Difference between revisions of "Main Page"

From cvss
 
(304 intermediate revisions by 9 users not shown)
Line 3: Line 3:
 
The Computer Vision Student Seminars at the University of Maryland College Park are a student-run series of talks given by [http://www.cfar.umd.edu/cvl/meetthe.html#Graduate current graduate students] for [http://www.cfar.umd.edu/cvl/meetthe.html#Graduate current graduate students].
 
The Computer Vision Student Seminars at the University of Maryland College Park are a student-run series of talks given by [http://www.cfar.umd.edu/cvl/meetthe.html#Graduate current graduate students] for [http://www.cfar.umd.edu/cvl/meetthe.html#Graduate current graduate students].
  
−
To receive regular information about the Computer Vision Student Seminars, subscribe to the mailing list by following the instructions [https://mailman.cs.umd.edu/mailman/listinfo/cvss here].
+
To receive regular information about the Computer Vision Student Seminars, subscribe to our [https://mailman.cs.umd.edu/mailman/listinfo/cvss mailing list] or our [http://talks.cs.umd.edu/lists/12 talks list].
  
 
==Description==
 
==Description==
Line 13: Line 13:
 
* Provide an opportunity for computer vision students to receive feedback on their current research;
 
* Provide an opportunity for computer vision students to receive feedback on their current research;
 
* Provide speaking opportunities for computer vision students.
 
* Provide speaking opportunities for computer vision students.
−
 
  
 
The guidelines for the format are:
 
The guidelines for the format are:
Line 21: Line 20:
 
* 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.
 
* 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 Fall 2015==
  
−
==Schedule Fall 2011==
+
All talks take place on Thursdays at 3:30pm in AVW 3450.
−
 
 
−
All talks take place Thursdays at 4pm in AVW 3450.
 
  
−
{| class="wikitable" cellpadding="10" border="1" cellspacing="0"
+
{| class="wikitable" cellpadding="10" border="1" cellspacing="1"
 
|-
 
|-
 
! Date
 
! Date
Line 32: Line 30:
 
! Title
 
! Title
 
|-
 
|-
−
| September 8
+
| December 3
−
| Vishal Patel
+
| Angjoo Kanazawa
−
| Wavelets with Composite Dilations
+
| Learning 3D Deformation of Animals from 2D Images
−
|-
 
−
| September 15
 
−
| Radu Dondera
 
−
| Kernel PLS Regression for Robust Monocular Pose Estimation
 
−
|-
 
−
| September 22
 
−
| Dave Shaw
 
−
| Regularization and Localization for Prediction on Manifolds
 
−
|-
 
−
| September 29
 
−
| Douglas Summers-Stay (room 3165)
 
−
| Scene Classification with Visual Filters
 
−
|-
 
−
| October 6
 
−
| Arpit Jain
 
−
| Learning What and How of Contextual Models for Scene Labeling
 
−
|-
 
−
| October 13
 
−
| Yi-Chen Chen
 
−
| Rotation Invariant Simultaneous Clustering and Dictionary Learning  
 
−
|-
 
−
| October 20
 
−
| Anne Jorstad
 
−
| Deformation and Lighting Insensitive Face Recognition: From Optical Flow to Geodesics
 
−
|-
 
−
| October 27
 
−
| Garrett Warnell
 
−
| Compressive Sensing in Visual Tracking
 
−
|-
 
−
| November 3
 
−
| Abhishek Sharma
 
−
| Cross-Modal Classification and Retrieval: Techniques and Challenges
 
−
|-
 
−
| November 10
 
−
| Cheuk Yiu Ip
 
−
| Saliency-Assisted Navigation of Very Large Landscape Images
 
−
|-
 
−
| November 17
 
−
| ''(no meeting, CVPR deadline 11/21)''
 
−
|
 
−
|-
 
−
| November 24
 
−
| ''(no meeting, Thanksgiving)''
 
−
|
 
−
|-
 
−
| December 1
 
−
| Ming-Yu Liu
 
−
| Entropy Rate Clustering: Cluster Analysis via Maximizing a Submodular Function Subject to a Matroid Constraint
 
−
|-
 
−
| December 8
 
−
| Nitesh Shroff
 
−
|
 
 
|-
 
|-
−
| December 15
+
| December 10
−
| ''(no meeting, final exams)''
+
| Xintong Han
−
|
+
| Automated Event Retrieval using Web Trained Detectors
 
|}
 
|}
  
 +
==Talk Abstracts Spring 2015==
  
−
==Talk Abstracts Fall 2011==
 
−
 
−
===Wavelets with Composite Dilations===
 
−
Speaker: [http://www.umiacs.umd.edu/~pvishalm/ Vishal Patel] -- Date: September 8, 2011
 
−
 
−
Sparse representation of visual information lies at the foundation of many image processing applications, such as image restoration and compression. It is well known that wavelets provide a very sparse representation for a large class of signals and images. For instance, from a continuous perspective, wavelets can be shown to sparsely represent one-dimensional signals that are smooth away from point discontinuities. Unfortunately, separable wavelet transforms have some limitations in higher dimensions. For this reason, in recent years there has been considerable interest in obtaining directionally-oriented image decompositions. Wavelets with composite dilations offer a general and especially effective framework for the construction of such representations.  In this talk, I will discuss the theory and implementation of several recently introduced multiscale directional transforms. Then, I will present a new general scheme for creating an M-channel directional filter bank. An advantage of an M-channel directional filter bank is that it can project the image directly onto the desired basis. Applications in image denoising, deconvolution and image enhancement will be presented.
 
−
 
−
===Kernel PLS Regression for Robust Monocular Pose Estimation===
 
−
Speaker: [http://www.umiacs.umd.edu/~rdondera/ Radu Dondera] -- Date: September 15, 2011
 
−
 
−
We evaluate the robustness of five regression techniques for monocular 3D pose estimation. While most of the discriminative pose estimation methods focus on overcoming the fundamental problem of insufficient training data, we are interested in characterizing performance improvement for increasingly large training sets. Commercially available rendering software allows us to efficiently generate large numbers of realistic images of poses from diverse actions. Inspired by recent work in human detection, we apply PLS and kPLS regression to pose estimation. We observe that kPLS regression incrementally approximates GP regression using the strongest nonlinear correlations between image features and pose. This provides robustness, and our experiments show kPLS regression is more robust than two GP-based state-of-the-art methods for pose estimation. We address the ambiguity problem of pose estimation by random partitioning of the pose space and report results on the HumanEva dataset.
 
−
 
−
===Regularization and Localization for Prediction on Manifolds===
 
−
Speaker: David Shaw -- Date: September 22, 2011
 
−
 
−
In data analysis, one is interested in using the information about the response variable contained in the predictors in the best way possible.  This can lead to problems when the predictors are highly collinear, as it implies an inherent lower-dimensional structure in the data.  One method of analyzing data of this form is to make the assumption that these structured dependencies arise due to the predictors lying on some implicit lower-dimensional manifold.  This assumption helps solve the problem of reducing the dimension of the predictors in the interest of removing some redundant information, but it introduces the problem of analyzing the transformed data.  In particular, making accurate predictions with the lower-dimensional data that can be interpreted in the higher-dimensional space can be difficult.  The technique of weighted regression with regularization on the model parameters can help to overcome these issues.
 
−
 
−
===Scene Classification with Visual Filters===
 
−
Speaker: [http://www.cs.umd.edu/~dss/ Douglas Summers-Stay] -- Date: September 29, 2011
 
−
 
−
"Scene Classification" is the computer vision problem of labeling all the pixels in an image according to the class they fall into, such as "street," "tree," or "person." A tool we have developed here at the computer vision lab called "visual filters" uses a series of nonlinear filters to attempt to create such classification maps. I will discuss what we are doing now and how we can incorporate ideas from "deep learning" to improve this in the future. An introduction for beginners with some examples is [http://llamasandmystegosaurus.blogspot.com/search?q=visual+filters here].
 
−
 
−
===Learning What and How of Contextual Models for Scene Labeling===
 
−
Speaker: [http://www.umiacs.umd.edu/~ajain/ Arpit Jain] -- Date: October 6, 2011
 
−
 
−
In this talk I will discuss about 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. Most of the previous approaches used either a fixed fully connected Markov Network(MN) or ad-hoc neighborhood connected MN. But not edges in MN are useful and this is what I will show during my talk. I will also address the coupled problem of predicting the feature weights associated with each edge of a Markov network for evaluation of context. Experimental results indicate that this scene dependent structure construction model eliminates spurious edges and improves performance over fully-connected and neighborhood connected Markov network.
 
−
 
−
===Rotation Invariant Simultaneous Clustering and Dictionary Learning===
 
−
Speaker: Yi-Chen Chen -- Date: October 13, 2011
 
−
 
−
We present an approach that simultaneously clusters database members and learns dictionaries from the clusters. The method learns dictionaries in the Radon transform domain, while clustering in the image domain. The main feature of the proposed approach is that it provides rotation invariant clustering which is useful in Content Based Image Retrieval (CBIR). We demonstrate through experimental results that the proposed rotation invariant clustering provides good retrieval performance than the standard Gabor-based method that has similar objectives.
 
−
 
−
===Deformation and Lighting Insensitive Face Recognition: From Optical Flow to Geodesics===
 
−
Speaker: [http://www-users.math.umd.edu/~jorstad/ Anne Jorstad] -- Date: October 20, 2011
 
−
 
−
We seek to solve the face identification problem across variations in expression and lighting together in a single framework.  In order to understand variations in expression, a dense correspondence between images must be found, leading to algorithms similar to Optical Flow.  We present a new lighting-insensitive metric to drive this Optical Flow-like framework.  An extension of this work to the manifold of face images is then proposed, where a curve on the manifold represents the way a face might morph through time, allowing pixels to vary slowly as properties of the face change.  The length of the geodesic connecting a pair of faces defines their similarity for nearest neighbor matching.
 
−
 
−
===Compressive Sensing in Visual Tracking===
 
−
Speaker: Garrett Warnell -- Date: October 27, 2011
 
−
 
−
Visual tracking is a classical computer vision task.  However, the ubiquity of modern sensors makes it more difficult due to the large amount of data available for processing.  The emerging theory of compressive sensing has the potential to address this problem in that it promises the ability to reduce the amount of data collected without sacrificing the amount of information within.  In this talk, I will review recent research research toward the adaptation of some computer vision algorithms commonly used in visual tracking such that they can operate in the lower-dimensional compressive domain.  Specifically, background subtraction and particle filtering will be discussed.
 
−
 
−
===Cross-Modal Classification and Retrieval: Techniques and Challenges===
 
−
Speaker: [http://www.cs.umd.edu/~bhokaal/ Abhishek Sharma] -- Date: November 3, 2011
 
  
−
Classification data arrives in multiple forms of representations and distributions (modality) having a common underlying content. Classification or Retrieval is required to be done solely based on the content irrespective of the modality. For example - given a text description of a topic (history) find appropriate images from a database OR given a person's face image in some pose and lighting which is different than that of the gallery, find the matching face OR based on user supplied tags find matching images from the database. These problems are finding applications everywhere because of wide-spread Internet and extremely cheap sensors (cameras and keyboards).
+
===Learning 3D Deformation of Animals from 2D Images===
 +
Speaker: [http://www.umiacs.umd.edu/~kanazawa/ Angjoo Kanazawa] -- Date: December 3, 2015
  
−
In this talk, we will go over some popular techniques from the literature to tackle the problem of cross-modal classification and retrieval. Specifically, I will be discussing Canonical Correlational Analysis (and variants), Partial Least Square, Bilinear Model (Freeman and Tannenbaum), Tied Factor Analysis, Probabilstic LDA, Multi-view LDA and SVM-2k along with detailed pros and cons of each of these. Then I will present a comparative application of all these approaches along with recent methods for pose and lighting invariant face recognition as a case study.  
+
Abstract: Understanding how an animal can deform and articulate is essential for a realistic modification of its 3D model. In this paper, we show that such information can be learned from user-clicked 2D images and a template 3D model of the target animal. We present a volumetric deformation framework that produces a set of new 3D models by deforming a template 3D model according to a set of user-clicked images. Our framework is based on a novel locally-bounded deformation energy, where every local region has its own stiffness value that bounds how much distortion is allowed at that location. We jointly learn the local stiffness bounds as we deform the template 3D mesh to match each user-clicked image. We show that this seemingly complex task can be solved as a sequence of convex optimization problems. We demonstrate the effectiveness of our approach on cats and horses, which are highly deformable and articulated animals. Our framework produces new 3D models of animals that are significantly more plausible than methods without learned stiffness.
  
−
===Saliency-Assisted Navigation of Very Large Landscape Images===
+
Link: [http://arxiv.org/pdf/1507.07646v1.pdf paper]
−
Speaker: [http://www.cs.umd.edu/~ipcy/ Cheuk Yiu Ip] -- Date: November 10, 2011
 
  
−
This work presents the first steps towards navigation of very large images, particularly landscape images, from an interactive visualization perspective. The grand challenge in navigation of very large images is identifying regions of potential interest. We outline a three-step approach. We show that our approach of progressive elicitation is fast and allows rapid identification of regions of interest. Our approach is scalable and computationally reasonable on very large images. We validate the results of our approach by comparing them to user-tagged regions of interest on several very large landscape images from the Internet.
+
===Automated Event Retrieval using Web Trained Detectors===
  
−
===Entropy Rate Clustering: Cluster Analysis via Maximizing a Submodular Function Subject to a Matroid Constraint===
+
Speaker: [http://www.umiacs.umd.edu/~xintong/ Xintong Han] -- Date: December 10, 2015
−
Speaker: [http://www.umiacs.umd.edu/~mingyliu/ Ming-Yu Liu] -- Date: December 1, 2011
 
  
−
We propose a new objective function for clustering. This objective function consists of two components: the entropy rate of a random walk on a graph and a balancing term. The entropy rate favors the formation of compact and homogeneous clusters, while the balancing function encourages clusters with similar sizes and penalizes larger clusters that aggressively group samples. We present a novel graph construction for the graph associated with the data and show that this construction induces a matroid-- a combinatorial structure that generalizes the concept of linear independence in vector spaces. The clustering result is given by the graph topology that maximizes the objective function under the matroid constraint. By exploiting the submodular and monotonic properties of the objective function, we develop an efficient greedy algorithm. Furthermore, we prove an approximation bound of 1/2 for the optimality of the greedy solution. We validate the proposed algorithm on various benchmarks and show its competitive performances with respect to popular clustering algorithms. We further apply it for the task of superpixel segmentation. Experiments on the Berkeley segmentation dataset reveal its superior performances over the state-of-the-art superpixel segmentation algorithms in all the standard evaluation metrics.
+
Abstract: Complex event retrieval is a challenging research problem, especially when no training videos are available. An alternative to collecting training videos is to train a large semantic concept bank a priori. Given a text description of an event, event retrieval is performed by selecting concepts linguistically related to the event description and fusing the concept responses on unseen videos. However, defining an exhaustive concept lexicon and pre-training it requires vast computational resources. Therefore, recent approaches automate concept discovery and training by leveraging large amounts of weakly annotated web data. Compact visually salient concepts are automatically obtained by the use of concept pairs or, more generally, n-grams. However, not all visually salient n-grams are necessarily useful for an event query - some combinations of concepts may be visually compact but irrelevant--and this drastically affects performance. We propose an event retrieval algorithm that constructs pairs of automatically discovered concepts and then prunes those concepts that are unlikely to be helpful for retrieval. Pruning depends both on the query and on the specific video instance being evaluated. Our approach also addresses calibration and domain adaptation issues that arise when applying concept detectors to unseen videos. We demonstrate large improvements over other vision based systems on the TRECVID MED 13 dataset.
  
 +
Link: [http://arxiv.org/pdf/1509.07845v1.pdf paper]
  
 
==Past Semesters==
 
==Past Semesters==
−
* [[cvss_summer2011|Schedule Summer 2011]]
+
* [[Cvss:Spring2015| Spring 2015]]
 +
* [[cvss fall2014|Fall 2014]]
 +
* [[cvss_spring2014|Spring 2014]]
 +
* [[cvss_fall2013|Fall 2013]]
 +
* [[cvss_summer2013|Summer 2013]]
 +
* [[cvss_spring2013|Spring 2013]]
 +
* [[cvss_fall2012|Fall 2012]]
 +
* [[cvss_spring2012|Spring 2012]]
 +
* [[cvss_fall2011|Fall 2011]]
 +
* [[cvss_summer2011|Summer 2011]]
  
 +
==Funded By==
 +
* Computer Vision Faculty
 +
<!-- * '''[http://www.northropgrumman.com/ Northrop Grumman]''' -->
  
 
==Current Seminar Series Coordinators==
 
==Current Seminar Series Coordinators==
Line 162: Line 77:
 
Emails are at umiacs.umd.edu.
 
Emails are at umiacs.umd.edu.
  
−
{| class="wikitable" cellpadding="5"
+
{| cellpadding="1"
 +
|-
 +
| [http://sites.google.com/site/austinomyers/ Austin Myers], amyers@
 +
| (student of [http://www.cfar.umd.edu/~yiannis/ Professor Yiannis Aloimonos])
 +
|-
 +
| [http://www.umiacs.umd.edu/~kanazawa/ Angjoo Kanazawa], kanazawa@
 +
| (student of [http://cs.umd.edu/~djacobs/ Professor David Jacobs])
 +
|-
 +
| [http://sites.google.com/site/yechengxi/ Chenxi Ye] cxy@
 +
| (student of [http://www.cfar.umd.edu/~yiannis/ Professor Yiannis Aloimonos])
 +
|-
 +
| [http://www.umiacs.umd.edu/~xintong/ Xintong Han], xintong@
 +
| (student of [http://www.umiacs.umd.edu/~lsd/ Professor Larry Davis])
 
|-
 
|-
−
| Anne Jorstad, jorstad@
+
| [http://www.cs.umd.edu/~bharat/ Bharat Singh], bharat@
−
| (student of [http://www.cs.umd.edu/~djacobs/ Professor David Jacobs])
+
| (student of [http://www.umiacs.umd.edu/~lsd/ Professor Larry Davis])
 
|-
 
|-
−
| Sameh Khamis, sameh@
+
| [http://bcsiriuschen.github.io/ Bor-Chun (Sirius) Chen], sirius@
 
| (student of [http://www.umiacs.umd.edu/~lsd/ Professor Larry Davis])
 
| (student of [http://www.umiacs.umd.edu/~lsd/ Professor Larry Davis])
 +
|}
 +
 +
Gone but not forgotten.
 +
{| cellpadding="1"
 +
|-
 +
| [http://www.umiacs.umd.edu/~jhchoi/ Jonghyun Choi], jhchoi@
 +
| (student of [http://www.umiacs.umd.edu/~lsd/ Professor Larry Davis])
 +
|-
 +
| Ching-Hui Chen, ching@
 +
| (student of [http://www.umiacs.umd.edu/~rama/ Professor Rama Chellappa])
 +
|
 
|-
 
|-
−
| Sima Taheri, taheri@
+
| [http://ravitejav.weebly.com/ Raviteja Vemulapalli], raviteja @
 
| (student of [http://www.umiacs.umd.edu/~rama/ Professor Rama Chellappa])
 
| (student of [http://www.umiacs.umd.edu/~rama/ Professor Rama Chellappa])
 
|-
 
|-
−
| Ching Lik Teo, cteo@
+
| [http://www.umiacs.umd.edu/~sameh/ Sameh Khamis]
−
| (student of [http://www.cfar.umd.edu/~yiannis/ Professor Yiannis Aloimonos])
+
|
 +
|-
 +
| [http://www.umiacs.umd.edu/~ejaz/ Ejaz Ahmed]
 +
|
 +
|-
 +
| [http://cvlabwww.epfl.ch/~jorstad/ Anne Jorstad]
 +
| now at EPFL
 +
|-
 +
| [http://www.umiacs.umd.edu/~jni/ Jie Ni]
 +
| now at Sony
 +
|-
 +
| [http://www.umiacs.umd.edu/~taheri/ Sima Taheri]
 +
|
 +
|-
 +
| [http://www.umiacs.umd.edu/~cteo/ Ching Lik Teo]
 +
|
 
|}
 
|}

Latest revision as of 23:40, 3 December 2015

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[edit]

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 Fall 2015[edit]

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

Date Speaker Title
December 3 Angjoo Kanazawa Learning 3D Deformation of Animals from 2D Images
December 10 Xintong Han Automated Event Retrieval using Web Trained Detectors

Talk Abstracts Spring 2015[edit]

Learning 3D Deformation of Animals from 2D Images[edit]

Speaker: Angjoo Kanazawa -- Date: December 3, 2015

Abstract: Understanding how an animal can deform and articulate is essential for a realistic modification of its 3D model. In this paper, we show that such information can be learned from user-clicked 2D images and a template 3D model of the target animal. We present a volumetric deformation framework that produces a set of new 3D models by deforming a template 3D model according to a set of user-clicked images. Our framework is based on a novel locally-bounded deformation energy, where every local region has its own stiffness value that bounds how much distortion is allowed at that location. We jointly learn the local stiffness bounds as we deform the template 3D mesh to match each user-clicked image. We show that this seemingly complex task can be solved as a sequence of convex optimization problems. We demonstrate the effectiveness of our approach on cats and horses, which are highly deformable and articulated animals. Our framework produces new 3D models of animals that are significantly more plausible than methods without learned stiffness.

Link: paper

Automated Event Retrieval using Web Trained Detectors[edit]

Speaker: Xintong Han -- Date: December 10, 2015

Abstract: Complex event retrieval is a challenging research problem, especially when no training videos are available. An alternative to collecting training videos is to train a large semantic concept bank a priori. Given a text description of an event, event retrieval is performed by selecting concepts linguistically related to the event description and fusing the concept responses on unseen videos. However, defining an exhaustive concept lexicon and pre-training it requires vast computational resources. Therefore, recent approaches automate concept discovery and training by leveraging large amounts of weakly annotated web data. Compact visually salient concepts are automatically obtained by the use of concept pairs or, more generally, n-grams. However, not all visually salient n-grams are necessarily useful for an event query - some combinations of concepts may be visually compact but irrelevant--and this drastically affects performance. We propose an event retrieval algorithm that constructs pairs of automatically discovered concepts and then prunes those concepts that are unlikely to be helpful for retrieval. Pruning depends both on the query and on the specific video instance being evaluated. Our approach also addresses calibration and domain adaptation issues that arise when applying concept detectors to unseen videos. We demonstrate large improvements over other vision based systems on the TRECVID MED 13 dataset.

Link: paper

Past Semesters[edit]

Funded By[edit]

  • Computer Vision Faculty

Current Seminar Series Coordinators[edit]

Emails are at umiacs.umd.edu.

Austin Myers, amyers@ (student of Professor Yiannis Aloimonos)
Angjoo Kanazawa, kanazawa@ (student of Professor David Jacobs)
Chenxi Ye cxy@ (student of Professor Yiannis Aloimonos)
Xintong Han, xintong@ (student of Professor Larry Davis)
Bharat Singh, bharat@ (student of Professor Larry Davis)
Bor-Chun (Sirius) Chen, sirius@ (student of Professor Larry Davis)

Gone but not forgotten.

Jonghyun Choi, jhchoi@ (student of Professor Larry Davis)
Ching-Hui Chen, ching@ (student of Professor Rama Chellappa)
Raviteja Vemulapalli, raviteja @ (student of Professor Rama Chellappa)
Sameh Khamis
Ejaz Ahmed
Anne Jorstad now at EPFL
Jie Ni now at Sony
Sima Taheri
Ching Lik Teo

Web Accessibility

Retrieved from "https://wiki.cs.umd.edu/cvss/w/index.php?title=Main_Page&oldid=1868"