Sorry, you need to enable JavaScript to visit this website.

Image, Video, and Multidimensional Signal Processing

Mining Representative Actions for Actor Identification


Previous works on actor identification mainly focused on static
features based on face identification and costume detection,
without considering the abundant dynamic information contained
in videos. In this paper, we propose a novel method
to mine representative actions of each actor, and show the remarkable
power of such actions for actor identification task.
Videos are firstly divided into shots and represented by BoW
based on spatial-temporal features. Then we integrate the prototype

Paper Details

Authors:
Submitted On:
21 March 2016 - 6:37pm
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

Mining Representative Actions for Actor Identification - wlxie.pdf

(290 downloads)

Subscribe

[1] , "Mining Representative Actions for Actor Identification", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/938. Accessed: Aug. 21, 2018.
@article{938-16,
url = {http://sigport.org/938},
author = { },
publisher = {IEEE SigPort},
title = {Mining Representative Actions for Actor Identification},
year = {2016} }
TY - EJOUR
T1 - Mining Representative Actions for Actor Identification
AU -
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/938
ER -
. (2016). Mining Representative Actions for Actor Identification. IEEE SigPort. http://sigport.org/938
, 2016. Mining Representative Actions for Actor Identification. Available at: http://sigport.org/938.
. (2016). "Mining Representative Actions for Actor Identification." Web.
1. . Mining Representative Actions for Actor Identification [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/938

NONCONVEX COMPRESSIVE SENSING RECONSTRUCTION FOR TENSOR USING STRUCTURES IN MODES


poster.pdf

PDF icon poster.pdf (523 downloads)

Paper Details

Authors:
Xin Ding, Wei Chen, Ian Wassell
Submitted On:
21 March 2016 - 6:33am
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

poster.pdf

(523 downloads)

Subscribe

[1] Xin Ding, Wei Chen, Ian Wassell, "NONCONVEX COMPRESSIVE SENSING RECONSTRUCTION FOR TENSOR USING STRUCTURES IN MODES", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/921. Accessed: Aug. 21, 2018.
@article{921-16,
url = {http://sigport.org/921},
author = {Xin Ding; Wei Chen; Ian Wassell },
publisher = {IEEE SigPort},
title = {NONCONVEX COMPRESSIVE SENSING RECONSTRUCTION FOR TENSOR USING STRUCTURES IN MODES},
year = {2016} }
TY - EJOUR
T1 - NONCONVEX COMPRESSIVE SENSING RECONSTRUCTION FOR TENSOR USING STRUCTURES IN MODES
AU - Xin Ding; Wei Chen; Ian Wassell
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/921
ER -
Xin Ding, Wei Chen, Ian Wassell. (2016). NONCONVEX COMPRESSIVE SENSING RECONSTRUCTION FOR TENSOR USING STRUCTURES IN MODES. IEEE SigPort. http://sigport.org/921
Xin Ding, Wei Chen, Ian Wassell, 2016. NONCONVEX COMPRESSIVE SENSING RECONSTRUCTION FOR TENSOR USING STRUCTURES IN MODES. Available at: http://sigport.org/921.
Xin Ding, Wei Chen, Ian Wassell. (2016). "NONCONVEX COMPRESSIVE SENSING RECONSTRUCTION FOR TENSOR USING STRUCTURES IN MODES." Web.
1. Xin Ding, Wei Chen, Ian Wassell. NONCONVEX COMPRESSIVE SENSING RECONSTRUCTION FOR TENSOR USING STRUCTURES IN MODES [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/921

Manga-Specific Features and Latent Style Model for Manga Style Analysis


A latent style model describing manga styles based on the proposed manga-specific features is constructed to facilitate novel style-based applications. Two manga-specific features, i.e., screentone features showing texture and shade, and panel features showing panel arrangement, are firstly proposed to describe manga pages. Based on the latent Dirichlet allocation technique, we discover latent style elements embedded in manga documents, which are described by visual words derived from manga-specific features.

Paper Details

Authors:
Submitted On:
20 March 2016 - 8:45pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Manga-Specific Features and Latent Style Model for Manga Style Analysis.pdf

(276 downloads)

Subscribe

[1] , "Manga-Specific Features and Latent Style Model for Manga Style Analysis", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/896. Accessed: Aug. 21, 2018.
@article{896-16,
url = {http://sigport.org/896},
author = { },
publisher = {IEEE SigPort},
title = {Manga-Specific Features and Latent Style Model for Manga Style Analysis},
year = {2016} }
TY - EJOUR
T1 - Manga-Specific Features and Latent Style Model for Manga Style Analysis
AU -
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/896
ER -
. (2016). Manga-Specific Features and Latent Style Model for Manga Style Analysis. IEEE SigPort. http://sigport.org/896
, 2016. Manga-Specific Features and Latent Style Model for Manga Style Analysis. Available at: http://sigport.org/896.
. (2016). "Manga-Specific Features and Latent Style Model for Manga Style Analysis." Web.
1. . Manga-Specific Features and Latent Style Model for Manga Style Analysis [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/896

News Story Clustering with Fisher Embedding


An automatic news story clustering system is presented to facilitate efficient news browsing and summarization. We describe news content by considering both what objects appear and how these objects move in news stories. With Fisher embedding, we respectively encode local features, semantics features, and dense trajectories as Fisher vectors, based on which similarity between news stories can be well evaluated and thus better clustering performance can be obtained.

Paper Details

Authors:
Submitted On:
20 March 2016 - 8:46pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

News Story Clustering with Fisher Embedding.pdf

(298 downloads)

Subscribe

[1] , "News Story Clustering with Fisher Embedding", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/895. Accessed: Aug. 21, 2018.
@article{895-16,
url = {http://sigport.org/895},
author = { },
publisher = {IEEE SigPort},
title = {News Story Clustering with Fisher Embedding},
year = {2016} }
TY - EJOUR
T1 - News Story Clustering with Fisher Embedding
AU -
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/895
ER -
. (2016). News Story Clustering with Fisher Embedding. IEEE SigPort. http://sigport.org/895
, 2016. News Story Clustering with Fisher Embedding. Available at: http://sigport.org/895.
. (2016). "News Story Clustering with Fisher Embedding." Web.
1. . News Story Clustering with Fisher Embedding [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/895

Intrinsic Two-Dimensional Local Structures for Micro-Expression Recognition


Intrinsic two-dimensional local structures

An elapsed facial emotion involves changes of facial contour due to the motions (such as contraction or stretch) of facial muscles located at the eyes, nose, lips and etc. Thus, the important information such as corners of facial contours that are located in various regions of the face are crucial to the recognition of facial expressions, and even more apparent for micro-expressions. In this paper, we propose the first known notion of employing intrinsic two-dimensional (i2D) local structures to represent these features for micro-expression recognition.

Paper Details

Authors:
Yee-Hui Oh, Anh Cat Le Ngo, Raphael Chung-Wei Phan, John See, Huo-Chong Ling
Submitted On:
20 March 2016 - 12:16pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

mi2dbp_icassp2016.pdf

(332 downloads)

Subscribe

[1] Yee-Hui Oh, Anh Cat Le Ngo, Raphael Chung-Wei Phan, John See, Huo-Chong Ling, "Intrinsic Two-Dimensional Local Structures for Micro-Expression Recognition", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/886. Accessed: Aug. 21, 2018.
@article{886-16,
url = {http://sigport.org/886},
author = {Yee-Hui Oh; Anh Cat Le Ngo; Raphael Chung-Wei Phan; John See; Huo-Chong Ling },
publisher = {IEEE SigPort},
title = {Intrinsic Two-Dimensional Local Structures for Micro-Expression Recognition},
year = {2016} }
TY - EJOUR
T1 - Intrinsic Two-Dimensional Local Structures for Micro-Expression Recognition
AU - Yee-Hui Oh; Anh Cat Le Ngo; Raphael Chung-Wei Phan; John See; Huo-Chong Ling
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/886
ER -
Yee-Hui Oh, Anh Cat Le Ngo, Raphael Chung-Wei Phan, John See, Huo-Chong Ling. (2016). Intrinsic Two-Dimensional Local Structures for Micro-Expression Recognition. IEEE SigPort. http://sigport.org/886
Yee-Hui Oh, Anh Cat Le Ngo, Raphael Chung-Wei Phan, John See, Huo-Chong Ling, 2016. Intrinsic Two-Dimensional Local Structures for Micro-Expression Recognition. Available at: http://sigport.org/886.
Yee-Hui Oh, Anh Cat Le Ngo, Raphael Chung-Wei Phan, John See, Huo-Chong Ling. (2016). "Intrinsic Two-Dimensional Local Structures for Micro-Expression Recognition." Web.
1. Yee-Hui Oh, Anh Cat Le Ngo, Raphael Chung-Wei Phan, John See, Huo-Chong Ling. Intrinsic Two-Dimensional Local Structures for Micro-Expression Recognition [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/886

Spatio-Temporal Mid-Level Feature Bank for Action Recognition in Low Quality Video


Spatio-Temporal Mid-level Feature Bank

It is a great challenge to perform high level recognition tasks on videos that are poor in quality. In this paper, we propose a new spatio-temporal mid-level (STEM) feature bank for recognizing human actions in low quality videos. The feature bank comprises of a trio of local spatio-temporal features, i.e. shape, motion and textures, which respectively encode structural, dynamic and statistical information in video. These features are encoded into mid-level representations and aggregated to construct STEM.

Paper Details

Authors:
Saimunur Rahman, John See
Submitted On:
20 March 2016 - 11:22am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

stem_icassp2016.pdf

(354 downloads)

Subscribe

[1] Saimunur Rahman, John See, "Spatio-Temporal Mid-Level Feature Bank for Action Recognition in Low Quality Video", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/884. Accessed: Aug. 21, 2018.
@article{884-16,
url = {http://sigport.org/884},
author = {Saimunur Rahman; John See },
publisher = {IEEE SigPort},
title = {Spatio-Temporal Mid-Level Feature Bank for Action Recognition in Low Quality Video},
year = {2016} }
TY - EJOUR
T1 - Spatio-Temporal Mid-Level Feature Bank for Action Recognition in Low Quality Video
AU - Saimunur Rahman; John See
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/884
ER -
Saimunur Rahman, John See. (2016). Spatio-Temporal Mid-Level Feature Bank for Action Recognition in Low Quality Video. IEEE SigPort. http://sigport.org/884
Saimunur Rahman, John See, 2016. Spatio-Temporal Mid-Level Feature Bank for Action Recognition in Low Quality Video. Available at: http://sigport.org/884.
Saimunur Rahman, John See. (2016). "Spatio-Temporal Mid-Level Feature Bank for Action Recognition in Low Quality Video." Web.
1. Saimunur Rahman, John See. Spatio-Temporal Mid-Level Feature Bank for Action Recognition in Low Quality Video [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/884

Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics


Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics

In this paper, we present Discriminant Correlation Analysis (DCA), a feature level fusion technique that incorporates the class associations in correlation analysis of the feature sets. DCA performs an effective feature fusion by maximizing the pair-wise correlations across the two feature sets, and at the same time, eliminating the between-class correlations and restricting the correlations to be within classes.

[1] Mohammad Haghighat, Mohamed Abdel-Mottaleb, Wadee Alhalabi, "Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/828. Accessed: Aug. 21, 2018.
@article{828-16,
url = {http://sigport.org/828},
author = {Mohammad Haghighat; Mohamed Abdel-Mottaleb; Wadee Alhalabi },
publisher = {IEEE SigPort},
title = {Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics},
year = {2016} }
TY - EJOUR
T1 - Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics
AU - Mohammad Haghighat; Mohamed Abdel-Mottaleb; Wadee Alhalabi
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/828
ER -
Mohammad Haghighat, Mohamed Abdel-Mottaleb, Wadee Alhalabi. (2016). Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics. IEEE SigPort. http://sigport.org/828
Mohammad Haghighat, Mohamed Abdel-Mottaleb, Wadee Alhalabi, 2016. Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics. Available at: http://sigport.org/828.
Mohammad Haghighat, Mohamed Abdel-Mottaleb, Wadee Alhalabi. (2016). "Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics." Web.
1. Mohammad Haghighat, Mohamed Abdel-Mottaleb, Wadee Alhalabi. Discriminant Correlation Analysis for Feature Level Fusion with Application to Multimodal Biometrics [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/828

Dcitionary Learning for Poisson Compressed Sensing


Imaging techniques involve counting of photons striking a detector. Due to fluctuations in the counting process, the measured photon counts are known to be corrupted by Poisson noise. In this paper, we propose a blind dictionary learning framework for the reconstruction of photographic image data from Poisson corrupted measurements acquired by a \emph{compressive} camera.

Paper Details

Authors:
Sukanya Patil, Rajbabu Velmurugan and Ajit Rajwade
Submitted On:
19 March 2016 - 1:06pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP_final_poster.pdf

(267 downloads)

Subscribe

[1] Sukanya Patil, Rajbabu Velmurugan and Ajit Rajwade, "Dcitionary Learning for Poisson Compressed Sensing", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/826. Accessed: Aug. 21, 2018.
@article{826-16,
url = {http://sigport.org/826},
author = {Sukanya Patil; Rajbabu Velmurugan and Ajit Rajwade },
publisher = {IEEE SigPort},
title = {Dcitionary Learning for Poisson Compressed Sensing},
year = {2016} }
TY - EJOUR
T1 - Dcitionary Learning for Poisson Compressed Sensing
AU - Sukanya Patil; Rajbabu Velmurugan and Ajit Rajwade
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/826
ER -
Sukanya Patil, Rajbabu Velmurugan and Ajit Rajwade. (2016). Dcitionary Learning for Poisson Compressed Sensing. IEEE SigPort. http://sigport.org/826
Sukanya Patil, Rajbabu Velmurugan and Ajit Rajwade, 2016. Dcitionary Learning for Poisson Compressed Sensing. Available at: http://sigport.org/826.
Sukanya Patil, Rajbabu Velmurugan and Ajit Rajwade. (2016). "Dcitionary Learning for Poisson Compressed Sensing." Web.
1. Sukanya Patil, Rajbabu Velmurugan and Ajit Rajwade. Dcitionary Learning for Poisson Compressed Sensing [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/826

Tensor Completion via Functional Smooth Component Deflation

Paper Details

Authors:
Tatsuya Yokota, Andrzej Cichocki
Submitted On:
19 March 2016 - 5:46am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP2016_v2.pdf

(319 downloads)

Subscribe

[1] Tatsuya Yokota, Andrzej Cichocki, "Tensor Completion via Functional Smooth Component Deflation", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/795. Accessed: Aug. 21, 2018.
@article{795-16,
url = {http://sigport.org/795},
author = {Tatsuya Yokota; Andrzej Cichocki },
publisher = {IEEE SigPort},
title = {Tensor Completion via Functional Smooth Component Deflation},
year = {2016} }
TY - EJOUR
T1 - Tensor Completion via Functional Smooth Component Deflation
AU - Tatsuya Yokota; Andrzej Cichocki
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/795
ER -
Tatsuya Yokota, Andrzej Cichocki. (2016). Tensor Completion via Functional Smooth Component Deflation. IEEE SigPort. http://sigport.org/795
Tatsuya Yokota, Andrzej Cichocki, 2016. Tensor Completion via Functional Smooth Component Deflation. Available at: http://sigport.org/795.
Tatsuya Yokota, Andrzej Cichocki. (2016). "Tensor Completion via Functional Smooth Component Deflation." Web.
1. Tatsuya Yokota, Andrzej Cichocki. Tensor Completion via Functional Smooth Component Deflation [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/795

DICTIONARY LEARNING FOR POISSON COMPRESSED SENSING


Imaging techniques involve counting of photons striking a detector.
Due to fluctuations in the counting process, the measured
photon counts are known to be corrupted by Poisson
noise. In this paper, we propose a blind dictionary learning
framework for the reconstruction of photographic image data
from Poisson corrupted measurements acquired by a compressive
camera. We exploit the inherent non-negativity of the
data by modeling the dictionary as well as the sparse dictionary
coefficients as non-negative entities, and infer these directly

Paper Details

Authors:
Sukanya Patil, Rajbabu Velmurugan, Ajit Rajwade
Submitted On:
19 March 2016 - 4:43am
Short Link:
Type:
Event:

Document Files

ICASSP_poster.pdf

(899 downloads)

Subscribe

[1] Sukanya Patil, Rajbabu Velmurugan, Ajit Rajwade, "DICTIONARY LEARNING FOR POISSON COMPRESSED SENSING", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/791. Accessed: Aug. 21, 2018.
@article{791-16,
url = {http://sigport.org/791},
author = {Sukanya Patil; Rajbabu Velmurugan; Ajit Rajwade },
publisher = {IEEE SigPort},
title = {DICTIONARY LEARNING FOR POISSON COMPRESSED SENSING},
year = {2016} }
TY - EJOUR
T1 - DICTIONARY LEARNING FOR POISSON COMPRESSED SENSING
AU - Sukanya Patil; Rajbabu Velmurugan; Ajit Rajwade
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/791
ER -
Sukanya Patil, Rajbabu Velmurugan, Ajit Rajwade. (2016). DICTIONARY LEARNING FOR POISSON COMPRESSED SENSING. IEEE SigPort. http://sigport.org/791
Sukanya Patil, Rajbabu Velmurugan, Ajit Rajwade, 2016. DICTIONARY LEARNING FOR POISSON COMPRESSED SENSING. Available at: http://sigport.org/791.
Sukanya Patil, Rajbabu Velmurugan, Ajit Rajwade. (2016). "DICTIONARY LEARNING FOR POISSON COMPRESSED SENSING." Web.
1. Sukanya Patil, Rajbabu Velmurugan, Ajit Rajwade. DICTIONARY LEARNING FOR POISSON COMPRESSED SENSING [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/791

Pages