Difference between revisions of "Main Page"

From cvss
 
(173 intermediate revisions by 5 users not shown)
Line 20: 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 Spring 2013==
+
All talks take place on Thursdays at 3:30pm in AVW 3450.
  
All talks take place Thursdays at 4:30pm in AVW 3450.
+
{| class="wikitable" cellpadding="10" border="1" cellspacing="1"
 
 
{| class="wikitable" cellpadding="10" border="1" cellspacing="0"
 
 
|-
 
|-
 
! Date
 
! Date
Line 31: Line 30:
 
! Title
 
! Title
 
|-
 
|-
| January 24
+
| December 3
| ''(no meeting)''
 
|
 
|-
 
| January 31
 
| Mohammad Rastegari
 
| Scalable object-class retrieval with approximate and top-k ranking
 
|-
 
| February 7
 
 
| Angjoo Kanazawa
 
| Angjoo Kanazawa
| Dog Breed Classification Using Part Localization
+
| Learning 3D Deformation of Animals from 2D Images
|-
 
| February 14
 
| Stephen Xi Chen
 
| Piecing Together the Segmentation Jigsaw using Context
 
|-
 
| February 21
 
| Guangxiao Zhang
 
| Discriminative Dictionary Learning for Sparse Coding : A Batch Version and a Semi-Supervised Online Version
 
|-
 
| February 28
 
| Kota Hara
 
| Boosted Regression Tree and its Application to Computer Vision
 
|-
 
| March 7
 
| Prof. Mohand Said Allili, Assistant professor (University of Quebec/Canada)
 
| Statistical Multi-Scale Decomposition Modeling of Texture and Applications
 
|-
 
| March 14
 
| Arijit Biswas
 
| Attributes for Classifier Feedback
 
|-
 
| March 21
 
| ''(Spring Break, no meeting)''
 
|
 
|-
 
| March 26
 
| Amir R. Zamir
 
| Large Scale Image and Video Geo-localization Using Street View Imagery
 
|-
 
| April 4
 
| ''(Midterms, no meeting)''
 
|
 
|-
 
| April 11
 
| ''(ICCV deadline, no meeting)''
 
|
 
|-
 
| April 18
 
| Sumit Shekhar
 
| Domain-Adaptive Dictionaries
 
|-
 
| April 25
 
| Mohsen Hejrati
 
| Analyzing 3D objects in cluttered images
 
|-
 
| May 2
 
| Xavier Gibert Serra
 
|
 
 
|-
 
|-
| May 9
+
| December 10
| Raviteja Vemulapalli
+
| Xintong Han
|  
+
| Automated Event Retrieval using Web Trained Detectors
 
|}
 
|}
  
==Talk Abstracts Spring 2013==
+
==Talk Abstracts Spring 2015==
 
 
===Scalable object-class retrieval with approximate and top-k ranking===
 
Speaker: [http://www.cs.umd.edu/~mrastega/ Mohammad Rastegari] -- Date: January 31, 2013
 
 
 
In this paper we address the problem of object-class retrieval in large image data sets: given a small set of training examples defining a visual category, the objective is to efficiently retrieve images of the same class from a large database. We propose two contrasting retrieval schemes achieving good accuracy and high efficiency. The first exploits sparse classification models expressed as linear combinations of a small number of features. These sparse models can be efficiently evaluated using inverted file indexing. Furthermore, we introduce a novel ranking procedure that provides a significant speedup over inverted file indexing when the goal is restricted to finding the top-k (i.e., the k highest ranked) images in the data set. We contrast these sparse retrieval models with a second scheme based on approximate ranking using vector quantization. Experimental results show that our algorithms for object-class retrieval can search a 10 million database in just a couple of seconds and produce categorization accuracy comparable to the best known class-recognition systems.
 
 
 
===Dog Breed Classification Using Part Localization===
 
Speaker: [http://www.umiacs.umd.edu/~kanazawa/ Angjoo Kanazawa] -- Date: February 7, 2013
 
 
 
We propose a novel approach to fine-grained image classification in which instances from different classes share common parts but
 
have wide variation in shape and appearance. We use dog breed identification as a test case to show that extracting corresponding parts improves classification performance. This domain is especially challenging since the appearance of corresponding parts can vary dramatically, e.g., the faces of bulldogs and beagles are very different. To find accurate correspondences, we build exemplar-based geometric and appearance models of dog breeds and their face parts. Part correspondence allows us to extract and compare descriptors in like image locations. Our approach also features a hierarchy of parts (e.g., face and eyes) and breed-specific part localization. We achieve 67% recognition rate on a large  real-world dataset including 133 dog breeds and 8,351 images, and experimental results show that accurate part localization significantly increases classification performance compared to state-of-the-art approaches.
 
 
 
===Piecing Together the Segmentation Jigsaw using Context===
 
Speaker: [https://sites.google.com/site/xichenstephen/ Stephen Xi Chen] -- Date: February 14, 2013
 
 
 
We present an approach to jointly solve the segmentation and recognition problem using a multiple segmentation framework. We formulate the problem as segment selection from a pool of segments, 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. Our approach improves labeling performance compared to other segmentation based recognition approaches.
 
 
 
===Discriminative Dictionary Learning for Sparse Coding : A Batch Version and a Semi-Supervised Online Version===
 
Speaker: Guangxiao Zhang -- Date: February 21, 2013
 
 
 
Dictionary learning has been a hot topic in recent years in computer vision. Many dictionary learning strategies have been proposed and led to excellent results in image denoising, inpainting, and recognition. However, most of them optimizes for reconstruction and therefore may not be the best for classification. Moreover, such dictionaries are often over-complete (more dictionary items than the dimension), which is computationally costly when the number of categories is large.
 
 
 
In the first part of the talk, we present a greedy learning algorithm to obtain a compact (small-sized) and discriminative dictionary. Starting with an over-complete dictionary, we map the dictionary items with label into an undirected k-nearest neighbor graph, and model the discriminative dictionary learning as a graph topology selection problem. By optimizing a monotonic, submodular objective function, our algorithm is shown to be highly efficient and effective in face recognition, object recognition, and action/gesture classification tasks.
 
 
 
In the second part of the talk, we present an online, semi-supervised dictionary learning algorithm that is suitable when the size of the dataset is large and the labels are expensive to obtain. Similar to the previous work, our goal is to obtain a dictionary which is both representative and discriminative. Besides learning from labeled data, we also exploit the large amount of cheap, unlabeled training data to reinforce the representation power. An online framework makes the algorithm applicable to large-scale dataset.
 
 
 
===Boosted Regression Tree and its Application to Computer Vision===
 
Speaker: [http://www.kotahara.com/ Kota Hara] -- Date: February 28, 2013
 
 
 
Boosting techniques have been applied to various computer vision tasks, however, most of them are used for classification purposes. In this talk, I will first present Boosted Regression Tree (BRT), a regression version of the boosting used with regression trees, and its simple extension to multidimensional output regression. Then I will show the applications of the BRT on three computer vision tasks, head pose estimation, human pose estimation and class-specific object shape estimation. The BRT is applied to the head pose estimation task straightforwardly. In the human pose estimation task, a body pose estimation task is divided into a set of local pose estimation tasks that maintain a dependency structure and the BRT is used to solve those local pose estimation tasks in a successive manner. Lastly, the class-specific object shape estimation task is addressed by introducing a low dimensional space representing the object shape manifold and using it to bridge the image feature space and the original object shape space.
 
 
 
===Statistical Multi-Scale Decomposition Modeling of Texture and Applications===
 
Speaker: [http://w3.uqo.ca/allimo01/ Prof. Mohand Said Allili], Assistant professor (University of Quebec/Canada): March 7, 2013
 
 
 
Texture modeling and representation has been the subject of interest of several research works in the last decades. This presentation will focus on texture representation using multi-scale decompositions. More specifically, a new statistical framework, based on finite mixtures of Generalized Gaussian (MoGG) distributions, will be presented to model the distribution of multi-scale wavelet/contourlet decomposition coefficients of texture images. After a brief review of the state of the art about wavelet/contourlet statistical modeling, details about parameter estimation of the MoGG model will be presented. Then, two applications will be shown for the proposed approach, namely: wavelet/contourlet-based texture classification and retrieval, and fabric texture defect detection. Experimental results with comparison to recent state of the art methods will be presented as well.
 
 
 
 
 
===Attributes for Classifier Feedback===
 
Speaker: [http://www.umiacs.umd.edu/~arijit/ Arijit Biswas] : March 14, 2013
 
 
 
Active learning provides useful tools to reduce annotation costs without compromising classifier performance. However it traditionally views the supervisor simply as a labeling machine. Recently a new interactive learning paradigm was introduced that allows the supervisor to additionally convey useful domain knowledge using attributes. The learner first conveys its belief about an actively chosen image e.g. "I think this is a forest, what do you think?''. If the learner is wrong, the supervisor provides an explanation e.g. "No, this is too open to be a forest''. With access to a pre-trained set of relative attribute predictors, the learner fetches all unlabeled images more open than the query image, and uses them as negative examples of forests to update its classifier. This rich human-machine communication leads to better classification performance. In this talk, we talk about three improvements over this set-up. First, we incorporate a weighting scheme that instead of making a hard decision reasons about the likelihood of an image being a negative example. Second, we do away with pre-trained attributes and instead learn the attribute models on the fly, alleviating overhead and restrictions of a pre-determined attribute vocabulary. Finally, we propose an active learning framework that accounts for not just the label- but also the attributes-based feedback while selecting the next query image. We demonstrate significant improvement in classification accuracy on faces and shoes. We also collect and make available the largest relative attributes dataset containing 29 attributes of faces from 60 categories.
 
  
===Large Scale Image and Video Geo-localization Using Street View Imagery===
 
Speaker: [http://www.cs.ucf.edu/~aroshan/ Amir R. Zamir] : March 26, 2013
 
  
There has been a growing interest in large scale visual geo-localization methods which utilize structured reference datasets such as Street View. In this talk, we present two frameworks for geo-locating images and videos in a city scale with an accuracy comparable to hand-held GPS devices.
+
===Learning 3D Deformation of Animals from 2D Images===
 +
Speaker: [http://www.umiacs.umd.edu/~kanazawa/ Angjoo Kanazawa] -- Date: December 3, 2015
  
We extract SIFT features from the reference dataset and index them in a data structure tree to make a timely search feasible. To geo-locate a query image, we match its SIFT features against the reference tree and remove the unreliable correspondences using our geo-spatial pruning which incorporates GPS information in the pruning process. We smooth the distribution function formed using the location of the SIFT matches by a two-dimensional Gaussian to utilize the correspondences from nearby places and find the accurate location of the query image.  
+
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.
  
Additionally, we present a method for extracting the geo-spatial trajectory of a moving camera in a city from videos in the wild such as typical YouTube clips. First, we divide the video into smaller segments and localize each one individually. Then, we fuse the information from different segments utilizing a Bayesian formulation to have a temporally consistent trajectory. Lastly, we perform a post processing by a novel non-model-based trajectory reconstruction method based on Minimum Spanning trees; we argue that such post processing is essential for addressing the problems that the basic Bayesian formulation faces due to having a predefined underlying motion model, while the motion of camera in wild videos does not necessary follow any pattern.
+
Link: [http://arxiv.org/pdf/1507.07646v1.pdf paper]
  
===Analyzing 3D objects in cluttered images===
+
===Automated Event Retrieval using Web Trained Detectors===
Speaker: [http://www.umiacs.umd.edu/~sshekha/ Sumit Shekhar] : April 18, 2013
 
  
Data-driven dictionaries have produced state-of-the-art results in various classification tasks. However, when the target data has a different distribution than the source data, the learned sparse representation may not be optimal. In this talk, I will discuss a technique to learn a joint dictionary which can work well for the target data as well, and present some results on face and object recognition.
+
Speaker: [http://www.umiacs.umd.edu/~xintong/ Xintong Han] -- Date: December 10, 2015
  
===Analyzing 3D objects in cluttered images===
+
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.
Speaker: [http://www.ics.uci.edu/~shejrati/ Mohsen Hejrati] : April 25, 2013
 
  
We present an approach to detecting and analyzing the 3D configuration of objects in real-world images with heavy occlusion and clutter. We focus on the application of finding and analyzing cars. We do so with a two-stage framework; the first stage reasons about 2D shape and appearance variation due to within-class variation (station wagons look different than sedans) and changes in viewpoint. Rather than using a view-based model, we describe a compositional representation that models a large number of effective views and shapes using a small number of local view-based templates. We use this model to propose candidate detections and 2D estimates of shape. These estimates are then refined by our second stage, using an explicit 3D model of shape and viewpoint. We use a morphable model to capture 3D within-class variation, and use a weak-perspective camera model to capture viewpoint. We learn all model parameters from 2D annotations. We demonstrate state-of-the-art accuracy for detection, viewpoint estimation, and 3D shape reconstruction on challenging images from the PASCAL VOC 2011 dataset.
+
Link: [http://arxiv.org/pdf/1509.07845v1.pdf paper]
  
 
==Past Semesters==
 
==Past Semesters==
 +
* [[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_fall2012|Fall 2012]]
 
* [[cvss_spring2012|Spring 2012]]
 
* [[cvss_spring2012|Spring 2012]]
Line 166: Line 71:
 
==Funded By==
 
==Funded By==
 
* Computer Vision Faculty
 
* Computer Vision Faculty
* [http://www.northropgrumman.com/ Northrop Grumman]
+
<!-- * '''[http://www.northropgrumman.com/ Northrop Grumman]''' -->
  
 
==Current Seminar Series Coordinators==
 
==Current Seminar Series Coordinators==
Line 172: Line 77:
 
Emails are at umiacs.umd.edu.
 
Emails are at umiacs.umd.edu.
  
{| class="wikitable" cellpadding="5"
+
{| cellpadding="1"
 
|-
 
|-
| [http://www.umiacs.umd.edu/~ejaz/ Ejaz Ahmed], ejaz@
+
| [http://sites.google.com/site/austinomyers/ Austin Myers], amyers@
| (student of [http://www.umiacs.umd.edu/~lsd/ Professor Larry Davis])
+
| (student of [http://www.cfar.umd.edu/~yiannis/ Professor Yiannis Aloimonos])
 
|-
 
|-
 
| [http://www.umiacs.umd.edu/~kanazawa/ Angjoo Kanazawa], kanazawa@
 
| [http://www.umiacs.umd.edu/~kanazawa/ Angjoo Kanazawa], kanazawa@
| (student of [http://www.cs.umd.edu/~djacobs/ Professor David Jacobs])
+
| (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/~jni/ Jie Ni], jni@
+
| [http://www.umiacs.umd.edu/~xintong/ Xintong Han], xintong@
| (student of [http://www.umiacs.umd.edu/~rama/ Professor Rama Chellappa])
+
| (student of [http://www.umiacs.umd.edu/~lsd/ Professor Larry Davis])
 +
|-
 +
| [http://www.cs.umd.edu/~bharat/ Bharat Singh], bharat@
 +
| (student of [http://www.umiacs.umd.edu/~lsd/ Professor Larry Davis])
 
|-
 
|-
| [http://www.umiacs.umd.edu/~cteo/ Ching Lik Teo], cteo@
+
| [http://bcsiriuschen.github.io/ Bor-Chun (Sirius) Chen], sirius@
| (student of [http://www.cfar.umd.edu/~yiannis/ Professor Yiannis Aloimonos])
+
| (student of [http://www.umiacs.umd.edu/~lsd/ Professor Larry Davis])
 
|}
 
|}
  
 
Gone but not forgotten.
 
Gone but not forgotten.
 
+
{| cellpadding="1"
{| class="wikitable" cellpadding="5"
+
|-
 +
| [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])
 +
|
 
|-
 
|-
| [http://cvlab.epfl.ch/~jorstad/ Anne Jorstad]
+
| [http://ravitejav.weebly.com/ Raviteja Vemulapalli], raviteja @
| now PostDoc at EPFL
+
| (student of [http://www.umiacs.umd.edu/~rama/ Professor Rama Chellappa])
 
|-
 
|-
 
| [http://www.umiacs.umd.edu/~sameh/ Sameh Khamis]
 
| [http://www.umiacs.umd.edu/~sameh/ Sameh Khamis]
| off this semester
+
|  
 +
|-
 +
| [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/~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