Select a calendar:
Filter November Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for November 19, 2013
-
PhD Defense - Derya Ozkan
Tue, Nov 19, 2013 @ 01:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title: Towards Intelligent Virtual Listeners: Computational Models of Social Nonverbal Behaviors
PhD Candidate: Derya Ozkan
Committee:
Louis-Philippe Morency (Chair)
Gerard Medioni
Jonathan Gratch
Stacy Marsella
Shrikanth Narayanan (outside member)
Human nonverbal communication is a highly interactive process, in which the participants dynamically send and respond to nonverbal signals. These signals play a significant role in determining the nature of a social exchange. Although human can naturally recognize, interpret and produce these nonverbal signals in social context, computers are not equipped with such abilities. Therefore, creating computational models for holding fluid interactions with human participants has become an important topic for many research fields including human-computer interaction, robotics, artificial intelligence, and cognitive sciences. Central to the problem of modeling social behaviors is the challenge of understanding the dynamics involved with listener backchannel feedbacks (i.e. the nods and paraverbals such as ``uh-hu'' and ``mm-hmm'' that listeners produce as someone is speaking).
In this thesis, I present a framework for modeling visual backchannels of a listener during a dyadic conversation. I address the four major challenges involved in modeling nonverbal human behaviors, more specifically listener backchannels: (1) high dimensional data, (2) multimodal processing, (3) mutual influence between the participants, and (4) variability in human's behaviors. We address the first challenge by proposing a sparse feature selection method that gives researchers a new tool to analyze human nonverbal communication. To address to second challenge of effective and efficient fusion of multimodal information, we introduce a new model called Latent Mixture of Discriminative Experts (LMDE) that can automatically learn the hidden dynamic between modalities. For the third challenge, we present a context-based prediction framework that models the mutual influence between the participants of a human conversation to improve the final prediction model. Finally, we propose a new approach for modeling wisdom of crowds called wisdom-LMDE, which is able to learn the variations and commonalities among different crowd members.
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
PhD Student Colloquium
Tue, Nov 19, 2013 @ 03:30 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Presenters / Abstracts In Announcement Body, USC
Talk Title: PhD Student Colloquium
Series: CS Colloquium
Abstract: Soravit Changpinyo and Kuan Liu
Title: Similarity Component Analysis
Abstract: Measuring similarity is crucial to many learning tasks. To this end, metric learning has been the dominant paradigm. However, similarity is a richer and broader notion than what metrics entail. For example, similarity can arise from the process of aggregating the decisions of multiple latent components, where each latent component compares data in its own way by focusing on a different subset of features. We propose Similarity Component Analysis (SCA), a probabilistic graphical model that discovers those latent components from data. In SCA, a latent component generates a local similarity value, computed with its own metric, independently of other components. The final similarity measure is then obtained by combining the local similarity values with a (noisy-) OR gate. We derive an EM-based algorithm for fitting the model parameters with similarity-annotated data from pairwise comparisons. We validate the SCA model on synthetic datasets where SCA discovers the ground-truth about the latent components. We also apply SCA to a multiway classification task and a link prediction task. For both tasks, SCA attains significantly better prediction accuracies than competing methods. Moreover, we show how SCA can be instrumental in exploratory analysis of data, where we gain insights about the data by examining patterns hidden in its latent components’ local similarity values.
Boqing Gong
Title: Reshaping Visual Datasets for Domain Adaptation
Abstract: In visual recognition problems, the common data distribution mismatches between training and testing make domain adaptation essential. However, image data is difficult to manually divide into the discrete domains required by adaptation algorithms, and the standard practice of equating datasets with domains is a weak proxy for all the real conditions that alter the statistics in complex ways (lighting, pose, background, resolution, etc.) We propose an approach to automatically discover latent domains in image or video datasets. Our formulation imposes two key properties on domains: maximum distinctiveness and maximum learnability. By maximum distinctiveness, we require the underlying distributions of the identified domains to be different from each other to the maximum extent; by maximum learnability, we ensure that a strong discriminative model can be learned from the domain. We devise a nonparametric formulation and efficient optimization procedure that can successfully discover domains among both training and test data. We extensively evaluate our approach on object recognition and human activity recognition tasks.
Mrinal Kalakrishnan
Title: Learning Objective Functions for Autonomous Locomotion and Manipulation
Abstract: Efforts on learning from demonstration in robotics have largely been focused on reproducing behavior similar in appearance to the provided demonstrations, loosely classified as Direct Policy Learning. An alternative approach, known as Inverse Reinforcement Learning (IRL), is to learn the objective function that the demonstrations are assumed to be optimal under. With the help of a planner or trajectory optimizer, such an approach allows the system to synthesize novel behavior in situations that were not experienced in the demonstrations. We present new algorithms for IRL that have successfully been applied in two real-world, competitive robotics settings: (1) In the domain of rough terrain quadruped locomotion, we present an algorithm that learns an objective function for foothold selection based on "terrain templates". The learner automatically generates and selects the appropriate features which form the objective function, which reduces the need for feature engineering while attaining a high level of generalization. (2) For the domain of autonomous manipulation, we present a local sampling-based path integral IRL approach to deal with the high dimensional space of trajectories. We apply this method to two problems in robotic manipulation: redundancy resolution in inverse kinematics, and trajectory optimization for grasping and manipulation. Both methods have proven themselves as part of larger integrated systems in competitive settings against other teams, where testing was conducted by an independent test team in situations that were not seen during training.
Host: PhD Committee
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
