomarkers (biomarker evaluation; sub-challenge #3).
25 APR 2019 - 6 JUN 2019 // Host by CrowdANALYTIX // Prize: $10000
Note: Develop a model to predict, given mortgage application information, whether the mortgage will be funded or not.
To predict whether a mortgage will be funded using only this application data, certain leading factors driving the loan’s ultimate status will be identified. Solvers will discover the specific aspects of the dataset that have the greatest impact, and build a model based on this information.
12 MAY 2019 - 9 JUL 2019 // Host by CrowdANALYTIX // Prize: NaN
Note: Identify the characters from product image from a list of 42 possible values.
While using machine learning to perform image recognition is currently one of the most popular use cases, in some cases, the existing large-scale models are too broad to be effective for specific business use cases. In this contest we will use a data driven approach to identify the “characters” in an image (product images).
March 15 - August 2, 2019 // Host by Grand Challenges // Prize: NaN
Note: The goal of this challenge is to accelerate the development of reliable kidney and kidney tumor semantic segmentation methodologies.
Note: The goal of the challenge is to evaluate new and existing algorithms for automated detection of liver cancer in whole-slide images (WSIs). There are two tasks and therefore two leaderboards for evaluating the performance of the algorithms. Participants can choose to join both or either tasks according to their interests.
Task 1: Liver Cancer Segmentation
Task 2: Viable Tumor Burden Estimation
Now - December 31 2029 // Host by Kaggle // Prize: NaN
Note: Identify the objects in images
Feb 8, 2019 - Apr 26, 2099 // Host by EvalAI // Prize: NaN
Note: Image captioning models have achieved impressive results on datasets containing limited visual concepts and large amounts of paired image-caption training data. However, if these models are to ever function in the wild, a much larger variety of visual concepts must be learned, ideally from less supervision. To encourage the development of image captioning models that can learn visual concepts from alternative data sources, such as object detection datasets, we present the first large-scale benchmark for this task. Dubbed nocaps, for novel object captioning at scale, our benchmark consists of 166,100 human-generated captions describing 15,100 images from the Open Images validation and test sets. The associated training data consists of COCO image-caption pairs, plus Open Images imagelevel labels and object bounding boxes. Since Open Images contains many more classes than COCO, nearly 400 object classes seen in test images have no or very few associated training captions (hence, nocaps). We extend existing novel object captioning models to establish strong baselines for this benchmark and provide analysis to guide future work on this task.
Note: The nuScenes dataset is a large-scale autonomous driving dataset.
No deadline // Host by Kaggle // Prize: NaN
Note: Final project for “How to win a data science competition” Coursera course
Nov. 23, 2016 - Never // Host by CodaLab // Prize: NaN
July 20, 2019 - Never // Host by CodaLab // Prize: NaN
Note: Unlike other QA datasets like SQuAD in which the answers are extractive, we allow the answers to be abstractive. The task requires model to read a short tweet and a question and outputs a text phrase (does not need to be in the tweet) as the answer.
July 1 - Never // Host by CodaLab // Prize: NaN
Note: Given two corpora Ca and Cb, rank all target words according to their degree of lexical semantic change between Ca and Cb as annotated by human judges. (Higher rank means higher change.)
Note: YouCook2 is the largest task-oriented, instructional video dataset in the vision community. It contains 2000 long untrimmed videos from 89 cooking recipes; on average, each distinct recipe has 22 videos. The procedure steps for each video are annotated with temporal boundaries and described by imperative English sentences (see the example below).
Note: The challenges associated with the dataset are the Semantic Segmentation challenge and the Yield Estimation challenge. In the Semantic Segmentation challenge, participants must perform pixel-wise classifiction on a subset of the labelled images. In the Yield Estimation challenge, participants must estimate the oil radish yield of same subset of labelled images.
Note: Challenge participants need to develop driving models that can drive most similar to the human driver that recorded the dataset.
May. 17, 2019 - Never // Host by CodaLab // Prize: NaN
Note: This is an EE331 competition leaderboard for Mobile age group classification. It consists of 157K datasamples with 85 various features and age group label (ranging from 1 to 6). The data is splitted into train : validation : test sset with 70 : 20 : 10 ratio.
May. 17, 2019 - Never // Host by CodaLab // Prize: NaN
Note: Perfect Pitching Simulator!
Note: ActivityNet-Entities, is based on the video description dataset ActivityNet Captions and augments it with 158k bounding box annotations, each grounding a noun phrase (NP). Here we release the complete set of NP-based annotations as well as the pre-processed object-based annotations.
please see our dataset repo, code repo, and CVPR 2019 oral paper.
May 6, 2019 - Never // Host by CodaLab // Prize: NaN
Note: YouCook2 is currently suitable for video-language research, weakly-supervised activity and object recognition in video, common object and action discovery across videos and procedure learning.
Dec. 1, 2018 - Never // Host by CodaLab // Prize: NaN
Note: The challenge consists in building an AI agent that can play efficiently and win simplified text-based games using TextWorld.
Note: This portal is only used for models that used ‘ts’ (timestamp annotations)
TVQA is a large-scale video QA dataset based on 6 popular TV shows (Friends, The Big Bang Theory, How I Met Your Mother, House M.D., Grey’s Anatomy, Castle).
Note: The shared task on DRS parsing will be co-located with IWCS-2019 held in Gothenburg, Sweden on 23-27 May.
Frame semantics and semantic parsing:
Task 1: Cross-lingual Semantic Parsing with UCCA
Task 2: Unsupervised Lexical Semantic Frame Induction
Opinion, emotion and abusive language detection
Task 3: EmoContext: Contextual Emotion Detection in Text
Task 4: Hyperpartisan News Detection
Task 5: HatEval: Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter
Task 6: OffensEval: Identifying and Categorizing Offensive Language in Social Media<\a>
Fact vs fiction
Task 7: RumourEval 2019: Determining Rumour Veracity and Support for Rumours
Task 8: Fact Checking in Community Question Answering Forums
Information extraction and question answering
Task 9: Suggestion Mining from Online Reviews and Forums
Task 10: Math Question Answering
NLP for scientific applications
Task 12: Toponym Resolution in Scientific Papers
Aug. 18, 2018 - Never // Host by CodaLab // Prize: NaN
Note: You can get all the information and data at https://pilehvar.github.io/wic
Note: “We introduce a new video dataset and benchmark to assess single-object tracking algorithms.”
June 27, 2019 - Never // Host by Unearthed // Prize: NaN
Note: This global online competition invites innovators from around the world to build an algorithm that can determine and map the spatial extents of the core tray and then the individual rows contained within.
June 27, 2019 - Never // Host by Unearthed // Prize: NaN
Note: This is an online competition inviting companies and individuals from around the world to provide a solution that can correctly identify recorded depths within a core photograph.
June 27, 2019 - Never // Host by Unearthed // Prize: NaN
Note: This global online competition invites data scientists and innovators from around the world to develop a prediction model for tailings density (and therefore water consumption) in Newcrest’s gold processing operations.
under construction // Host by Grand Challenges // Prize: NaN
Note: Dataset contains manual annotations as a ground truth data.
No deadline // Host by Grand Challenges // Prize: NaN
Note: The DRIVE database has been established to enable comparative studies on segmentation of blood vessels in retinal images. Develop a system to automatically segment vessels in human retina fundus images.
No deadline // Host by Grand Challenges // Prize: NaN
Note: The PatchCamelyon benchmark is a new and challenging image classification dataset. It consists of 327.680 color images (96 x 96px) extracted from histopathologic scans of lymph node sections. Each image is annoted with a binary label indicating presence of metastatic tissue. PCam provides a new benchmark for machine learning models: bigger than CIFAR10, smaller than imagenet, trainable on a single GPU.
May 16 - TBA // Host by Grand Challenges // Prize: NaN
Note: Spine or vertebral segmentation is a crucial step in all applications regarding automated quantification of spinal morphology and pathology. With the advent of deep learning, for such a task on computed tomography (CT) scans, a big and varied data is a primary sought-after resource.
Task 1: Vertebra Labelling
Task 2: Vertebra Segmentation
Mar 13, 2018 - Dec 31, 2099 // Host by EvalAI // Prize: NaN
Note: The challenge requires an autonomous agent to follow a natural language navigation instruction to navigate to a goal location in a previously unseen real-world building.
Jun 20, 2018 - Jun 22, 2100 // Host by EvalAI // Prize: NaN
Note: Our proposed challenge addresses the following two tasks for this dataset: (1) predict the answer to a visual question and (2) predict whether a visual question cannot be answered.
No deadline // Host by Stanford NLP Group // Prize: NaN
Note: Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage, or the question might be unanswerable.
No deadline // Host by Stanford NLP Group // Prize: NaN
Note: CoQA is a large-scale dataset for building Conversational Question Answering systems. The goal of the CoQA challenge is to measure the ability of machines to understand a text passage and answer a series of interconnected questions that appear in a conversation. CoQA is pronounced as coca.
No deadline // Host by Google AI // Prize: NaN
Note: A community-based challenge to incentivize and measure progress towards the goal of zero confident classification errors in machine learning models.
(不受限对抗样本挑战) The project on Github
No deadline // Host by salesforce // Prize: NaN
Note: The Natural Language Decathlon is a multitask challenge that spans ten tasks: question answering (SQuAD), machine translation (IWSLT), summarization (CNN/DM), natural language inference (MNLI), sentiment analysis (SST), semantic role labeling(QA‑SRL), zero-shot relation extraction (QA‑ZRE), goal-oriented dialogue (WOZ), semantic parsing (WikiSQL), and commonsense reasoning (MWSC).