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

Image/Video Processing

MULTI-VIEW VISUAL SPEECH RECOGNITION BASED ON MULTI TASK LEARNING


Visual speech recognition (VSR), also known as lip reading is a task that recognizes words or phrases using video clips of lip movement. Traditional VSR methods are limited in that they are based mostly on VSR of frontal-view facial movement. However, for practical application, VSR should include lip movement from all angles. In this paper, we propose a pose-invariant network which can recognize words spoken from any arbitrary view input.

Paper Details

Authors:
HouJeung Han , Sunghun Kang and Chang D. Yoo
Submitted On:
15 September 2017 - 3:48am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster

(8 downloads)

Keywords

Subscribe

[1] HouJeung Han , Sunghun Kang and Chang D. Yoo, "MULTI-VIEW VISUAL SPEECH RECOGNITION BASED ON MULTI TASK LEARNING", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2092. Accessed: Oct. 19, 2017.
@article{2092-17,
url = {http://sigport.org/2092},
author = {HouJeung Han ; Sunghun Kang and Chang D. Yoo },
publisher = {IEEE SigPort},
title = {MULTI-VIEW VISUAL SPEECH RECOGNITION BASED ON MULTI TASK LEARNING},
year = {2017} }
TY - EJOUR
T1 - MULTI-VIEW VISUAL SPEECH RECOGNITION BASED ON MULTI TASK LEARNING
AU - HouJeung Han ; Sunghun Kang and Chang D. Yoo
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2092
ER -
HouJeung Han , Sunghun Kang and Chang D. Yoo. (2017). MULTI-VIEW VISUAL SPEECH RECOGNITION BASED ON MULTI TASK LEARNING. IEEE SigPort. http://sigport.org/2092
HouJeung Han , Sunghun Kang and Chang D. Yoo, 2017. MULTI-VIEW VISUAL SPEECH RECOGNITION BASED ON MULTI TASK LEARNING. Available at: http://sigport.org/2092.
HouJeung Han , Sunghun Kang and Chang D. Yoo. (2017). "MULTI-VIEW VISUAL SPEECH RECOGNITION BASED ON MULTI TASK LEARNING." Web.
1. HouJeung Han , Sunghun Kang and Chang D. Yoo. MULTI-VIEW VISUAL SPEECH RECOGNITION BASED ON MULTI TASK LEARNING [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2092

LONG-TERM OBJECT TRACKING BASED ON SIAMESE NETWORK

Paper Details

Authors:
YuehuanWang, Xiaoyun Yan
Submitted On:
15 September 2017 - 3:46am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

LONG-TERM OBJECT TRACKING BASED ON SIAMESE NETWORK .pdf

(14 downloads)

Keywords

Subscribe

[1] YuehuanWang, Xiaoyun Yan, "LONG-TERM OBJECT TRACKING BASED ON SIAMESE NETWORK", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2089. Accessed: Oct. 19, 2017.
@article{2089-17,
url = {http://sigport.org/2089},
author = {YuehuanWang; Xiaoyun Yan },
publisher = {IEEE SigPort},
title = {LONG-TERM OBJECT TRACKING BASED ON SIAMESE NETWORK},
year = {2017} }
TY - EJOUR
T1 - LONG-TERM OBJECT TRACKING BASED ON SIAMESE NETWORK
AU - YuehuanWang; Xiaoyun Yan
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2089
ER -
YuehuanWang, Xiaoyun Yan. (2017). LONG-TERM OBJECT TRACKING BASED ON SIAMESE NETWORK. IEEE SigPort. http://sigport.org/2089
YuehuanWang, Xiaoyun Yan, 2017. LONG-TERM OBJECT TRACKING BASED ON SIAMESE NETWORK. Available at: http://sigport.org/2089.
YuehuanWang, Xiaoyun Yan. (2017). "LONG-TERM OBJECT TRACKING BASED ON SIAMESE NETWORK." Web.
1. YuehuanWang, Xiaoyun Yan. LONG-TERM OBJECT TRACKING BASED ON SIAMESE NETWORK [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2089

stereo-plus-depth imaging system

Paper Details

Authors:
Cheolkon Jung, Joongkyu Kim
Submitted On:
15 September 2017 - 3:41am
Short Link:
Type:
Paper Code:

Document Files

ICIP2017

(13 downloads)

Keywords

Subscribe

[1] Cheolkon Jung, Joongkyu Kim, "stereo-plus-depth imaging system", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2088. Accessed: Oct. 19, 2017.
@article{2088-17,
url = {http://sigport.org/2088},
author = {Cheolkon Jung; Joongkyu Kim },
publisher = {IEEE SigPort},
title = {stereo-plus-depth imaging system},
year = {2017} }
TY - EJOUR
T1 - stereo-plus-depth imaging system
AU - Cheolkon Jung; Joongkyu Kim
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2088
ER -
Cheolkon Jung, Joongkyu Kim. (2017). stereo-plus-depth imaging system. IEEE SigPort. http://sigport.org/2088
Cheolkon Jung, Joongkyu Kim, 2017. stereo-plus-depth imaging system. Available at: http://sigport.org/2088.
Cheolkon Jung, Joongkyu Kim. (2017). "stereo-plus-depth imaging system." Web.
1. Cheolkon Jung, Joongkyu Kim. stereo-plus-depth imaging system [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2088

ICIP2017_Incremental zero-shot learning based on attributes for image classification


Instead of assuming a closed-world environment comprising a fixed number of objects, modern pattern recognition systems need to recognize outliers, identify anomalies, or discover entirely new objects, which is known as zero-shot object recognition. However, many existing zero-shot learning methods are not efficient enough to incrementally update themselves with new samples mixed with known or novel class labels. In this paper, we propose an incremental zero-shot learning framework (IIAP/QR) based on indirect-attribute-prediction (IAP) model. Firstly, a fast incremental

Paper Details

Authors:
Nan Xue, Yi Wang, Xin Fan, Maomao Min
Submitted On:
15 September 2017 - 3:07am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICIP2017 conference slide of paper 1688

(15 downloads)

Keywords

Additional Categories

Subscribe

[1] Nan Xue, Yi Wang, Xin Fan, Maomao Min, "ICIP2017_Incremental zero-shot learning based on attributes for image classification", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2087. Accessed: Oct. 19, 2017.
@article{2087-17,
url = {http://sigport.org/2087},
author = {Nan Xue; Yi Wang; Xin Fan; Maomao Min },
publisher = {IEEE SigPort},
title = {ICIP2017_Incremental zero-shot learning based on attributes for image classification},
year = {2017} }
TY - EJOUR
T1 - ICIP2017_Incremental zero-shot learning based on attributes for image classification
AU - Nan Xue; Yi Wang; Xin Fan; Maomao Min
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2087
ER -
Nan Xue, Yi Wang, Xin Fan, Maomao Min. (2017). ICIP2017_Incremental zero-shot learning based on attributes for image classification. IEEE SigPort. http://sigport.org/2087
Nan Xue, Yi Wang, Xin Fan, Maomao Min, 2017. ICIP2017_Incremental zero-shot learning based on attributes for image classification. Available at: http://sigport.org/2087.
Nan Xue, Yi Wang, Xin Fan, Maomao Min. (2017). "ICIP2017_Incremental zero-shot learning based on attributes for image classification." Web.
1. Nan Xue, Yi Wang, Xin Fan, Maomao Min. ICIP2017_Incremental zero-shot learning based on attributes for image classification [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2087

ICIP 2017-ROBUST ELLIPSE DETECTION VIA ARC SEGMENTATION AND CLASSIFICATION

Paper Details

Authors:
Huixu Dong, Dilip K. Prasad, I-Ming Chen
Submitted On:
15 September 2017 - 2:04am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2017-ICIP1701

(18 downloads)

Keywords

Subscribe

[1] Huixu Dong, Dilip K. Prasad, I-Ming Chen, " ICIP 2017-ROBUST ELLIPSE DETECTION VIA ARC SEGMENTATION AND CLASSIFICATION ", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2086. Accessed: Oct. 19, 2017.
@article{2086-17,
url = {http://sigport.org/2086},
author = {Huixu Dong; Dilip K. Prasad; I-Ming Chen },
publisher = {IEEE SigPort},
title = { ICIP 2017-ROBUST ELLIPSE DETECTION VIA ARC SEGMENTATION AND CLASSIFICATION },
year = {2017} }
TY - EJOUR
T1 - ICIP 2017-ROBUST ELLIPSE DETECTION VIA ARC SEGMENTATION AND CLASSIFICATION
AU - Huixu Dong; Dilip K. Prasad; I-Ming Chen
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2086
ER -
Huixu Dong, Dilip K. Prasad, I-Ming Chen. (2017). ICIP 2017-ROBUST ELLIPSE DETECTION VIA ARC SEGMENTATION AND CLASSIFICATION . IEEE SigPort. http://sigport.org/2086
Huixu Dong, Dilip K. Prasad, I-Ming Chen, 2017. ICIP 2017-ROBUST ELLIPSE DETECTION VIA ARC SEGMENTATION AND CLASSIFICATION . Available at: http://sigport.org/2086.
Huixu Dong, Dilip K. Prasad, I-Ming Chen. (2017). " ICIP 2017-ROBUST ELLIPSE DETECTION VIA ARC SEGMENTATION AND CLASSIFICATION ." Web.
1. Huixu Dong, Dilip K. Prasad, I-Ming Chen. ICIP 2017-ROBUST ELLIPSE DETECTION VIA ARC SEGMENTATION AND CLASSIFICATION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2086

CONTENT ADAPTIVE VIDEO SUMMARIZATION USING SPATIO-TEMPORAL FEATURES


This paper proposes a video summarization method based on novel spatio-temporal features that combine motion magnitude, object class prediction, and saturation. Motion magnitude measures how much motion there is in a video. Object class prediction provides information about an object in a video. Saturation measures the colorfulness of a video. Convolutional neural networks (CNNs) are incorporated for object class prediction. The sum of the normalized features per shot are ranked in descending order, and the summary is determined by the highest ranking shots.

Paper Details

Authors:
Submitted On:
15 September 2017 - 12:29am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP_Poster.pdf

(43 downloads)

Keywords

Subscribe

[1] , "CONTENT ADAPTIVE VIDEO SUMMARIZATION USING SPATIO-TEMPORAL FEATURES", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2080. Accessed: Oct. 19, 2017.
@article{2080-17,
url = {http://sigport.org/2080},
author = { },
publisher = {IEEE SigPort},
title = {CONTENT ADAPTIVE VIDEO SUMMARIZATION USING SPATIO-TEMPORAL FEATURES},
year = {2017} }
TY - EJOUR
T1 - CONTENT ADAPTIVE VIDEO SUMMARIZATION USING SPATIO-TEMPORAL FEATURES
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2080
ER -
. (2017). CONTENT ADAPTIVE VIDEO SUMMARIZATION USING SPATIO-TEMPORAL FEATURES. IEEE SigPort. http://sigport.org/2080
, 2017. CONTENT ADAPTIVE VIDEO SUMMARIZATION USING SPATIO-TEMPORAL FEATURES. Available at: http://sigport.org/2080.
. (2017). "CONTENT ADAPTIVE VIDEO SUMMARIZATION USING SPATIO-TEMPORAL FEATURES." Web.
1. . CONTENT ADAPTIVE VIDEO SUMMARIZATION USING SPATIO-TEMPORAL FEATURES [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2080

Multiview Pedestrian Localisation via a Prime Candidate Chart


A sound way to localize occluded people is to project the foregrounds from multiple camera views to a reference view by homographies and find the foreground intersections. However, this may give rise to phantoms due to foreground intersections from different people. In this paper, each intersection region is warped back to the original camera view and is associated with a candidate box of the average pedestrians’ size at that location. Then a joint occupancy likelihood is calculated for each intersection region.

Paper Details

Authors:
Ming Xu, Jeremy S. Smith
Submitted On:
15 September 2017 - 12:23am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Multiview Pedestrian Localisation via a Prime Candidate Chart_v8.pdf

(14 downloads)

Keywords

Subscribe

[1] Ming Xu, Jeremy S. Smith, "Multiview Pedestrian Localisation via a Prime Candidate Chart", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2077. Accessed: Oct. 19, 2017.
@article{2077-17,
url = {http://sigport.org/2077},
author = {Ming Xu; Jeremy S. Smith },
publisher = {IEEE SigPort},
title = {Multiview Pedestrian Localisation via a Prime Candidate Chart},
year = {2017} }
TY - EJOUR
T1 - Multiview Pedestrian Localisation via a Prime Candidate Chart
AU - Ming Xu; Jeremy S. Smith
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2077
ER -
Ming Xu, Jeremy S. Smith. (2017). Multiview Pedestrian Localisation via a Prime Candidate Chart. IEEE SigPort. http://sigport.org/2077
Ming Xu, Jeremy S. Smith, 2017. Multiview Pedestrian Localisation via a Prime Candidate Chart. Available at: http://sigport.org/2077.
Ming Xu, Jeremy S. Smith. (2017). "Multiview Pedestrian Localisation via a Prime Candidate Chart." Web.
1. Ming Xu, Jeremy S. Smith. Multiview Pedestrian Localisation via a Prime Candidate Chart [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2077

Hierarchical Bilinear Network for High Performance Face Detection

Paper Details

Authors:
Submitted On:
14 September 2017 - 10:57pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

HBN_lv.pdf

(10 downloads)

Keywords

Subscribe

[1] , "Hierarchical Bilinear Network for High Performance Face Detection", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2064. Accessed: Oct. 19, 2017.
@article{2064-17,
url = {http://sigport.org/2064},
author = { },
publisher = {IEEE SigPort},
title = {Hierarchical Bilinear Network for High Performance Face Detection},
year = {2017} }
TY - EJOUR
T1 - Hierarchical Bilinear Network for High Performance Face Detection
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2064
ER -
. (2017). Hierarchical Bilinear Network for High Performance Face Detection. IEEE SigPort. http://sigport.org/2064
, 2017. Hierarchical Bilinear Network for High Performance Face Detection. Available at: http://sigport.org/2064.
. (2017). "Hierarchical Bilinear Network for High Performance Face Detection." Web.
1. . Hierarchical Bilinear Network for High Performance Face Detection [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2064

Learning Optimal Parameters for Binary Sensing Image Reconstruction Algorithms


A novel data-driven reconstruction algorithm for quantum image sensors (QIS) is proposed. Observations are efficiently decoded by modeling the reconstruction structure as a two-layer neural network, where optimal coefficients are obtained via error backpropagation. Our model encapsulates the structure of state-of-the-art algorithms, yet it presents a faster alternative which adapts to input examples without a priori statistical information.

Paper Details

Authors:
Renán A. Rojas, Wangyu Luo, Victor Murray, and Yue M. Lu
Submitted On:
14 September 2017 - 9:54pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

rojas_2017_learning_poster.pdf

(12 downloads)

Keywords

Subscribe

[1] Renán A. Rojas, Wangyu Luo, Victor Murray, and Yue M. Lu, "Learning Optimal Parameters for Binary Sensing Image Reconstruction Algorithms", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2063. Accessed: Oct. 19, 2017.
@article{2063-17,
url = {http://sigport.org/2063},
author = {Renán A. Rojas; Wangyu Luo; Victor Murray; and Yue M. Lu },
publisher = {IEEE SigPort},
title = {Learning Optimal Parameters for Binary Sensing Image Reconstruction Algorithms},
year = {2017} }
TY - EJOUR
T1 - Learning Optimal Parameters for Binary Sensing Image Reconstruction Algorithms
AU - Renán A. Rojas; Wangyu Luo; Victor Murray; and Yue M. Lu
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2063
ER -
Renán A. Rojas, Wangyu Luo, Victor Murray, and Yue M. Lu. (2017). Learning Optimal Parameters for Binary Sensing Image Reconstruction Algorithms. IEEE SigPort. http://sigport.org/2063
Renán A. Rojas, Wangyu Luo, Victor Murray, and Yue M. Lu, 2017. Learning Optimal Parameters for Binary Sensing Image Reconstruction Algorithms. Available at: http://sigport.org/2063.
Renán A. Rojas, Wangyu Luo, Victor Murray, and Yue M. Lu. (2017). "Learning Optimal Parameters for Binary Sensing Image Reconstruction Algorithms." Web.
1. Renán A. Rojas, Wangyu Luo, Victor Murray, and Yue M. Lu. Learning Optimal Parameters for Binary Sensing Image Reconstruction Algorithms [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2063

FSVO: SEMI-DIRECT MONOCULAR VISUAL ODOMETRY USING FIXED MAPS


We propose a fixed-map semi-direct visual odometry (FSVO) algorithm for Micro Aerial Vehicles (MAVs). The proposed approach does not need computationally expensive feature extraction and matching techniques for motion estimation at each frame. Instead, we extract and match ORiented Brief (ORB) features between keyframes and assist-frames. We replace the incremental map generation step in traditional algorithms with fixed map generation at keyframe and assist- frame only in our algorithm, resulting in reduced storage memory and higher flexibility for relocalization.

Paper Details

Authors:
Yulan Guo, Zaiping Lin, Wei An
Submitted On:
14 September 2017 - 9:58pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2017—ZhihengFu

(14 downloads)

Keywords

Subscribe

[1] Yulan Guo, Zaiping Lin, Wei An, "FSVO: SEMI-DIRECT MONOCULAR VISUAL ODOMETRY USING FIXED MAPS", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2062. Accessed: Oct. 19, 2017.
@article{2062-17,
url = {http://sigport.org/2062},
author = {Yulan Guo; Zaiping Lin; Wei An },
publisher = {IEEE SigPort},
title = {FSVO: SEMI-DIRECT MONOCULAR VISUAL ODOMETRY USING FIXED MAPS},
year = {2017} }
TY - EJOUR
T1 - FSVO: SEMI-DIRECT MONOCULAR VISUAL ODOMETRY USING FIXED MAPS
AU - Yulan Guo; Zaiping Lin; Wei An
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2062
ER -
Yulan Guo, Zaiping Lin, Wei An. (2017). FSVO: SEMI-DIRECT MONOCULAR VISUAL ODOMETRY USING FIXED MAPS. IEEE SigPort. http://sigport.org/2062
Yulan Guo, Zaiping Lin, Wei An, 2017. FSVO: SEMI-DIRECT MONOCULAR VISUAL ODOMETRY USING FIXED MAPS. Available at: http://sigport.org/2062.
Yulan Guo, Zaiping Lin, Wei An. (2017). "FSVO: SEMI-DIRECT MONOCULAR VISUAL ODOMETRY USING FIXED MAPS." Web.
1. Yulan Guo, Zaiping Lin, Wei An. FSVO: SEMI-DIRECT MONOCULAR VISUAL ODOMETRY USING FIXED MAPS [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2062

Pages