Time: Thursday 3:30-5:30pm.

Place: DBH3013

At least one week prior to your presentation, please fill out the papers/topics that you plan to present at the meeting.

Topic: Facial expression analysis and affective computing

Abstract: Automatic analysis of facial expression in a realistic scenario is a difficult problem due to that the 2-D imagery of human facial expression consists of rigid head motion and non-rigid muscle motion. We are tasked to solve this “coupled-motion” problem and analyze facial expression in a meaningful manner. We first proposed an image-based representation, Emotion Avatar Image, to help person-independent expression recognition. This method allows us to analyze facial expression in a canonical space, which makes the comparison of corresponding features more accurate and reasonable. Second, an real-time registration technique is designed to improve frame-based streaming facial action unit (AU) recognition. We do not always have the luxury of obtaining the temporal segmented discrete facial expressions, e.g., joy or surprise. The project introduces a frame-based method for registration. It not only aligns faces (or objects in general) to a reference, but also guarantees temporal smoothness, both of which are essential for spontaneous expression analysis. Third, the proposed accurate expression recognition techniques are then applied to the field of advertising, where facial expression is demonstrated to be closely correlated with the commercial viewing behavior of audiences.

Paper: Task-driven dictionary learning

Abstract: Modeling data with linear combinations of a few elements from a learned dictionary has been the focus of much recent research in machine learning, neuroscience, and signal processing. For signals such as natural images that admit such sparse representations, it is now well established that these models are well suited to restoration tasks. In this context, learning the dictionary amounts to solving a large-scale matrix factorization problem, which can be done efficiently with classical optimization tools. The same approach has also been used for learning features from data for other purposes, e.g., image classification, but tuning the dictionary in a supervised way for these tasks has proven to be more difficult. In this paper, we present a general formulation for supervised dictionary learning adapted to a wide variety of tasks, and present an efficient algorithm for solving the corresponding optimization problem. Experiments on handwritten digit classification, digital art identification, nonlinear inverse image problems, and compressed sensing demonstrate that our approach is effective in large-scale settings, and is well suited to supervised and semi-supervised classification, as well as regression tasks for data that admit sparse representations.

http://arxiv.org/pdf/1009.5358 Slides: task-driven_dictionary_learning.pdf

Paper: NYC3DCars: A Dataset of 3D Vehicles in Geographic Context

Abstract: Geometry and geography can play an important role in recognition tasks in computer vision. To aid in studying connections between geometry and recognition, we introduce NYC3DCars, a rich dataset for vehicle detection in urban scenes built from Internet photos drawn from the wild, focused on densely trafficked areas of New York City. Our dataset is augmented with detailed geometric and geographic information, including full camera poses derived from structure from motion, 3D vehicle annotations, and geographic information from open resources, including road segmentations and directions of travel. NYC3DCars can be used to study new questions about using geometric information in detection tasks, and to explore applications of Internet photos in understanding cities. To demonstrate the utility of our data, we evaluate the use of the geographic information in our dataset to enhance a parts-based detection method, and suggest other avenues for future exploration.

nyc3d.cs.cornell.edu/static/paper.pdf

Papers:

Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
Jonathan Tompson, Arjun Jain, Yann LeCun, Christoph Bregler
http://arxiv.org/abs/1406.2984

1. Deformable Part Models are Convolutional Neural Networks
   Ross Girshick, Forrest Iandola, Trevor Darrell, Jitendra Malik
   http://arxiv.org/abs/1409.5403

Paper:

Paper:

Paper:

Paper:

Paper:

Paper: