Search results for: Nebojsa Jojic

Items from 1 to 20 out of 28 results

article

Subspace Learning by $$\ell ^{0}$$ ℓ0 -Induced Sparsity

Yingzhen Yang, Jiashi Feng, Nebojsa Jojic, Jianchao Yang, more

International Journal of Computer Vision > 2018 > 126 > 10 > 1138-1156

Subspace clustering methods partition the data that lie in or close to a union of subspaces in accordance with the subspace structure. Such methods with sparsity prior, such as sparse subspace clustering (SSC) (Elhamifar and Vidal in IEEE Trans Pattern Anal Mach Intell 35(11):2765–2781, 2013) with the sparsity induced by the $$\ell ^{1}$$ ℓ1 -norm, are demonstrated to be effective in subspace clustering...

chapter

Summarization and Classification of Wearable Camera Streams by Learning the Distributions over Deep Features of Out-of-Sample Image Sequences

Alessandro Penna, Sadegh Mohammadi, Nebojsa Jojic, Vittorio Murino

2017 IEEE International Conference on Computer Vision (ICCV) > 4336 - 4344

2017 IEEE International Conference on Computer Vision (ICCV)

A popular approach to training classifiers of new image classes is to use lower levels of a pre-trained feed-forward neural network and retrain only the top. Thus, most layers simply serve as highly nonlinear feature extractors. While these features were found useful for classifying a variety of scenes and objects, previous work also demonstrated unusual levels of sensitivity to the input especially...

chapter

ER3: A Unified Framework for Event Retrieval, Recognition and Recounting

Zhanning Gao, Gang Hua, Dongqing Zhang, Nebojsa Jojic, more

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) > 2107 - 2116

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

We develop a unified framework for complex event retrieval, recognition and recounting. The framework is based on a compact video representation that exploits the temporal correlations in image features. Our feature alignment procedure identifies and removes the feature redundancies across frames and outputs an intermediate tensor representation we call video imprint. The video imprint is then fed...

article

Traveling on discrete embeddings of gene expression

Pietro Lovato, Manuele Bicego, Maria Kesa, Nebojsa Jojic, more

Artificial Intelligence in Medicine > 2016 > 70 > C > 1-11

High-throughput technologies have generated an unprecedented amount of high-dimensional gene expression data. Algorithmic approaches could be extremely useful to distill information and derive compact interpretable representations of the statistical patterns present in the data. This paper proposes a mining approach to extract an informative representation of gene expression profiles based on a generative...

chapter

Shift-Invariant Adaptive Double Threading: Learning MHC II - Peptide Binding

Noah Zaitlen, Manuel Reyes-Gomez, David Heckerman, Nebojsa Jojic

Lecture Notes in Computer Science > Research in Computational Molecular Biology > 181-195

Specificity of MHC binding to short peptide fragments from cellular as well as pathogens’ proteins has been found to correlate with disease outcome and pathogen or cancer evolution. The large variation in MHC class II epitope length has complicated training of predictors for binding affinities compared to MHC class I. In this paper, we treat the relative position of the peptide inside the MHC protein...

chapter

Audio-Video Sensor Fusion with Probabilistic Graphical Models

Matthew J. Beal, Hagai Attias, Nebojsa Jojic

Lecture Notes in Computer Science > Computer Vision — ECCV 2002 > Image Features / Visual Motion > 736-750

We present a new approach to modeling and processing multimedia data. This approach is based on graphical models that combine audio and video variables. We demonstrate it by developing a new algorithm for tracking a moving object in a cluttered, noisy scene using two microphones and a camera. Our model uses unobserved variables to describe the data in terms of the process that generates them. It is...

chapter

On analysis of cloth drape range data

Nebojsa Jojic, Thomas S. Huang

Lecture Notes in Computer Science > Computer Vision — ACCV'98 > 463-470

In this paper we present an algorithm for analysis of the range data of cloth drapes. The goal of the analysis is estimation of parameters for modeling and the geometry of the underlying object. In an analysis-by-synthesis manner, the algorithm compares the drape of the model with the range data and searches for the best fit. It can be applied to any physics-based cloth model. The motivating application...

chapter

Constructing Treatment Portfolios Using Affinity Propagation

Delbert Dueck, Brendan J. Frey, Nebojsa Jojic, Vladimir Jojic, more

Lecture Notes in Computer Science > Research in Computational Molecular Biology > 360-371

A key problem of interest to biologists and medical researchers is the selection of a subset of queries or treatments that provide maximum utility for a population of targets. For example, when studying how gene deletion mutants respond to each of thousands of drugs, it is desirable to identify a small subset of genes that nearly uniquely define a drug ‘footprint’ that provides maximum predictability...

chapter

A Generative Model of Dense Optical Flow in Layers

Anitha Kannan, Brendan Frey, Nebojsa Jojic

Lecture Notes in Computer Science > Spatial Coherence for Visual Motion Analysis > 104-114

We introduce a generative model of dense flow fields within a layered representation of 3-dimensional scenes. Using probabilistic inference and learning techniques (namely, variational methods), we solve the inverse problem and locally segment the foreground from the background, estimate the nonuniform motion of each, and fill in the disocclusions. To illustrate the usefulness of both the representation...

chapter

Reconstructing the Phylogeny of Mobile Elements

Sean O’Rourke, Noah Zaitlen, Nebojsa Jojic, Eleazar Eskin

Lecture Notes in Computer Science > Research in Computational Molecular Biology > 196-210

The study of mobile element evolution yields valuable insights into the mechanism and history of genome rearrangement, and can help answer questions about our evolutionary history. However, because the mammalian genome contains millions of copies of mobile elements exhibiting a complex evolutionary history, traditional phylogenetic methods are ill-suited to reconstructing their history. New phylogenetic...

chapter

3-D reconstruction of multipart self-occluding objects

Nebojsa Jojic, Jin Gu, Helen C. Shen, Thomas Huang

Lecture Notes in Computer Science > Computer Vision — ACCV'98 > 455-462

In this paper we present a method for reconstruction of multipart objects from several arbitrary views using deformable superquadrics as the models of the object's parts. Two visual cues are used: occluding contours and stereo (possibly aided by projected patterns). The object can be relatively complex and can exhibit numerous self occlusions from some or all views. Our preliminary experiments on...

chapter

Learning Montages of Transformed Latent Images as Representations of Objects That Change in Appearance

Chris Pal, Brendan J. Frey, Nebojsa Jojic

Lecture Notes in Computer Science > Computer Vision — ECCV 2002 > Calibration / Active and Real-Time and Robot Vision / Image and Video Indexing / Medical Image Understanding / Vision Systems / Engineering and Evaluations / Statistical Learning > 715-731

This paper introduces a novel probabilistic model for representing objects that change in appearance as a result of changes in pose, due to small deformations of their sub-parts and the relative spatial transformation of sub-parts of the object. We call the model a probabilistic montage. The model is based upon the idea that an image can be represented as a montage using many, small transformed and...

chapter

Variable Selection through Correlation Sifting

Jim C. Huang, Nebojsa Jojic

Lecture Notes in Computer Science > Research in Computational Molecular Biology > 106-123

Many applications of computational biology require a variable selection procedure to sift through a large number of input variables and select some smaller number that influence a target variable of interest. For example, in virology, only some small number of viral protein fragments influence the nature of the immune response during viral infection. Due to the large number of variables to be considered,...

chapter

Nonparametric Combinatorial Sequence Models

Fabian L. Wauthier, Michael I. Jordan, Nebojsa Jojic

Lecture Notes in Computer Science > Research in Computational Molecular Biology > 516-530

This work considers biological sequences that exhibit combinatorial structures in their composition: groups of positions of the aligned sequences are “linked” and covary as one unit across sequences. If multiple such groups exist, complex interactions can emerge between them. Sequences of this kind arise frequently in biology but methodologies for analyzing them are still being developed. This paper...

chapter

Object Recognition with Hierarchical Stel Models

Alessandro Perina, Nebojsa Jojic, Umberto Castellani, Marco Cristani, more

Lecture Notes in Computer Science > Computer Vision – ECCV 2010 > Visual Learning > 15-28

We propose a new generative model, and a new image similarity kernel based on a linked hierarchy of probabilistic segmentations. The model is used to efficiently segment multiple images into a consistent set of image regions. The segmentations are provided at several levels of granularity and links among them are automatically provided. Model training and inference in it is faster than most local...

chapter

Tamper-Resistant Biometric IDs

Darko Kirovski, Nebojša Jojić, Gavin Jancke

ISSE 2004 — Securing Electronic Business Processes > Technology > 160-175

We present FaceCerts, a simple, inexpensive, and cryptographically secure identity certification system. A FaceCert is a printout of person’s portrait photo, an arbitrary textual message, and a 2-D color barcode which encodes an RSA signature of the message hash and the compressed representation of the face encompassed by the photo. The signature is created using the private key of the party issuing...

article

Capturing Spatial Interdependence in Image Features: The Counting Grid, an Epitomic Representation for Bags of Features

Alessandro Perina, Nebojsa Jojic

IEEE Transactions on Pattern Analysis and Machine Intelligence > 2015 > 37 > 12 > 2374 - 2387

In recent scene recognition research images or large image regions are often represented as disorganized “bags” of features which can then be analyzed using models originally developed to capture co-variation of word counts in text. However, image feature counts are likely to be constrained in different ways than word counts in text. For example, as a camera pans upwards from a building entrance over...

chapter

Capturing Layers in Image Collections with Componential Models: From the Layered Epitome to the Componential Counting Grid

Alessandro Perina, Nebojsa Jojic

2013 IEEE Conference on Computer Vision and Pattern Recognition > 500 - 507

2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Recently, the Counting Grid (CG) model was developed to represent each input image as a point in a large grid of feature counts. This latent point is a corner of a window of grid points which are all uniformly combined to match the (normalized) feature counts in the image. Being a bag of word model with spatial layout in the latent space, the CG model has superior handling of field of view changes...

article

Free Energy Score Spaces: Using Generative Information in Discriminative Classifiers

Alessandro Perina, Marco Cristani, Umberto Castellani, Vittorio Murino, more

IEEE Transactions on Pattern Analysis and Machine Intelligence > 2012 > 34 > 7 > 1249 - 1262

A score function induced by a generative model of the data can provide a feature vector of a fixed dimension for each data sample. Data samples themselves may be of differing lengths (e.g., speech segments or other sequential data), but as a score function is based on the properties of the data generation process, it produces a fixed-length vector in a highly informative space, typically referred...

article

Stel Component Analysis: Joint Segmentation, Modeling and Recognition of Objects Classes

Alessandro Perina, Nebojsa Jojic, Marco Cristani, Vittorio Murino

International Journal of Computer Vision > 2012 > 100 > 3 > 241-260

Models that captures the common structure of an object class have appeared few years ago in the literature (Jojic and Caspi in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 212–219, 2004; Winn and Jojic in Proceedings of International Conference on Computer Vision (ICCV), pp. 756–763, 2005); they are often referred as “stel models.” Their main...

Publication date

Set your own date range

Publication type

book (17)
article (11)

Keywords

FEATURE EXTRACTION (4)
COMPUTATIONAL MODELING (3)
DATA MODELS (3)
EM ALGORITHM (2)
EPITOME (2)
NEURAL NETWORKS (2)
TRAINING (2)
$$\ELL ^{0}$$ ℓ 0 -INDUCED SPARSE SUBSPACE CLUSTERING (1)
ANTIGENIC VARIATION (1)
BAG OF FEATURES SPATIAL LAYOUT SCENE ANALYSIS BAG OF FEATURES SPATIAL LAYOUT SCENE ANALYSIS B (1)
BAG OF WORDS (1)
BAG OF WORDS AND BEYOND (1)
BAG OF WORDS CLASSIFICATION (1)
BAG OF WORDS CLUSTERING (1)
BINDING PREDICTION (1)
BIOLOGICAL SYSTEM MODELING (1)
BUILDINGS (1)
CAMERAS (1)
CHINESE RESTAURANT FRANCHISE (1)
CHINESE RESTAURANT PROCESS (1)
CLASSIFICATION. (1)
CLUSTERING (1)
COGNITION (1)
COMPUTATIONAL MODELS (1)
COMPUTER VISION (1)
CONTENT-BASED RETRIEVAL (1)
DATA VISUALIZATION (1)
DIMENSIONALITY REDUCTION (1)
ENTROPY (1)
GENE EXPRESSION MATRIX (1)
GENE SELECTION (1)
GENERATIVE MODEL (1)
GENERATIVE MODELS (1)
HLA (1)
HUMAN LEUKOCYTE ANTIGEN (1)
HYBRID GENERATIVE/DISCRIMINATIVE PARADIGM (1)
IMAGE RECONSTRUCTION (1)
IMAGE RESTORATION (1)
INPAINTING (1)
LAYOUT (1)
MACHINE LEARNING (1)
MAJOR HISTOCOMPATIBILITY COMPLEX (1)
MALARIA (1)
MARKOV PROCESSES (1)
MHC BINDING (1)
MISSING DATA (1)
MIXTURE MODELS (1)
MODEL AVERAGING (1)
NONPARAMETRIC REGRESSION (1)
OBJECT CLASS MODELING (1)
OBJECT REMOVAL (1)
PATCH (1)
PATTERN RECOGNITION (1)
PEPTIDE BINDING (1)
PLACE RECOGNITION (1)
PLASMODIUM FALCIPARUM (1)
PREDICTIONS (1)
PROXIMAL GRADIENT DESCENT (1)
RECOGNITION (1)
SCENE UNDERSTANDING (1)
SEGMENTATION (1)
SEQUENCE MODELS (1)
SPARSE SIMILARITY MATRIX (1)
STATISTICAL LEARNING (1)
SUBSPACE-SPARSE REPRESENTATION (1)
SUPER-RESOLUTION (1)
TCA (1)
VAR GENES (1)
VARIATIONAL FREE ENERGY (1)
VARIATIONAL TECHNIQUE (1)
VECTORS (1)
VIDEO FAST FORWARD (1)
VIDEO SUMMARIZATION (1)
VISUALIZATION (1)
more

Data set

Springer (17)
ieee (7)
Elsevier (4)

INFONA - science communication portal

Search results for: Nebojsa Jojic

Subspace Learning by $$\ell ^{0}$$ ℓ0 -Induced Sparsity

Summarization and Classification of Wearable Camera Streams by Learning the Distributions over Deep Features of Out-of-Sample Image Sequences

ER3: A Unified Framework for Event Retrieval, Recognition and Recounting

Traveling on discrete embeddings of gene expression

Shift-Invariant Adaptive Double Threading: Learning MHC II - Peptide Binding

Audio-Video Sensor Fusion with Probabilistic Graphical Models

On analysis of cloth drape range data

Constructing Treatment Portfolios Using Affinity Propagation

A Generative Model of Dense Optical Flow in Layers

Reconstructing the Phylogeny of Mobile Elements

3-D reconstruction of multipart self-occluding objects

Learning Montages of Transformed Latent Images as Representations of Objects That Change in Appearance

Variable Selection through Correlation Sifting

Nonparametric Combinatorial Sequence Models

Object Recognition with Hierarchical Stel Models

Tamper-Resistant Biometric IDs

Capturing Spatial Interdependence in Image Features: The Counting Grid, an Epitomic Representation for Bags of Features

Capturing Layers in Image Collections with Componential Models: From the Layered Epitome to the Componential Counting Grid

Free Energy Score Spaces: Using Generative Information in Discriminative Classifiers

Stel Component Analysis: Joint Segmentation, Modeling and Recognition of Objects Classes

Filter options

Publication date

Publication type

Keywords

Data set

Journal

INFONA - science communication portal

Search results for: Nebojsa Jojic

Add recipient

Sending message cancelled

Are you sure you want to cancel sending this message?

Send message

Filter options

Publication date

Date range setting

Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.

Publication type

Keywords

Data set

Journal

Reporting an error / abuse

Sending the report failed

Accessibility options