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

Image, Video, and Multidimensional Signal Processing

SHOW, TRANSLATE AND TELL


Humans have an incredible ability to process and understand
information from multiple sources such as images,
video, text, and speech. Recent success of deep neural
networks has enabled us to develop algorithms which give
machines the ability to understand and interpret this information.
There is a need to both broaden their applicability and
develop methods which correlate visual information along
with semantic content. We propose a unified model which
jointly trains on images and captions, and learns to generate

Paper Details

Authors:
Dheeraj Peri, Shagan Sah, Raymond Ptucha
Submitted On:
20 September 2019 - 7:51pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

STT_v5.pdf

(8)

Subscribe

[1] Dheeraj Peri, Shagan Sah, Raymond Ptucha, "SHOW, TRANSLATE AND TELL", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4795. Accessed: Oct. 18, 2019.
@article{4795-19,
url = {http://sigport.org/4795},
author = {Dheeraj Peri; Shagan Sah; Raymond Ptucha },
publisher = {IEEE SigPort},
title = {SHOW, TRANSLATE AND TELL},
year = {2019} }
TY - EJOUR
T1 - SHOW, TRANSLATE AND TELL
AU - Dheeraj Peri; Shagan Sah; Raymond Ptucha
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4795
ER -
Dheeraj Peri, Shagan Sah, Raymond Ptucha. (2019). SHOW, TRANSLATE AND TELL. IEEE SigPort. http://sigport.org/4795
Dheeraj Peri, Shagan Sah, Raymond Ptucha, 2019. SHOW, TRANSLATE AND TELL. Available at: http://sigport.org/4795.
Dheeraj Peri, Shagan Sah, Raymond Ptucha. (2019). "SHOW, TRANSLATE AND TELL." Web.
1. Dheeraj Peri, Shagan Sah, Raymond Ptucha. SHOW, TRANSLATE AND TELL [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4795

MULTI-TASK LEARNING WITH COMPRESSIBLE FEATURES FOR COLLABORATIVE INTELLIGENCE


A promising way to deploy Artificial Intelligence (AI)-based services on mobile devices is to run a part of the AI model (a deep neural network) on the mobile itself, and the rest in the cloud. This is sometimes referred to as collaborative intelligence. In this framework, intermediate features from the deep network need to be transmitted to the cloud for further processing. We study the case where such features are used for multiple purposes in the cloud (multi-tasking) and where they need to be compressible in order to allow efficient transmission to the cloud.

Paper Details

Authors:
Submitted On:
20 September 2019 - 2:18pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP_2019.pptx

(9)

Subscribe

[1] , "MULTI-TASK LEARNING WITH COMPRESSIBLE FEATURES FOR COLLABORATIVE INTELLIGENCE", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4793. Accessed: Oct. 18, 2019.
@article{4793-19,
url = {http://sigport.org/4793},
author = { },
publisher = {IEEE SigPort},
title = {MULTI-TASK LEARNING WITH COMPRESSIBLE FEATURES FOR COLLABORATIVE INTELLIGENCE},
year = {2019} }
TY - EJOUR
T1 - MULTI-TASK LEARNING WITH COMPRESSIBLE FEATURES FOR COLLABORATIVE INTELLIGENCE
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4793
ER -
. (2019). MULTI-TASK LEARNING WITH COMPRESSIBLE FEATURES FOR COLLABORATIVE INTELLIGENCE. IEEE SigPort. http://sigport.org/4793
, 2019. MULTI-TASK LEARNING WITH COMPRESSIBLE FEATURES FOR COLLABORATIVE INTELLIGENCE. Available at: http://sigport.org/4793.
. (2019). "MULTI-TASK LEARNING WITH COMPRESSIBLE FEATURES FOR COLLABORATIVE INTELLIGENCE." Web.
1. . MULTI-TASK LEARNING WITH COMPRESSIBLE FEATURES FOR COLLABORATIVE INTELLIGENCE [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4793

A COMPOUND NEURAL NETWORK FOR BRAIN TUMOR SEGMENTATION

Paper Details

Authors:
Yucui Guo; Yujing Zheng
Submitted On:
20 September 2019 - 4:53am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2019-eposter_zh-bupt-V1.pdf

(5)

Subscribe

[1] Yucui Guo; Yujing Zheng, "A COMPOUND NEURAL NETWORK FOR BRAIN TUMOR SEGMENTATION ", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4766. Accessed: Oct. 18, 2019.
@article{4766-19,
url = {http://sigport.org/4766},
author = {Yucui Guo; Yujing Zheng },
publisher = {IEEE SigPort},
title = {A COMPOUND NEURAL NETWORK FOR BRAIN TUMOR SEGMENTATION },
year = {2019} }
TY - EJOUR
T1 - A COMPOUND NEURAL NETWORK FOR BRAIN TUMOR SEGMENTATION
AU - Yucui Guo; Yujing Zheng
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4766
ER -
Yucui Guo; Yujing Zheng. (2019). A COMPOUND NEURAL NETWORK FOR BRAIN TUMOR SEGMENTATION . IEEE SigPort. http://sigport.org/4766
Yucui Guo; Yujing Zheng, 2019. A COMPOUND NEURAL NETWORK FOR BRAIN TUMOR SEGMENTATION . Available at: http://sigport.org/4766.
Yucui Guo; Yujing Zheng. (2019). "A COMPOUND NEURAL NETWORK FOR BRAIN TUMOR SEGMENTATION ." Web.
1. Yucui Guo; Yujing Zheng. A COMPOUND NEURAL NETWORK FOR BRAIN TUMOR SEGMENTATION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4766

DEEP UNSUPERVISED LEARNING FOR SIMULTANEOUS VISUAL ODOMETRY AND DEPTH ESTIMATION

Paper Details

Authors:
Yawen Lu, Guoyu Lu
Submitted On:
9 October 2019 - 12:52am
Short Link:
Type:

Document Files

ICIP_poster__1.pptx

(6)

Subscribe

[1] Yawen Lu, Guoyu Lu, "DEEP UNSUPERVISED LEARNING FOR SIMULTANEOUS VISUAL ODOMETRY AND DEPTH ESTIMATION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4760. Accessed: Oct. 18, 2019.
@article{4760-19,
url = {http://sigport.org/4760},
author = {Yawen Lu; Guoyu Lu },
publisher = {IEEE SigPort},
title = {DEEP UNSUPERVISED LEARNING FOR SIMULTANEOUS VISUAL ODOMETRY AND DEPTH ESTIMATION},
year = {2019} }
TY - EJOUR
T1 - DEEP UNSUPERVISED LEARNING FOR SIMULTANEOUS VISUAL ODOMETRY AND DEPTH ESTIMATION
AU - Yawen Lu; Guoyu Lu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4760
ER -
Yawen Lu, Guoyu Lu. (2019). DEEP UNSUPERVISED LEARNING FOR SIMULTANEOUS VISUAL ODOMETRY AND DEPTH ESTIMATION. IEEE SigPort. http://sigport.org/4760
Yawen Lu, Guoyu Lu, 2019. DEEP UNSUPERVISED LEARNING FOR SIMULTANEOUS VISUAL ODOMETRY AND DEPTH ESTIMATION. Available at: http://sigport.org/4760.
Yawen Lu, Guoyu Lu. (2019). "DEEP UNSUPERVISED LEARNING FOR SIMULTANEOUS VISUAL ODOMETRY AND DEPTH ESTIMATION." Web.
1. Yawen Lu, Guoyu Lu. DEEP UNSUPERVISED LEARNING FOR SIMULTANEOUS VISUAL ODOMETRY AND DEPTH ESTIMATION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4760

IMPRESSION ESTIMATION FOR DEFORMED PORTRAITS WITH A LANDMARK-BASED RANKING NETWORK


In recent years, it has become a trend for people to manipulate their own portraits before posting them on a social networking service. However, it is difficult to get a desired portrait after manipulation without sufficient experience or skill. To obtain a simpler and more effective portrait manipulation technique, we consider an automated portrait manipulation method based on five impression words: clear, sweet, elegant, modern, and dynamic.

Paper Details

Authors:
Kiyoharu Aizawa
Submitted On:
23 September 2019 - 9:20am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2019ICIPposter_miyata_verfinal3.pdf

(4)

Subscribe

[1] Kiyoharu Aizawa, "IMPRESSION ESTIMATION FOR DEFORMED PORTRAITS WITH A LANDMARK-BASED RANKING NETWORK", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4745. Accessed: Oct. 18, 2019.
@article{4745-19,
url = {http://sigport.org/4745},
author = {Kiyoharu Aizawa },
publisher = {IEEE SigPort},
title = {IMPRESSION ESTIMATION FOR DEFORMED PORTRAITS WITH A LANDMARK-BASED RANKING NETWORK},
year = {2019} }
TY - EJOUR
T1 - IMPRESSION ESTIMATION FOR DEFORMED PORTRAITS WITH A LANDMARK-BASED RANKING NETWORK
AU - Kiyoharu Aizawa
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4745
ER -
Kiyoharu Aizawa. (2019). IMPRESSION ESTIMATION FOR DEFORMED PORTRAITS WITH A LANDMARK-BASED RANKING NETWORK. IEEE SigPort. http://sigport.org/4745
Kiyoharu Aizawa, 2019. IMPRESSION ESTIMATION FOR DEFORMED PORTRAITS WITH A LANDMARK-BASED RANKING NETWORK. Available at: http://sigport.org/4745.
Kiyoharu Aizawa. (2019). "IMPRESSION ESTIMATION FOR DEFORMED PORTRAITS WITH A LANDMARK-BASED RANKING NETWORK." Web.
1. Kiyoharu Aizawa. IMPRESSION ESTIMATION FOR DEFORMED PORTRAITS WITH A LANDMARK-BASED RANKING NETWORK [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4745

MULTIMODAL LATENT FACTOR MODEL WITH LANGUAGE CONSTRAINT FOR PREDICATE DETECTION

Paper Details

Authors:
Xuan Ma, Bing-Kun Bao, Changsheng Xu
Submitted On:
19 September 2019 - 7:56am
Short Link:
Type:
Event:

Document Files

poster-2.pdf

(6)

Subscribe

[1] Xuan Ma, Bing-Kun Bao, Changsheng Xu, "MULTIMODAL LATENT FACTOR MODEL WITH LANGUAGE CONSTRAINT FOR PREDICATE DETECTION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4725. Accessed: Oct. 18, 2019.
@article{4725-19,
url = {http://sigport.org/4725},
author = {Xuan Ma; Bing-Kun Bao; Changsheng Xu },
publisher = {IEEE SigPort},
title = {MULTIMODAL LATENT FACTOR MODEL WITH LANGUAGE CONSTRAINT FOR PREDICATE DETECTION},
year = {2019} }
TY - EJOUR
T1 - MULTIMODAL LATENT FACTOR MODEL WITH LANGUAGE CONSTRAINT FOR PREDICATE DETECTION
AU - Xuan Ma; Bing-Kun Bao; Changsheng Xu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4725
ER -
Xuan Ma, Bing-Kun Bao, Changsheng Xu. (2019). MULTIMODAL LATENT FACTOR MODEL WITH LANGUAGE CONSTRAINT FOR PREDICATE DETECTION. IEEE SigPort. http://sigport.org/4725
Xuan Ma, Bing-Kun Bao, Changsheng Xu, 2019. MULTIMODAL LATENT FACTOR MODEL WITH LANGUAGE CONSTRAINT FOR PREDICATE DETECTION. Available at: http://sigport.org/4725.
Xuan Ma, Bing-Kun Bao, Changsheng Xu. (2019). "MULTIMODAL LATENT FACTOR MODEL WITH LANGUAGE CONSTRAINT FOR PREDICATE DETECTION." Web.
1. Xuan Ma, Bing-Kun Bao, Changsheng Xu. MULTIMODAL LATENT FACTOR MODEL WITH LANGUAGE CONSTRAINT FOR PREDICATE DETECTION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4725

Multimodal Point Distribution Model for Anthropological Landmark Detection


While current landmark detection algorithms offer a good approximation of the landmark locations, they are often unsuitable for the use in biological research. We present multimodal landmark detection approach, based on Point distribution model that detects a larger number of anthropologically relevant landmarks than the current landmark detection algorithms.
At the same time we show that improving detection accuracy of initial vertices, using image information, to which

Paper Details

Authors:
Petr Matula
Submitted On:
19 September 2019 - 6:14am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICIP_poster.pdf

(19)

Subscribe

[1] Petr Matula, "Multimodal Point Distribution Model for Anthropological Landmark Detection", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4720. Accessed: Oct. 18, 2019.
@article{4720-19,
url = {http://sigport.org/4720},
author = {Petr Matula },
publisher = {IEEE SigPort},
title = {Multimodal Point Distribution Model for Anthropological Landmark Detection},
year = {2019} }
TY - EJOUR
T1 - Multimodal Point Distribution Model for Anthropological Landmark Detection
AU - Petr Matula
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4720
ER -
Petr Matula. (2019). Multimodal Point Distribution Model for Anthropological Landmark Detection. IEEE SigPort. http://sigport.org/4720
Petr Matula, 2019. Multimodal Point Distribution Model for Anthropological Landmark Detection. Available at: http://sigport.org/4720.
Petr Matula. (2019). "Multimodal Point Distribution Model for Anthropological Landmark Detection." Web.
1. Petr Matula. Multimodal Point Distribution Model for Anthropological Landmark Detection [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4720

VISUAL LOCALIZATION USING SPARSE SEMANTIC 3D MAP


Accurate and robust visual localization under a wide range of viewing condition variations including season and illumination changes, as well as weather and day-night variations, is the key component for many computer vision and robotics applications. Under these conditions, most traditional methods would fail to locate the camera. In this paper we present a visual localization algorithm that combines structure-based method and image-based method with semantic information.

Paper Details

Authors:
Submitted On:
19 September 2019 - 5:21am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

VISUAL LOCALIZATION USING SPARSE SEMANTIC 3D MAP.pdf

(8)

Subscribe

[1] , "VISUAL LOCALIZATION USING SPARSE SEMANTIC 3D MAP", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4714. Accessed: Oct. 18, 2019.
@article{4714-19,
url = {http://sigport.org/4714},
author = { },
publisher = {IEEE SigPort},
title = {VISUAL LOCALIZATION USING SPARSE SEMANTIC 3D MAP},
year = {2019} }
TY - EJOUR
T1 - VISUAL LOCALIZATION USING SPARSE SEMANTIC 3D MAP
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4714
ER -
. (2019). VISUAL LOCALIZATION USING SPARSE SEMANTIC 3D MAP. IEEE SigPort. http://sigport.org/4714
, 2019. VISUAL LOCALIZATION USING SPARSE SEMANTIC 3D MAP. Available at: http://sigport.org/4714.
. (2019). "VISUAL LOCALIZATION USING SPARSE SEMANTIC 3D MAP." Web.
1. . VISUAL LOCALIZATION USING SPARSE SEMANTIC 3D MAP [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4714

RESIDUAL DILATION BASED FEATURE PYRAMID NETWORK

Paper Details

Authors:
Submitted On:
19 September 2019 - 4:53am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Poster.pdf

(225)

Subscribe

[1] , "RESIDUAL DILATION BASED FEATURE PYRAMID NETWORK", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4713. Accessed: Oct. 18, 2019.
@article{4713-19,
url = {http://sigport.org/4713},
author = { },
publisher = {IEEE SigPort},
title = {RESIDUAL DILATION BASED FEATURE PYRAMID NETWORK},
year = {2019} }
TY - EJOUR
T1 - RESIDUAL DILATION BASED FEATURE PYRAMID NETWORK
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4713
ER -
. (2019). RESIDUAL DILATION BASED FEATURE PYRAMID NETWORK. IEEE SigPort. http://sigport.org/4713
, 2019. RESIDUAL DILATION BASED FEATURE PYRAMID NETWORK. Available at: http://sigport.org/4713.
. (2019). "RESIDUAL DILATION BASED FEATURE PYRAMID NETWORK." Web.
1. . RESIDUAL DILATION BASED FEATURE PYRAMID NETWORK [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4713

IMPROVED FOURIER MELLIN INVARIANT FOR ROBUST ROTATION ESTIMATION WITH OMNI-CAMERAS


Spectral methods such as the improved Fourier Mellin Invariant (iFMI) transform have proved to be faster, more robust

Paper Details

Authors:
Qingwen Xu, Arturo Gomez Chavez, Heiko Bülow, Andreas Birk, Sören Schwertfeger
Submitted On:
18 September 2019 - 11:10pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

MA-PB-3-xuqw.pdf

(4)

Subscribe

[1] Qingwen Xu, Arturo Gomez Chavez, Heiko Bülow, Andreas Birk, Sören Schwertfeger, "IMPROVED FOURIER MELLIN INVARIANT FOR ROBUST ROTATION ESTIMATION WITH OMNI-CAMERAS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4698. Accessed: Oct. 18, 2019.
@article{4698-19,
url = {http://sigport.org/4698},
author = {Qingwen Xu; Arturo Gomez Chavez; Heiko Bülow; Andreas Birk; Sören Schwertfeger },
publisher = {IEEE SigPort},
title = {IMPROVED FOURIER MELLIN INVARIANT FOR ROBUST ROTATION ESTIMATION WITH OMNI-CAMERAS},
year = {2019} }
TY - EJOUR
T1 - IMPROVED FOURIER MELLIN INVARIANT FOR ROBUST ROTATION ESTIMATION WITH OMNI-CAMERAS
AU - Qingwen Xu; Arturo Gomez Chavez; Heiko Bülow; Andreas Birk; Sören Schwertfeger
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4698
ER -
Qingwen Xu, Arturo Gomez Chavez, Heiko Bülow, Andreas Birk, Sören Schwertfeger. (2019). IMPROVED FOURIER MELLIN INVARIANT FOR ROBUST ROTATION ESTIMATION WITH OMNI-CAMERAS. IEEE SigPort. http://sigport.org/4698
Qingwen Xu, Arturo Gomez Chavez, Heiko Bülow, Andreas Birk, Sören Schwertfeger, 2019. IMPROVED FOURIER MELLIN INVARIANT FOR ROBUST ROTATION ESTIMATION WITH OMNI-CAMERAS. Available at: http://sigport.org/4698.
Qingwen Xu, Arturo Gomez Chavez, Heiko Bülow, Andreas Birk, Sören Schwertfeger. (2019). "IMPROVED FOURIER MELLIN INVARIANT FOR ROBUST ROTATION ESTIMATION WITH OMNI-CAMERAS." Web.
1. Qingwen Xu, Arturo Gomez Chavez, Heiko Bülow, Andreas Birk, Sören Schwertfeger. IMPROVED FOURIER MELLIN INVARIANT FOR ROBUST ROTATION ESTIMATION WITH OMNI-CAMERAS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4698

Pages