In this paper we propose an approach for articulated tracking of multiple people in
unconstrained videos. Our starting point is a model that resembles existing architectures for …

Estimating human pose from videos and image sequences is not only an important
computer vision problem, but also plays very critical role in many real-world applications …

Given ubiquitous graph data such as the Web and social networks, proximity search on
graphs has been an active research topic. The task boils down to measuring the proximity …

In this work, we study a poorly understood trade-off between accuracy and runtime costs for
deep semantic video segmentation. While recent work has demonstrated advantages of …

We address the problem of integrating object reasoning with supervoxel labeling in
multiclass semantic video segmentation. To this end, we first propose an object-augmented …

Predictive algorithms are a critical part of the ubiquitous computing vision, enabling
appropriate action on behalf of users. A common class of algorithms, which has seen uptake …

Current approaches for activity recognition often ignore constraints on computational
resources:(1) they rely on extensive feature computation to obtain rich descriptors on all …

We propose to tackle the cost-sensitive learning problem, where each feature is associated
to a particular acquisition cost. We propose a new model with the following key properties:(i) …

Recent advances in recurrent neural nets (RNNs) have shown much promise in many
applications in natural language processing. For most of these tasks, such as sentiment …

We propose a reinforcement learning based approach to tackle the cost-sensitive learning
problem where each input feature has a specific cost. The acquisition process is handled …