Main Page

Computer Vision Student Seminars

The Computer Vision Student Seminars at the University of Maryland College Park are a student-run series of talks given by current graduate students for current graduate students.

To receive regular information about the Computer Vision Student Seminars, subscribe to our mailing list or our talks list.

Description

The purpose of these talks is to:

• Encourage interaction between computer vision students;
• Provide an opportunity for computer vision students to be aware of and possibly get involved in the research their peers are conducting;
• Provide an opportunity for computer vision students to receive feedback on their current research;
• Provide speaking opportunities for computer vision students.

The guidelines for the format are:

• An hour-long weekly meeting, consisting of one 20-40 minute talk followed by discussion and food.
• The talks are meant to be casual and discussion is encouraged.
• Topics may include current research, past research, general topic presentations, paper summaries and critiques, or anything else beneficial to the computer vision graduate student community.

Schedule Spring 2014

All talks take place on Thursdays at 3:30pm in AVW 3450.

Date	Speaker	Title
January 30	Arpit Jain	Scene and Video Understanding
February 6	Raviteja Vemulapalli	Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group
February 13	Google DC PhD Summit, no meeting
February 20	Varun Nagaraja	Feedback Loop between High Level Semantics and Low Level Vision
February 27	Mohammad Rastegari	Predictable Dual View Hashing and Domain Adaptive Classification
March 6	ECCV deadline, no meeting
March 13	Xavier Gibert Serra	TBA
March 20	Spring break, no meeting
March 27	Swaminathan Sankaranarayanan	TBA
April 3	Austin Myers	TBA
April 10	Jing Jing	TBA
April 17	Kota Hara	TBA
April 24	Ejaz Ahmed	TBA
May 1	Garrett Warnell	TBA
May 8	Sameh Khamis	TBA
May 15	Sumit Sekhar	TBA

Talk Abstracts Spring 2014

Scene and Video Understanding

Speaker: Arpit Jain -- Date: January 30, 2014

There has been significant improvements in the accuracy of scene understanding due to a shift from recognizing objects ``in isolation to context based recognition systems. Such systems improve recognition rates by augmenting appearance based models of individual objects with contextual information based on pairwise relationships between objects. These pairwise relations incorporate common world knowledge such as co-occurences and spatial arrangements of objects, scene layout, etc. However, these relations, even though consistent in 3D world, change due to viewpoint of the scene. In this thesis, we will look into the problems of incorporating contextual information from two different perspective for scene understanding problem (a) ``what contextual relations are useful and ``how they should be incorporated into Markov network during inference. (b) jointly solve the segmentation and recognition problem using a multiple segmentation framework based on contextual information in conjunction with appearance matching. In the later part of the thesis, we will investigate different representations for video understanding and propose a discriminative patch based representation for videos.

Our work depart from traditional view of incorporating context into scene understanding problem where a fixed model for context is learned. We argue that context is scene dependent and propose a data-driven approach to predict the importance of edges and construct a Markov network for image analysis based on statistical models of global and local image features. Since all contextual information are not equally important, we also address the coupled problem of predicting the feature weights associated with each edge of a Markov network for evaluation of context. We then address the problem of fixed segmentation while modelling context by using a multiple segmentation framework and formulating the problem as ``a jigsaw puzzle. We formulate the problem as segment selection from a pool of segments (jigsaws), assigning each selected segment a class label. Previous multiple segmentation approaches used local appearance matching to select segments in a greedy manner. In contrast, our approach formulates a cost function based on contextual information in conjunction with appearance matching. This relaxed cost function formulation is minimized using an efficient quadratic programming solver and an approximate solution is obtained by discretizing the relaxed solution.

Lastly, we propose a new representation for videos based on mid-level discriminative spatio-temporal patches. These spatio-temporal patches might correspond to a primitive human action, a semantic object, or perhaps a random but informative spatiotemporal patch in the video. What defines these spatiotemporal patches is their discriminative and representative properties. We automatically mine these patches from hundreds of training videos and experimentally demonstrate that these patches establish correspondence across videos and align the videos for label transfer techniques. Furthermore, these patches can be used as a discriminative vocabulary for action classification.

Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group

Speaker: Raviteja Vemulapalli -- Date: February 6, 2014

Recently introduced cost-effective depth sensors coupled with the real-time skeleton estimation algorithm of Shotton et al. [16] have resulted in a renewed interest in skeleton-based human action recognition. Most of the earlier skeleton-based approaches used either the joint locations or the joint angles to represent a human skeleton. In this paper, we propose a new skeletal representation that explicitly models the 3D geometric relationships between various body parts using rotations and translations in 3D space. Since 3D rigid body motions are members of the special Euclidean group SE(3), the proposed skeletal representation lies in the Lie group SE(3)×. . .×SE(3), which is a curved manifold. With the proposed representation human actions can be modeled as curves in this Lie group. Since classification of curves in this Lie group is not an easy task, we map the action curves from the Lie group to its Lie algebra, which is a vector space. We then perform classification using a combination of dynamic time warping, Fourier temporal pyramid representation and linear SVM. Experimental results on three action datasets show that the proposed representation performs better than various other commonly-used skeletal representations. The proposed approach also outperforms various state-of-the-art skeleton-based human action recognition approaches.

Feedback Loop between High Level Semantics and Low Level Vision

Speaker: Varun Nagaraja -- Date: February 20, 2014

High level semantical analysis typically involves constructing a Markov network over detections from low level detectors to encode context and model relationships between them. In complex higher order networks (e.g. Markov Logic Networks), each detection can be part of many factors and the network size grows rapidly as a function of the number of detections. Hence to keep the network size small, a threshold is applied on the confidence measures of the detections to discard the less likely detections. A practical challenge is to decide what thresholds to use to discard noisy detections. A high threshold will lead to a high false dismissal rate. A low threshold can result in many detections including mostly noisy ones which leads to a large network size and increased computational requirements.

We propose a feedback based incremental technique to tackle this problem, where we initialize the network with high confidence detections and then based on the high level semantics in the initial network, we can incrementally select the relevant missing low level detections. We show three different ways of selecting detections which are based on three scoring functions that bound the increase in the optimal value of the objective function of network, with varying degrees of accuracy and computational cost. We perform experiments with an event recognition task in one-on-one basketball videos that uses Markov Logic Networks.

Predictable Dual View Hashing and Domain Adaptive Classification

Speaker: Mohammad Rastegari -- Date: February 27, 2014

We propose a Predictable Dual-View Hashing (PDH) algorithm which embeds proximity of data samples in the original spaces. We create a cross-view hamming space with the ability to compare information from previously incomparable domains with a notion of 'predictability'. By performing comparative experimental analysis on two large datasets, PASCAL-Sentence and SUN-Attribute, we demonstrate the superiority of our method to the state-of-the-art dual-view binary code learning algorithms. We also propose an unsupervised domain adaptation method that exploits intrinsic compact structures of categories across different domains using binary attributes. Our method directly optimizes for classification in the target domain. The key insight is finding attributes that are discriminative across categories and predictable across domains.

Past Semesters

• Fall 2013
• Summer 2013
• Spring 2013
• Fall 2012
• Spring 2012
• Fall 2011
• Summer 2011

Funded By

• Computer Vision Faculty
• Northrop Grumman

Current Seminar Series Coordinators

Emails are at umiacs.umd.edu.

Angjoo Kanazawa, kanazawa@	(student of Professor David Jacobs)
Sameh Khamis, sameh@	(student of Professor Larry Davis)
Austin Myers, amyers@	(student of Professor Yiannis Aloimonos)
Raviteja Vemulapalli, raviteja @	(student of Professor Rama Chellappa)

Gone but not forgotten.

Ejaz Ahmed
Anne Jorstad	now at EPFL
Jie Ni	off this semester
Sima Taheri
Ching Lik Teo

Web Accessibility