上學時,我們中的一部分人經常參加一些程序設計競賽,例如:Astar, Topcoder, Google Code Jam, ACM/ICPC等,在這些競賽中,號稱中國大學生編程第一人的姚班樓教主脫穎而出。本文整理了一些AI相關的挑戰賽(有些雖已停辦,但具有參考價值),希望你成為下一個AI教主。
1 Computer Vision Challenge
1.1 Pascal VOC(Visual Object Classes)
Desc: Supervised-learning tasks, such as image classification.Performance on VOC has been saturation. Replaced by ImageNet. From 2005-2012, now finished.
URL: http://host.robots.ox.ac.uk/pascal/VOC/
1.2 CVPR ImageNet ILSVRC(Large Scale Visual Recognition Challenge)
Desc: Supervised-learning tasks, such as image classification. Performance on ImageNet has been saturation(2.2%). Replaced by WebVision. From 2010-2017, now finished.
URL: http://www.image-net.org/challenges/LSVRC/
1.3 CVPR WebVision
Desc: Weakly-supervised learning tasks. Web images from real-world scenarios. From 2017-now.
URL: http://www.vision.ee.ethz.ch/webvision/
1.4 ICCV MS COCO(Common Objects in Context)
Desc: Supervised-learning tasks, such as detection, instances segmentation, keypoint, stuff segmentation. From 2015-now.
URL: http://cocodataset.org/
1.5 ICCV MIT Places
Desc: Scene-centric supervised-learning tasks, such as scene parsing, instance segmentation, semantic boundary detection. From 2017-now.
URL: http://places.csail.mit.edu/
1.6 ACM Multimedia LSVC(Large-Scale Video Classification)
Desc: video classification.
URL: http://www.acmmm.org/2017/
1.7 CVPR LSUN(Large-scale Scene Understanding)
Desc: Scene-centric tasks, such as scene understanding, including scene object retrieval, outdoor scene segmentation, RGB-D 3D object detection and saliency prediction. From 2015-now.
URL: http://lsun.cs.princeton.edu/2017/
2 Speech Challenge
2.1 Blizzard Challenge
Desc: The basic challenge is to take the released speech database, build a synthetic voice from the data and synthesize a prescribed set of test sentences. From 2005-now.
URL: http://www.festvox.org/blizzard/
2.2 CHiME Challenge
Desc: The new challenge will consider the problem of distant microphone conversational speech recognition in everyday home environments. The challenge will target multi-microphone solutions with separate tracks for fixed microphone arrays and head-mounted microphones. From 2014-now.
URL: http://spandh.dcs.shef.ac.uk/chime_workshop/
2.3 NIST TAC KBP(Text Analysis Conference Knowledge Base Population)
Desc: The goal of TAC Knowledge Base Population (KBP) is to develop and evaluate technologies for populating knowledge bases (KBs) from unstructured text. From 2009-now.
URL: https://tac.nist.gov/2017/KBP/
2.4 Winograd Schema Challenge
Desc: An alternative to the Turing Test developed by Hector Levesque. From 2016-now.
URL: http://commonsensereasoning.org/winograd.html
2.5 NIST SRE(Speaker Recognition Evaluation)
Desc: The goal of the NIST SRE series is to contribute to the direction of research efforts and the calibration of technical capabilities of text independent speaker recognition. From 1996-now.
URL: https://www.nist.gov/itl/iad/mig/speaker-recognition
2.6 ACM Multimedia AVEC(Audio/Visual Emotion Challenge)
Desc: Audio/Visual Emotion Challenge. From 2011-now.
URL: https://dblp.uni-trier.de/db/conf/mm/mm2017.html
http://www.acmmm.org/2017/
2.7 ACM ICMI EmotiW
Desc: Consists of three sub-challenges: Engagement in the Wild, Group-based Emotion Recognition, Audio-video Emotion Recognition. From 2013-now.
URL:
https://icmi.acm.org/2018/index.php?id=challenges
http://vintage.winklerbros.net/resources.html
2.8 MEC(Multimodal Emotion Recognition Challenge)
Desc: The goal of the Challenge is to provide a common benchmark data set and to bring together the audio and video emotion recognition communities, and to promote the research in multimodal emotion recognition. From 2016-now.
URL: http://www.chineseldc.org/htdocsen/emotion.html
3 Computational Linguistics Challenge
3.1 WMT(Machine Translation)
Desc: Statistical Machine Translation. From 2005-now.
URL:
http://www.statmt.org/wmt18/index.html
http://www.statmt.org/
3.2 VCC(Voice Conversion Challenge)
Desc: The objective is speaker conversion, which is a well-known basic problem in voice conversion. Hub task and spoke task. From 2016-now.
URL: http://www.vc-challenge.org/
3.3 CGED(Chinese Grammatical Error Diagnosis)
Desc: The goal of CGED shared task is to develop NLP techniques to automatically diagnose grammatical errors in Chinese sentences written by L2 learners. From 2014-now.
URL: http://cged.biz/
3.4 IWSLT(International Workshop on Spoken Language Translation)
Desc: A yearly scientific workshop, associated with an open evaluation campaign on spoken language translation, where both scientific papers and system descriptions are presented. From 2004-now.
URL:
https://workshop2018.iwslt.org/
http://www.iwslt.org/
3.5 AI Challenger
Desc: 國內幾家公司主辦的,任務有:觀點型問題閱讀理解,細粒度用戶評論情感分析,英中文本機器翻譯,短視頻實時分類,無人駕駛視覺感知。From 2017-now.
URL: https://challenger.ai/
閱讀更多 深度學習社區 的文章