9

CVPR 2020 算法竞赛大盘点

 4 years ago
source link: http://mp.weixin.qq.com/s?__biz=MzIwMTE1NjQxMQ%3D%3D&%3Bmid=2247490624&%3Bidx=1&%3Bsn=417c40ff6dc4784b45ce9c4ff3a7ba09
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.

点击 我爱计算机视觉 标星,更快获取CVML新技术

UNZ7j2z.jpg!web

CVPR 2020 已经公布了大多数workshop的细节,与这些workshop对应的还有很多计算机视觉算法比赛,这些比赛代表着或新兴、或实用、或有趣、或被忽略的研究方向。

CV君今天汇总了大部分比赛(因有些还未公布网址),大多数已经开赛放出了数据集,欢迎大家按图索骥。

WebVision Image Classification

技术方向:图像分类、半监督学习、无监督学习

http://www.vision.ee.ethz.ch/webvision/challenge.html

ps.做好了能改变整个CV业界的方向。

Challenges for Computer Vision in Agriculture

技术方向:语义分割、航拍图像处理识别

https://www.agriculture-vision.com/prize-challenge

Thermal Image Super-Resolution Challenge

技术方向:超分辨率、热像仪图像处理

http://vcipl-okstate.org/pbvs/20/challenge.html

Low-rate and P-frame compression challenges

技术方向:图像视频压缩

http://challenge.compression.cc/motivation/

Diagram Image Retrieval and Analysis (DIRA) Challenge

技术方向:图表检索与分析

http://cvpr-dira.lipingyang.org/challenge/

ps.第一个这方向的工作。

Low-Power Computer Vision Competition

技术方向:低功耗计算机视觉、目标检测、图像分类

http://www.lpcv.ai/

Emotionet Challenge

技术方向:表情识别、人脸动作单元识别

http://cbcsl.ece.ohio-state.edu/enc-2020/index.html

Image Matching: Local Features and Beyond

技术方向:局部特征提取、含噪数据拟合

https://image-matching-workshop.github.io/

ps.深度学习时代,难得还有这么传统的方向。

New Trends in Image Restoration and Enhancement Challenges (NTIRE)

技术方向:图像超分辨率、图像去噪、去模糊、去摩尔纹、重建、去雾

http://www.vision.ee.ethz.ch/ntire20/

UG2+ Prize Challenge

技术方向:低质图像增强、图像恢复、目标检测、人脸验证

http://cvpr2020.ug2challenge.org/

ISIC Skin Image Analysis Workshop

技术方向:皮肤图像分析、图像分割、图像分类

https://workshop2020.isic-archive.com/

Weakly Supervised Learning Challenges

技术方向:弱监督学习、图像分割、场景解析、目标定位

https://lidchallenge.github.io/challenge.html

6th SpaceNet Challenge

技术方向:遥感图像处理识别、图像分割

https://www.grss-ieee.org/earthvision2020/challenge.html

MOTChallenge

技术方向:目标跟踪与分割

https://motchallenge.net/workshops/bmtt2020/tracking.html

DAVIS Video Object Segmentation

技术方向:视频目标分割

https://davischallenge.org/challenge2020/index.html

Anti-UAV Challenge

技术方向:反无人机、无人机检测与跟踪

https://anti-uav.github.io/

AI City Challenge

技术方向:智能交通、车辆检测、卡口车辆计数、重识别、车辆跟踪、交通异常检测

https://www.aicitychallenge.org/2020-challenge-tracks/

VizWiz Grand Challenge

技术方向:图像表述

https://vizwiz.org/tasks-and-datasets/image-captioning/

VQA and Dialog Challenges

技术方向:视觉问答与对话

https://visualqa.org/workshop

Continual Learning Challenge

技术方向:持续学习

https://sites.google.com/view/clvision2020/challenge

Cross-Domain Few-Shot Learning (CD-FSL) Challenge

技术方向:跨域少样本学习

https://www.learning-with-limited-labels.com/challenge

DeepFashion2 and FashionIQ Challenges

技术方向:服饰检索

https://sites.google.com/view/cvcreative2020#h.p_Qypem5p_Nm6c

The Seventh Workshop on Fine-Grained Visual Categorization

技术方向:细粒度视觉分类

https://sites.google.com/view/fgvc7

ActivityNet Challenge

技术方向:活动识别

http://activity-net.org/challenges/2020/

Challenge on Remote Physiological Signal Sensing

技术方向:基于人脸视频的心率识别

https://competitions.codalab.org/competitions/22287

Localization, Odometry, SLAM Challenge

技术方向:SLAM

https://sites.google.com/view/vislocslamcvpr2020/home

2nd ScanNet Indoor Scene Understanding Challenge

技术方向:2D/3D图像分割、实例分割

http://www.scan-net.org/cvpr2020workshop/

未完待续,欢迎持续关注公众号后续文章。

CV细分方向交流群

52CV已经建立多个CV专业交流群,包括:目标跟踪、 目标检测、语义分割、姿态估计、人脸识别检测、医学影像处理、超分辨率、神经架构搜索、GAN、强化学习等,扫码添加CV君拉你入群,如已经为CV君其他账号好友请直接私信,

请务必注明相关方向,比如: 目标检测

jauQfyb.jpg!web

喜欢在QQ交流的童鞋,可以加52CV官方 QQ群805388940

(不会时时在线,如果没能及时通过验证还请见谅)

UbiEbaU.png!web

长按关注 我爱计算机视觉


About Joyk


Aggregate valuable and interesting links.
Joyk means Joy of geeK