摩拜单车自推出以来,深受用户喜爱,在很多城市已经成为除公共交通以外的居民首选的 出行方式,大大减轻了城市路网压力和拥堵情况。随着绿色出行和环保观念的深入人心, 将会有更多的用户选择摩拜单车,进一步实现让自行车回归城市的目标。同时,摩拜致力 于应用前沿科技的帮助人们更好地出行,利用机器学习去预测用户的出行目的地便是众多 应用场景中重要的一个。
目前,摩拜单车在北京的单车投放量已经超过40万。用户可以直接在人行道上找到停放的单车,用手机解锁,然后骑到目的地后再把单车停好并锁上。因此,为了更好地调配和管理这40万辆单车,需要准确地预测每个用户的骑行目的地。
自然语言理解是人工智能的重大难题之一,也是目前智能语音交互和人机对话的核心挑战。
在自然语言理解中,自然语言推理(Nature Language Inference,NLI)被认为是一个非常基础但重要的研究任务。它要求机器去理解自然语言的深层次语义信息,进而做出合理的推理。更具体的推理任务,则是判断句子关系,即对于给定的两个句子,判断它们含义是否一致。
NLI任务作为一种分类任务,可以帮助评价机器的自然语言理解能力。如果一个模型在NLI任务上有良好表现,则可以认为该模型具备一定的自然语言理解能力。
当前,NLI领域虽然发展迅猛,但仍有诸多难点和挑战,比如如何将常识知识融入机器推理模型中、如何更准确地理解语义等等。
在上述背景之下,搜狐发起并主办 “2021搜狐校园算法大赛”,有针对性地设置30万条数据,总奖金池6.5万元。旨在通过提供业务场景、真实数据、专家指导,选拔和培养有志于自然语言处理领域的算法研究、应用探索的青年才俊,共同探索更多可能、开启无限未来。
在太平洋西侧,每年夏季会陆续生成一系列热带风暴,其中有些发展成为台风乃至于超级台风,一边旋转一边向亚洲东海岸移动。台风往往在东南亚国家、中国、日本、以及朝鲜半岛登陆,带来狂风暴雨,造成巨大的财产损失,时有人员伤亡。如果能够提早一两天预测到台风的发展强度、行进轨迹、乃至于降水在各地的实时详细分布,就有可能为各国人民提供宝贵预警时间,多做防灾减灾工作。
赛题由马里兰大学博士宋宽构思设计,原始数据来源于日本气象厅葵花 8 号卫星的公开数据记录,由日本千叶大学进行第一轮数据处理,由宋宽博士进行第二轮数据处理。
比赛以算法交流为出发点,尝试深度学习在气象卫星图像领域的应用,希望通过社区的力量为台风预警与防灾探索可能的方向。欢迎各界共同参与讨论,如有意向开展关于赛题相关领域的交流、研讨、合作,或者关于杭州云栖Hackathon现场想法等等,可联系钉钉群主或邮件 jingyi.hjy@alibaba-inc.com。
Upgrades in consumption patterns mean that there is significant room for potential growth in the fashion industry. According to official statistics from different countries, the market value of the global apparel market is worth over USD 3 trillion. Although artificial intelligence (AI) technology has been evolving along with the fashion industry, there are still different challenges in different areas that need to be addressed.
To promote the development of the fashion industry, the Vision & Beauty Team of the Alibaba Group and the Institute of Textile and Clothing of The Hong Kong Polytechnic University are pleased to jointly launch a revolutionary dataset which integrates both professional fashion knowledge and machine learning formulation.
This challenge is focusing on one part of the dataset: keypoints detection of apparel. The analysis of apparel with computers could be easily affected by the dimension and shape of the apparel, distance and angle of shooting, or even how the apparel is displayed or the model is posing. Contestants are required to detect keypoints of apparel images. This task can help to improve the performance of applications such as alignment, recognition of the local attributes and auto-editing of the images of apparel.
Upgrades in consumption patterns mean that there is significant room for potential growth in the fashion industry. According to official statistics from different countries, the market value of the global apparel market is worth over USD 3 trillion. Although artificial intelligence (AI) technology has been evolving along with the fashion industry, there are still different challenges in different areas that need to be addressed.
To promote the development of the fashion industry, the Vision & Beauty Team of the Alibaba Group and the Institute of Textile and Clothing of The Hong Kong Polytechnic University are pleased to jointly launch a revolutionary dataset which integrates both professional fashion knowledge and machine learning formulation.
This challenge is focusing on one part of the dataset: attributes recognition of apparel. Apparel attributes are the basic knowledge of fashion field, which are large and complex. We constructed a hierarchical attributes tree as a structured classification target, to describe the cognitive process of apparel. Contestants are invited to design algorithms to recognize attributes of apparel images. This task might be widely applied for apparel image searching, navigating tagging, mix-and-match recommendation, etc.