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

Image, Video, and Multidimensional Signal Processing

DIRECT MULTI-SCALE DUAL-STREAM NETWORK FOR PEDESTRIAN DETECTION

Paper Details

Authors:
kisang hong
Submitted On:
14 September 2017 - 2:26am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

MA-L6-2_Jung.pdf

(181 downloads)

Subscribe

[1] kisang hong, "DIRECT MULTI-SCALE DUAL-STREAM NETWORK FOR PEDESTRIAN DETECTION", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1929. Accessed: Oct. 19, 2018.
@article{1929-17,
url = {http://sigport.org/1929},
author = {kisang hong },
publisher = {IEEE SigPort},
title = {DIRECT MULTI-SCALE DUAL-STREAM NETWORK FOR PEDESTRIAN DETECTION},
year = {2017} }
TY - EJOUR
T1 - DIRECT MULTI-SCALE DUAL-STREAM NETWORK FOR PEDESTRIAN DETECTION
AU - kisang hong
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1929
ER -
kisang hong. (2017). DIRECT MULTI-SCALE DUAL-STREAM NETWORK FOR PEDESTRIAN DETECTION. IEEE SigPort. http://sigport.org/1929
kisang hong, 2017. DIRECT MULTI-SCALE DUAL-STREAM NETWORK FOR PEDESTRIAN DETECTION. Available at: http://sigport.org/1929.
kisang hong. (2017). "DIRECT MULTI-SCALE DUAL-STREAM NETWORK FOR PEDESTRIAN DETECTION." Web.
1. kisang hong. DIRECT MULTI-SCALE DUAL-STREAM NETWORK FOR PEDESTRIAN DETECTION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1929

DIRECT MULTI-SCALE DUAL-STREAM NETWORK FOR PEDESTRIAN DETECTION

Paper Details

Authors:
kisang hong
Submitted On:
14 September 2017 - 2:28am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

MA-L6-2_Jung.pdf

(156 downloads)

Subscribe

[1] kisang hong, "DIRECT MULTI-SCALE DUAL-STREAM NETWORK FOR PEDESTRIAN DETECTION", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1928. Accessed: Oct. 19, 2018.
@article{1928-17,
url = {http://sigport.org/1928},
author = {kisang hong },
publisher = {IEEE SigPort},
title = {DIRECT MULTI-SCALE DUAL-STREAM NETWORK FOR PEDESTRIAN DETECTION},
year = {2017} }
TY - EJOUR
T1 - DIRECT MULTI-SCALE DUAL-STREAM NETWORK FOR PEDESTRIAN DETECTION
AU - kisang hong
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1928
ER -
kisang hong. (2017). DIRECT MULTI-SCALE DUAL-STREAM NETWORK FOR PEDESTRIAN DETECTION. IEEE SigPort. http://sigport.org/1928
kisang hong, 2017. DIRECT MULTI-SCALE DUAL-STREAM NETWORK FOR PEDESTRIAN DETECTION. Available at: http://sigport.org/1928.
kisang hong. (2017). "DIRECT MULTI-SCALE DUAL-STREAM NETWORK FOR PEDESTRIAN DETECTION." Web.
1. kisang hong. DIRECT MULTI-SCALE DUAL-STREAM NETWORK FOR PEDESTRIAN DETECTION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1928

SINGLE DEPTH IMAGE SUPER-RESOLUTION AND DENOISING BASED ON SPARSE GRAPHS VIA STRUCTURE TENSOR


The existing single depth image super-resolution (SR)
methods suppose that the image to be interpolated is noise
free. However, the supposition is invalid in practice because
noise will be inevitably introduced in the depth image acquisition
process. In this paper, we address the problem of image
denoising and SR jointly based on designing sparse graphs
that are useful for describing the geometric structures of data
domains. In our method, we first cluster similar patches in a
noisy depth image and compute an average patch. Different

Paper Details

Authors:
Xianming Liu,Yongbing Zhang,Qionghai Dai
Submitted On:
11 September 2017 - 9:36pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Yihui Feng_icip_2017.pdf

(151 downloads)

Subscribe

[1] Xianming Liu,Yongbing Zhang,Qionghai Dai, "SINGLE DEPTH IMAGE SUPER-RESOLUTION AND DENOISING BASED ON SPARSE GRAPHS VIA STRUCTURE TENSOR", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1922. Accessed: Oct. 19, 2018.
@article{1922-17,
url = {http://sigport.org/1922},
author = {Xianming Liu;Yongbing Zhang;Qionghai Dai },
publisher = {IEEE SigPort},
title = {SINGLE DEPTH IMAGE SUPER-RESOLUTION AND DENOISING BASED ON SPARSE GRAPHS VIA STRUCTURE TENSOR},
year = {2017} }
TY - EJOUR
T1 - SINGLE DEPTH IMAGE SUPER-RESOLUTION AND DENOISING BASED ON SPARSE GRAPHS VIA STRUCTURE TENSOR
AU - Xianming Liu;Yongbing Zhang;Qionghai Dai
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1922
ER -
Xianming Liu,Yongbing Zhang,Qionghai Dai. (2017). SINGLE DEPTH IMAGE SUPER-RESOLUTION AND DENOISING BASED ON SPARSE GRAPHS VIA STRUCTURE TENSOR. IEEE SigPort. http://sigport.org/1922
Xianming Liu,Yongbing Zhang,Qionghai Dai, 2017. SINGLE DEPTH IMAGE SUPER-RESOLUTION AND DENOISING BASED ON SPARSE GRAPHS VIA STRUCTURE TENSOR. Available at: http://sigport.org/1922.
Xianming Liu,Yongbing Zhang,Qionghai Dai. (2017). "SINGLE DEPTH IMAGE SUPER-RESOLUTION AND DENOISING BASED ON SPARSE GRAPHS VIA STRUCTURE TENSOR." Web.
1. Xianming Liu,Yongbing Zhang,Qionghai Dai. SINGLE DEPTH IMAGE SUPER-RESOLUTION AND DENOISING BASED ON SPARSE GRAPHS VIA STRUCTURE TENSOR [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1922

CONVOLUTIONAL NEURAL NETWORKS FOR LICENSE PLATE DETECTION IN IMAGES


License plate detection is a challenging task when dealing with open environments and images captured from a certain distance by lowcost cameras. In this paper, we propose an approach for detecting license plates based on a convolutional neural network which models a function that produces a score for each image sub-region, allowing us to estimate the locations of the detected license plates by combining the results obtained from sparse overlapping regions.

Paper Details

Authors:
Francisco Delmar Kurpiel, Rodrigo Minetto, Bogdan Tomoyuki Nassu
Submitted On:
11 September 2017 - 2:51pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2017-09 - ICIP 2017.pdf

(244 downloads)

Subscribe

[1] Francisco Delmar Kurpiel, Rodrigo Minetto, Bogdan Tomoyuki Nassu, "CONVOLUTIONAL NEURAL NETWORKS FOR LICENSE PLATE DETECTION IN IMAGES", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1915. Accessed: Oct. 19, 2018.
@article{1915-17,
url = {http://sigport.org/1915},
author = {Francisco Delmar Kurpiel; Rodrigo Minetto; Bogdan Tomoyuki Nassu },
publisher = {IEEE SigPort},
title = {CONVOLUTIONAL NEURAL NETWORKS FOR LICENSE PLATE DETECTION IN IMAGES},
year = {2017} }
TY - EJOUR
T1 - CONVOLUTIONAL NEURAL NETWORKS FOR LICENSE PLATE DETECTION IN IMAGES
AU - Francisco Delmar Kurpiel; Rodrigo Minetto; Bogdan Tomoyuki Nassu
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1915
ER -
Francisco Delmar Kurpiel, Rodrigo Minetto, Bogdan Tomoyuki Nassu. (2017). CONVOLUTIONAL NEURAL NETWORKS FOR LICENSE PLATE DETECTION IN IMAGES. IEEE SigPort. http://sigport.org/1915
Francisco Delmar Kurpiel, Rodrigo Minetto, Bogdan Tomoyuki Nassu, 2017. CONVOLUTIONAL NEURAL NETWORKS FOR LICENSE PLATE DETECTION IN IMAGES. Available at: http://sigport.org/1915.
Francisco Delmar Kurpiel, Rodrigo Minetto, Bogdan Tomoyuki Nassu. (2017). "CONVOLUTIONAL NEURAL NETWORKS FOR LICENSE PLATE DETECTION IN IMAGES." Web.
1. Francisco Delmar Kurpiel, Rodrigo Minetto, Bogdan Tomoyuki Nassu. CONVOLUTIONAL NEURAL NETWORKS FOR LICENSE PLATE DETECTION IN IMAGES [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1915

Investigating the Impact of High Frame Rates on Video Compression

Paper Details

Authors:
Alex Mackin, Fan Zhang, Miltiadis Alexios Papadopoulos and David Bull
Submitted On:
12 September 2017 - 10:55am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP-MACKIN.pdf

(179 downloads)

Subscribe

[1] Alex Mackin, Fan Zhang, Miltiadis Alexios Papadopoulos and David Bull, "Investigating the Impact of High Frame Rates on Video Compression", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1909. Accessed: Oct. 19, 2018.
@article{1909-17,
url = {http://sigport.org/1909},
author = {Alex Mackin; Fan Zhang; Miltiadis Alexios Papadopoulos and David Bull },
publisher = {IEEE SigPort},
title = {Investigating the Impact of High Frame Rates on Video Compression},
year = {2017} }
TY - EJOUR
T1 - Investigating the Impact of High Frame Rates on Video Compression
AU - Alex Mackin; Fan Zhang; Miltiadis Alexios Papadopoulos and David Bull
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1909
ER -
Alex Mackin, Fan Zhang, Miltiadis Alexios Papadopoulos and David Bull. (2017). Investigating the Impact of High Frame Rates on Video Compression. IEEE SigPort. http://sigport.org/1909
Alex Mackin, Fan Zhang, Miltiadis Alexios Papadopoulos and David Bull, 2017. Investigating the Impact of High Frame Rates on Video Compression. Available at: http://sigport.org/1909.
Alex Mackin, Fan Zhang, Miltiadis Alexios Papadopoulos and David Bull. (2017). "Investigating the Impact of High Frame Rates on Video Compression." Web.
1. Alex Mackin, Fan Zhang, Miltiadis Alexios Papadopoulos and David Bull. Investigating the Impact of High Frame Rates on Video Compression [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1909

Comp-LOP: Complex Form of Local Orientation Plane for Object Tracking


In this paper, we propose complex form of local orientation plane (Comp-LOP) for object tracking. Comp-LOP is a simple but effective descriptor, which is robust to occlusion for object tracking. It effectively considers spatiotemporal relationship between the target and its surrounding regions in a correlation filter framework by the complex form, which successfully deals with the heavy occlusion problem. Moreover, scale estimation is performed to treat target scale variations for improving tracking accuracy.

Paper Details

Authors:
Submitted On:
12 September 2017 - 10:06am
Short Link:
Type:
Event:

Document Files

ICIP2017_CompLOP_final.pdf

(133 downloads)

Subscribe

[1] , "Comp-LOP: Complex Form of Local Orientation Plane for Object Tracking", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1906. Accessed: Oct. 19, 2018.
@article{1906-17,
url = {http://sigport.org/1906},
author = { },
publisher = {IEEE SigPort},
title = {Comp-LOP: Complex Form of Local Orientation Plane for Object Tracking},
year = {2017} }
TY - EJOUR
T1 - Comp-LOP: Complex Form of Local Orientation Plane for Object Tracking
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1906
ER -
. (2017). Comp-LOP: Complex Form of Local Orientation Plane for Object Tracking. IEEE SigPort. http://sigport.org/1906
, 2017. Comp-LOP: Complex Form of Local Orientation Plane for Object Tracking. Available at: http://sigport.org/1906.
. (2017). "Comp-LOP: Complex Form of Local Orientation Plane for Object Tracking." Web.
1. . Comp-LOP: Complex Form of Local Orientation Plane for Object Tracking [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1906

2563 sliding window filter based unknown object pose estimation

Paper Details

Authors:
Submitted On:
11 September 2017 - 4:13am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

conference_poster_4.pdf

(141 downloads)

Subscribe

[1] , "2563 sliding window filter based unknown object pose estimation", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1897. Accessed: Oct. 19, 2018.
@article{1897-17,
url = {http://sigport.org/1897},
author = { },
publisher = {IEEE SigPort},
title = {2563 sliding window filter based unknown object pose estimation},
year = {2017} }
TY - EJOUR
T1 - 2563 sliding window filter based unknown object pose estimation
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1897
ER -
. (2017). 2563 sliding window filter based unknown object pose estimation. IEEE SigPort. http://sigport.org/1897
, 2017. 2563 sliding window filter based unknown object pose estimation. Available at: http://sigport.org/1897.
. (2017). "2563 sliding window filter based unknown object pose estimation." Web.
1. . 2563 sliding window filter based unknown object pose estimation [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1897

4D Effect Classification by Encoding CNN Features


4D effects are physical effects simulated in sync with videos, movies, and games to augment the events occurring in a story or a virtual world. Types of 4D effects commonly used for the immersive media may include seat motion, vibration, flash, wind, water, scent, thunderstorm, snow, and fog. Currently, the recognition of physical effects from a video is mainly conducted by human experts. Although 4D effects are promising in giving immersive experience and entertainment, this manual production has been the main obstacle to faster and wider application of 4D effects.

Paper Details

Authors:
Thomhert S. Siadari, Mikyong Han, Hyunjin Yoon
Submitted On:
14 September 2017 - 3:13am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

presentation slides

(184 downloads)

Subscribe

[1] Thomhert S. Siadari, Mikyong Han, Hyunjin Yoon, "4D Effect Classification by Encoding CNN Features", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1892. Accessed: Oct. 19, 2018.
@article{1892-17,
url = {http://sigport.org/1892},
author = {Thomhert S. Siadari; Mikyong Han; Hyunjin Yoon },
publisher = {IEEE SigPort},
title = {4D Effect Classification by Encoding CNN Features},
year = {2017} }
TY - EJOUR
T1 - 4D Effect Classification by Encoding CNN Features
AU - Thomhert S. Siadari; Mikyong Han; Hyunjin Yoon
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1892
ER -
Thomhert S. Siadari, Mikyong Han, Hyunjin Yoon. (2017). 4D Effect Classification by Encoding CNN Features. IEEE SigPort. http://sigport.org/1892
Thomhert S. Siadari, Mikyong Han, Hyunjin Yoon, 2017. 4D Effect Classification by Encoding CNN Features. Available at: http://sigport.org/1892.
Thomhert S. Siadari, Mikyong Han, Hyunjin Yoon. (2017). "4D Effect Classification by Encoding CNN Features." Web.
1. Thomhert S. Siadari, Mikyong Han, Hyunjin Yoon. 4D Effect Classification by Encoding CNN Features [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1892

SAR Image Despeckling by Combination of Fractional-Order Total Variation and Nonlocal Low Rank Regularization


This paper proposes a combinational regularization model for synthetic aperture radar (SAR) image despeckling. In contrast to most of the well-known regularization methods that only use one image prior property, the proposed combinational regularization model includes both fractional-order total variation (FrTV) regularization term and nonlocal low rank (NLR) regularization term.

Paper Details

Authors:
Submitted On:
10 September 2017 - 9:34pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2017-GaoChen.pdf

(181 downloads)

Subscribe

[1] , "SAR Image Despeckling by Combination of Fractional-Order Total Variation and Nonlocal Low Rank Regularization ", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1890. Accessed: Oct. 19, 2018.
@article{1890-17,
url = {http://sigport.org/1890},
author = { },
publisher = {IEEE SigPort},
title = {SAR Image Despeckling by Combination of Fractional-Order Total Variation and Nonlocal Low Rank Regularization },
year = {2017} }
TY - EJOUR
T1 - SAR Image Despeckling by Combination of Fractional-Order Total Variation and Nonlocal Low Rank Regularization
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1890
ER -
. (2017). SAR Image Despeckling by Combination of Fractional-Order Total Variation and Nonlocal Low Rank Regularization . IEEE SigPort. http://sigport.org/1890
, 2017. SAR Image Despeckling by Combination of Fractional-Order Total Variation and Nonlocal Low Rank Regularization . Available at: http://sigport.org/1890.
. (2017). "SAR Image Despeckling by Combination of Fractional-Order Total Variation and Nonlocal Low Rank Regularization ." Web.
1. . SAR Image Despeckling by Combination of Fractional-Order Total Variation and Nonlocal Low Rank Regularization [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1890

ByNet-SR: Image Super Resolution with a Bypass Connection Network

Paper Details

Authors:
Submitted On:
8 September 2017 - 9:13am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICIP17-poster.pdf

(257 downloads)

Subscribe

[1] , "ByNet-SR: Image Super Resolution with a Bypass Connection Network", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1876. Accessed: Oct. 19, 2018.
@article{1876-17,
url = {http://sigport.org/1876},
author = { },
publisher = {IEEE SigPort},
title = {ByNet-SR: Image Super Resolution with a Bypass Connection Network},
year = {2017} }
TY - EJOUR
T1 - ByNet-SR: Image Super Resolution with a Bypass Connection Network
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1876
ER -
. (2017). ByNet-SR: Image Super Resolution with a Bypass Connection Network. IEEE SigPort. http://sigport.org/1876
, 2017. ByNet-SR: Image Super Resolution with a Bypass Connection Network. Available at: http://sigport.org/1876.
. (2017). "ByNet-SR: Image Super Resolution with a Bypass Connection Network." Web.
1. . ByNet-SR: Image Super Resolution with a Bypass Connection Network [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1876

Pages