No abstract

Indoor scene recognition is a challenging open problem in high level vision. Most scene recognition models that work well for outdoor scenes perform poorly in the indoor domain. The main difficulty is that while some indoor scenes (e.g. corridors) can be well characterized by global spatial properties, others (e.g, bookstores) are better characterized by the objects they contain. More generally, to address the indoor scenes recognition problem we need a model that can exploit local and global discriminative information. In this paper we propose a prototype based model that can successfully combine both sources of information. To test our approach we created a dataset of 67 indoor scenes categories (the largest available) covering a wide range of domains. The results show that our approach can significantly outperform a state of the art classifier for the task.

Many problems in vision involve the prediction of a class label for each frame in an unsegmented sequence. In this paper we develop a discriminative framework for simultaneous sequence segmentation and labeling which can capture both intrinsic and extrinsic class dynamics. Our approach incorporates hidden state variables which model the sub-structure of a class sequence and learn the dynamics between class labels. Each class label has a disjoint set of associated hidden states, which enables efficient training and inference in our model. We evaluated our method on the task of recognizing human gestures from unsegmented video streams and performed experiments on three different datasets of head and eye gestures. Our results demonstrate that our model for visual gesture recognition outperform models based on Support Vector Machines, Hidden Markov Models, and Conditional Random Fields.

In recent years the l 1,∞ norm has been proposed for joint regularization. In essence, this type of regularization aims at extending the l 1 framework for learning sparse models to a setting where the goal is to learn a set of jointly sparse models. In this paper we derive a simple and effective projected gradient method for optimization of l 1,∞ regularized problems. The main challenge in developing such a method resides on being able to compute efficient projections to the l 1,∞ ball. We present an algorithm that works in O(n log n) time and O(n) memory where n is the number of parameters. We test our algorithm in a multi-task image annotation problem. Our results show that l 1,∞ leads to better performance than both l 2 and l 1 regularization and that it is is effective in discovering jointly sparse solutions.