Speaker: Manik Varma Title: Extreme Classification: A New Paradigm for Ranking & Recommendation The objective in extreme multi-label classification is to learn a classifier that can automatically tag a Speaker: Jason Weston Title: Hashtags, Clicks and Likes: Supervision for Content-based Posts We study the problem of understanding the content of short textual posts and images popular in social networks. There are an abundance of weakly supervised signals for such a goal, including hashtags provided by the users themselves, as well as various kinds of click, comment and like interactions. We show how employing word embedding and image embedding convolutional neural network models can effectively utilize this supervision. This is joint work with Keith Adams, Lubomir Bourdev, Sumit Chopra, Misha Denil, Emily Denton, Rob Fergus, Manohar Paluri, Marc-Aurelio Ranzato, Ledell Wu and Ming Yang. Speaker: John Langford Title: The Elusive Theory of Efficient Classification What is known about the theory of efficient classification? How far does the theory take us? And why doesn't it take us all the way? I'll discuss the key results and open questions I see for extreme multiclass classification. Speaker: Jia Deng Title: Knowledge-Driven Recognition of Objects and Actions A fundamental challenge in visual recognition is generalizing to new concepts. As we expand the label space from basic object categories to fine-grained classes and to compositions of visual entities (i.e. actions), most of the visual concepts will be in the long tail, i.e., most will have very few or even zero training examples. It is thus critical to leverage semantic knowledge, facts about how concepts are related, to enable generalization from common concepts to rare ones. In this talk I will discuss some recent work in this direction. I will first present a new visual classification model that incorporates pre-defined semantic relations between labels, namely hierarchy and exclusion. Then I will show how to jointly learn the visual classification model and the semantic relations in the context of action recognition. |