ABSTRACT
Recognizing visual contents in unconstrained videos has become a very important problem for many applications, such as Web video search and recommendation, smart advertising, robotics, etc. This workshop and challenge aims at exploring new challenges and approaches for large-scale video classification with large number of classes from open source videos in a realistic setting, based upon an extension of Fudan-Columbia Video Dataset (FCVID). This newly collected dataset contains over 8000 hours of video data from YouTube and Flicker, annotated into 500 categories. We hope this dataset can stimulate innovative research on this challenging and important problem.
Recommendations
Student Class Behavior Dataset: a video dataset for recognizing, detecting, and captioning students’ behaviors in classroom scenes
AbstractThe massive increase in classroom video data enables the possibility of utilizing artificial intelligence technology to automatically recognize, detect and caption students’ behaviors. This is beneficial for related research, e.g., pedagogy and ...
Slovo: Russian Sign Language Dataset
Computer Vision SystemsAbstractOne of the main challenges of the sign language recognition task is the difficulty of collecting a suitable dataset due to the gap between hard-of-hearing and hearing societies. In addition, the sign language in each country differs significantly, ...
Challenges Track Chairs' Welcome
WWW '18: Companion Proceedings of the The Web Conference 2018It is our great pleasure to welcome you to the WWW 2018 Challenges Track. It is the first time that the WWW conference includes such a track, which aim was to showcase the maturity of the state of the art on tasks common to the Web community and ...
Comments