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

Image/Video Processing

Intelligent Detail Enhancement for Differently Exposed Images

Paper Details

Authors:
Weihai Chen, Xingming Wu, Zhengguo Li
Submitted On:
15 September 2017 - 11:12pm
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

ICIP2017_1523.pdf

(14 downloads)

Keywords

Subscribe

[1] Weihai Chen, Xingming Wu, Zhengguo Li, "Intelligent Detail Enhancement for Differently Exposed Images", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2168. Accessed: Oct. 19, 2017.
@article{2168-17,
url = {http://sigport.org/2168},
author = {Weihai Chen; Xingming Wu; Zhengguo Li },
publisher = {IEEE SigPort},
title = {Intelligent Detail Enhancement for Differently Exposed Images},
year = {2017} }
TY - EJOUR
T1 - Intelligent Detail Enhancement for Differently Exposed Images
AU - Weihai Chen; Xingming Wu; Zhengguo Li
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2168
ER -
Weihai Chen, Xingming Wu, Zhengguo Li. (2017). Intelligent Detail Enhancement for Differently Exposed Images. IEEE SigPort. http://sigport.org/2168
Weihai Chen, Xingming Wu, Zhengguo Li, 2017. Intelligent Detail Enhancement for Differently Exposed Images. Available at: http://sigport.org/2168.
Weihai Chen, Xingming Wu, Zhengguo Li. (2017). "Intelligent Detail Enhancement for Differently Exposed Images." Web.
1. Weihai Chen, Xingming Wu, Zhengguo Li. Intelligent Detail Enhancement for Differently Exposed Images [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2168

RECONSTRUCTION OF POLARIZATION IMAGES FROM A MULTIMOD LIGHT FIELD CAMERA BASED ON THE ALIASING MODEL

Paper Details

Authors:
Submitted On:
15 September 2017 - 10:46pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP-1721.pdf

(14 downloads)

Keywords

Subscribe

[1] , "RECONSTRUCTION OF POLARIZATION IMAGES FROM A MULTIMOD LIGHT FIELD CAMERA BASED ON THE ALIASING MODEL", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2166. Accessed: Oct. 19, 2017.
@article{2166-17,
url = {http://sigport.org/2166},
author = { },
publisher = {IEEE SigPort},
title = {RECONSTRUCTION OF POLARIZATION IMAGES FROM A MULTIMOD LIGHT FIELD CAMERA BASED ON THE ALIASING MODEL},
year = {2017} }
TY - EJOUR
T1 - RECONSTRUCTION OF POLARIZATION IMAGES FROM A MULTIMOD LIGHT FIELD CAMERA BASED ON THE ALIASING MODEL
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2166
ER -
. (2017). RECONSTRUCTION OF POLARIZATION IMAGES FROM A MULTIMOD LIGHT FIELD CAMERA BASED ON THE ALIASING MODEL. IEEE SigPort. http://sigport.org/2166
, 2017. RECONSTRUCTION OF POLARIZATION IMAGES FROM A MULTIMOD LIGHT FIELD CAMERA BASED ON THE ALIASING MODEL. Available at: http://sigport.org/2166.
. (2017). "RECONSTRUCTION OF POLARIZATION IMAGES FROM A MULTIMOD LIGHT FIELD CAMERA BASED ON THE ALIASING MODEL." Web.
1. . RECONSTRUCTION OF POLARIZATION IMAGES FROM A MULTIMOD LIGHT FIELD CAMERA BASED ON THE ALIASING MODEL [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2166

SINGLE IMAGE DEPTH PREDICTION USING SUPER-COLUMN SUPER-PIXEL FEATURES


Depth prediction from a single monocular image is a challenging yet valuable task, as often a depth sensor is not available. The state-of-the-art approach \cite{Liu2016} combines a deep fully convolutional network (DFCN) with a conditional random field (CRF), allowing the CRF to correct and smooth the depth values estimated by the DFCN according to efficient contextual modeling.

poster-surf.pdf

PDF icon poster- (14 downloads)

Paper Details

Authors:
Xufeng Guo, Kien Nguyen, Simon Denman, Clinton Fookes, Sridha Sridharan
Submitted On:
15 September 2017 - 9:27pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster-

(14 downloads)

Keywords

Subscribe

[1] Xufeng Guo, Kien Nguyen, Simon Denman, Clinton Fookes, Sridha Sridharan, "SINGLE IMAGE DEPTH PREDICTION USING SUPER-COLUMN SUPER-PIXEL FEATURES", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2165. Accessed: Oct. 19, 2017.
@article{2165-17,
url = {http://sigport.org/2165},
author = {Xufeng Guo; Kien Nguyen; Simon Denman; Clinton Fookes; Sridha Sridharan },
publisher = {IEEE SigPort},
title = {SINGLE IMAGE DEPTH PREDICTION USING SUPER-COLUMN SUPER-PIXEL FEATURES},
year = {2017} }
TY - EJOUR
T1 - SINGLE IMAGE DEPTH PREDICTION USING SUPER-COLUMN SUPER-PIXEL FEATURES
AU - Xufeng Guo; Kien Nguyen; Simon Denman; Clinton Fookes; Sridha Sridharan
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2165
ER -
Xufeng Guo, Kien Nguyen, Simon Denman, Clinton Fookes, Sridha Sridharan. (2017). SINGLE IMAGE DEPTH PREDICTION USING SUPER-COLUMN SUPER-PIXEL FEATURES. IEEE SigPort. http://sigport.org/2165
Xufeng Guo, Kien Nguyen, Simon Denman, Clinton Fookes, Sridha Sridharan, 2017. SINGLE IMAGE DEPTH PREDICTION USING SUPER-COLUMN SUPER-PIXEL FEATURES. Available at: http://sigport.org/2165.
Xufeng Guo, Kien Nguyen, Simon Denman, Clinton Fookes, Sridha Sridharan. (2017). "SINGLE IMAGE DEPTH PREDICTION USING SUPER-COLUMN SUPER-PIXEL FEATURES." Web.
1. Xufeng Guo, Kien Nguyen, Simon Denman, Clinton Fookes, Sridha Sridharan. SINGLE IMAGE DEPTH PREDICTION USING SUPER-COLUMN SUPER-PIXEL FEATURES [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2165

EXPLOITING PROBABILISTIC RELATIONSHIPS BETWEEN ACTION CONCEPTS FOR COMPLEX EVENT CLASSIFICATION


Videos of complex events are difficult to represent solely as
bags of low level features. Increasingly, supervised concepts
or attributes are being employed as the intermediate representation
of such videos. We propose a probabilistic framework
that models the conditional relationships between the
concepts and events and devise an approximate yet tractable
solution to infer the posterior distribution to perform event
classification. Using noisy outputs of pre-trained concept detectors,
we learn semantic and visual dependencies between

Paper Details

Authors:
Submitted On:
15 September 2017 - 8:46pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Recovered File 2.pdf

(14 downloads)

Keywords

Subscribe

[1] , "EXPLOITING PROBABILISTIC RELATIONSHIPS BETWEEN ACTION CONCEPTS FOR COMPLEX EVENT CLASSIFICATION", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2164. Accessed: Oct. 19, 2017.
@article{2164-17,
url = {http://sigport.org/2164},
author = { },
publisher = {IEEE SigPort},
title = {EXPLOITING PROBABILISTIC RELATIONSHIPS BETWEEN ACTION CONCEPTS FOR COMPLEX EVENT CLASSIFICATION},
year = {2017} }
TY - EJOUR
T1 - EXPLOITING PROBABILISTIC RELATIONSHIPS BETWEEN ACTION CONCEPTS FOR COMPLEX EVENT CLASSIFICATION
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2164
ER -
. (2017). EXPLOITING PROBABILISTIC RELATIONSHIPS BETWEEN ACTION CONCEPTS FOR COMPLEX EVENT CLASSIFICATION. IEEE SigPort. http://sigport.org/2164
, 2017. EXPLOITING PROBABILISTIC RELATIONSHIPS BETWEEN ACTION CONCEPTS FOR COMPLEX EVENT CLASSIFICATION. Available at: http://sigport.org/2164.
. (2017). "EXPLOITING PROBABILISTIC RELATIONSHIPS BETWEEN ACTION CONCEPTS FOR COMPLEX EVENT CLASSIFICATION." Web.
1. . EXPLOITING PROBABILISTIC RELATIONSHIPS BETWEEN ACTION CONCEPTS FOR COMPLEX EVENT CLASSIFICATION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2164

POLSAR DATA ONLINE CLASSIFICATION BASED ON MULTI-VIEW LEARNING


Polarimetric synthetic aperture radar (PolSAR) plays an indispensable part in remote sensing. With its development and application, rapid and accurate online classification for PolSAR data becomes more and more important. PolSAR data can be depicted by different features such as polarimetric, texture and color features, which can be considered as multiple views. In this paper, we propose an online multiview

Paper Details

Authors:
Xiangli Nie, Shuguang Ding, Bo Zhang, Hong Qiao, Xiayuan Huang
Submitted On:
15 September 2017 - 5:20pm
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

Poster_ICIP2017_Online multiview learning.pdf

(14 downloads)

Keywords

Subscribe

[1] Xiangli Nie, Shuguang Ding, Bo Zhang, Hong Qiao, Xiayuan Huang, "POLSAR DATA ONLINE CLASSIFICATION BASED ON MULTI-VIEW LEARNING", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2161. Accessed: Oct. 19, 2017.
@article{2161-17,
url = {http://sigport.org/2161},
author = {Xiangli Nie; Shuguang Ding; Bo Zhang; Hong Qiao; Xiayuan Huang },
publisher = {IEEE SigPort},
title = {POLSAR DATA ONLINE CLASSIFICATION BASED ON MULTI-VIEW LEARNING},
year = {2017} }
TY - EJOUR
T1 - POLSAR DATA ONLINE CLASSIFICATION BASED ON MULTI-VIEW LEARNING
AU - Xiangli Nie; Shuguang Ding; Bo Zhang; Hong Qiao; Xiayuan Huang
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2161
ER -
Xiangli Nie, Shuguang Ding, Bo Zhang, Hong Qiao, Xiayuan Huang. (2017). POLSAR DATA ONLINE CLASSIFICATION BASED ON MULTI-VIEW LEARNING. IEEE SigPort. http://sigport.org/2161
Xiangli Nie, Shuguang Ding, Bo Zhang, Hong Qiao, Xiayuan Huang, 2017. POLSAR DATA ONLINE CLASSIFICATION BASED ON MULTI-VIEW LEARNING. Available at: http://sigport.org/2161.
Xiangli Nie, Shuguang Ding, Bo Zhang, Hong Qiao, Xiayuan Huang. (2017). "POLSAR DATA ONLINE CLASSIFICATION BASED ON MULTI-VIEW LEARNING." Web.
1. Xiangli Nie, Shuguang Ding, Bo Zhang, Hong Qiao, Xiayuan Huang. POLSAR DATA ONLINE CLASSIFICATION BASED ON MULTI-VIEW LEARNING [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2161

ATTRIBUTE-CONTROLLED FACE PHOTO SYNTHESIS FROM SIMPLE LINE DRAWING


acfps.pdf

PDF icon acfps.pdf (14 downloads)

Paper Details

Authors:
Qi Guo, Ce Zhu, Zhiqiang Xia, Zhengtao Wang, Yipeng Liu
Submitted On:
15 September 2017 - 1:25pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

acfps.pdf

(14 downloads)

Keywords

Subscribe

[1] Qi Guo, Ce Zhu, Zhiqiang Xia, Zhengtao Wang, Yipeng Liu, "ATTRIBUTE-CONTROLLED FACE PHOTO SYNTHESIS FROM SIMPLE LINE DRAWING", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2157. Accessed: Oct. 19, 2017.
@article{2157-17,
url = {http://sigport.org/2157},
author = {Qi Guo; Ce Zhu; Zhiqiang Xia; Zhengtao Wang; Yipeng Liu },
publisher = {IEEE SigPort},
title = {ATTRIBUTE-CONTROLLED FACE PHOTO SYNTHESIS FROM SIMPLE LINE DRAWING},
year = {2017} }
TY - EJOUR
T1 - ATTRIBUTE-CONTROLLED FACE PHOTO SYNTHESIS FROM SIMPLE LINE DRAWING
AU - Qi Guo; Ce Zhu; Zhiqiang Xia; Zhengtao Wang; Yipeng Liu
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2157
ER -
Qi Guo, Ce Zhu, Zhiqiang Xia, Zhengtao Wang, Yipeng Liu. (2017). ATTRIBUTE-CONTROLLED FACE PHOTO SYNTHESIS FROM SIMPLE LINE DRAWING. IEEE SigPort. http://sigport.org/2157
Qi Guo, Ce Zhu, Zhiqiang Xia, Zhengtao Wang, Yipeng Liu, 2017. ATTRIBUTE-CONTROLLED FACE PHOTO SYNTHESIS FROM SIMPLE LINE DRAWING. Available at: http://sigport.org/2157.
Qi Guo, Ce Zhu, Zhiqiang Xia, Zhengtao Wang, Yipeng Liu. (2017). "ATTRIBUTE-CONTROLLED FACE PHOTO SYNTHESIS FROM SIMPLE LINE DRAWING." Web.
1. Qi Guo, Ce Zhu, Zhiqiang Xia, Zhengtao Wang, Yipeng Liu. ATTRIBUTE-CONTROLLED FACE PHOTO SYNTHESIS FROM SIMPLE LINE DRAWING [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2157

REALISTIC IMAGE COMPOSITE WITH BEST-BUDDY PRIOR OF NATURAL IMAGE PATCHES


Realistic image composite requires the appearance of foreground and background layers to be consistent. This is difficult to achieve because the foreground and the background may be taken from very different environments. This paper proposes a novel composite adjustment method that can harmonize appearance of different composite layers. We introduce the Best-Buddy Prior (BBP), which is a novel compact representations of the joint co-occurrence distribution of natural image patches. BBP can be learned from unlabelled images given only the unsupervised regional segmentation.

Paper Details

Authors:
Fan Zhong,Xiangyu Sun, Xueying Qin
Submitted On:
15 September 2017 - 1:12pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Poster-EALISTIC IMAGE COMPOSITE WITH BBP.pdf

(11 downloads)

Keywords

Subscribe

[1] Fan Zhong,Xiangyu Sun, Xueying Qin, "REALISTIC IMAGE COMPOSITE WITH BEST-BUDDY PRIOR OF NATURAL IMAGE PATCHES", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2154. Accessed: Oct. 19, 2017.
@article{2154-17,
url = {http://sigport.org/2154},
author = {Fan Zhong;Xiangyu Sun; Xueying Qin },
publisher = {IEEE SigPort},
title = {REALISTIC IMAGE COMPOSITE WITH BEST-BUDDY PRIOR OF NATURAL IMAGE PATCHES},
year = {2017} }
TY - EJOUR
T1 - REALISTIC IMAGE COMPOSITE WITH BEST-BUDDY PRIOR OF NATURAL IMAGE PATCHES
AU - Fan Zhong;Xiangyu Sun; Xueying Qin
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2154
ER -
Fan Zhong,Xiangyu Sun, Xueying Qin. (2017). REALISTIC IMAGE COMPOSITE WITH BEST-BUDDY PRIOR OF NATURAL IMAGE PATCHES. IEEE SigPort. http://sigport.org/2154
Fan Zhong,Xiangyu Sun, Xueying Qin, 2017. REALISTIC IMAGE COMPOSITE WITH BEST-BUDDY PRIOR OF NATURAL IMAGE PATCHES. Available at: http://sigport.org/2154.
Fan Zhong,Xiangyu Sun, Xueying Qin. (2017). "REALISTIC IMAGE COMPOSITE WITH BEST-BUDDY PRIOR OF NATURAL IMAGE PATCHES." Web.
1. Fan Zhong,Xiangyu Sun, Xueying Qin. REALISTIC IMAGE COMPOSITE WITH BEST-BUDDY PRIOR OF NATURAL IMAGE PATCHES [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2154

Dense Non-rigid Structure-from-Motion Made Easy -- A Spatial-Temporal Smoothness based Solution


This paper proposes a simple spatial-temporal smoothness based method for solving dense non-rigid structure-from-motion (NRSfM). First, we revisit the temporal smoothness and demonstrate that it can be extended to dense case directly. Second, we propose to exploit the spatial smoothness by resorting to the Laplacian of the 3D non-rigid shape. Third, to handle real world noise and outliers in measurements, we robustify the data term by using the L1 norm.

Paper Details

Authors:
Submitted On:
15 September 2017 - 1:37pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP-2017-Non-Rigid.pdf

(13 downloads)

Keywords

Subscribe

[1] , "Dense Non-rigid Structure-from-Motion Made Easy -- A Spatial-Temporal Smoothness based Solution", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2153. Accessed: Oct. 19, 2017.
@article{2153-17,
url = {http://sigport.org/2153},
author = { },
publisher = {IEEE SigPort},
title = {Dense Non-rigid Structure-from-Motion Made Easy -- A Spatial-Temporal Smoothness based Solution},
year = {2017} }
TY - EJOUR
T1 - Dense Non-rigid Structure-from-Motion Made Easy -- A Spatial-Temporal Smoothness based Solution
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2153
ER -
. (2017). Dense Non-rigid Structure-from-Motion Made Easy -- A Spatial-Temporal Smoothness based Solution. IEEE SigPort. http://sigport.org/2153
, 2017. Dense Non-rigid Structure-from-Motion Made Easy -- A Spatial-Temporal Smoothness based Solution. Available at: http://sigport.org/2153.
. (2017). "Dense Non-rigid Structure-from-Motion Made Easy -- A Spatial-Temporal Smoothness based Solution." Web.
1. . Dense Non-rigid Structure-from-Motion Made Easy -- A Spatial-Temporal Smoothness based Solution [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2153

DIFFUSE-SPECULAR SEPARATION OF MULTI-VIEW IMAGES UNDER VARYING ILLUMINATION


Separating diffuse and specular reflection components is important for preprocessing of various computer vision techniques such as photometric stereo. In this paper, we address diffuse-specular separation for photometric stereo based on light fields. Specifically, we reveal the low-rank structure of the multi-view images under varying light source directions, and then formulate the diffuse-specular separation as a low-rank approximation of the 3rd order tensor.

Paper Details

Authors:
Kouki Takechi, Takahiro Okabe
Submitted On:
15 September 2017 - 12:15pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2017_2381.pdf

(17 downloads)

Keywords

Subscribe

[1] Kouki Takechi, Takahiro Okabe, "DIFFUSE-SPECULAR SEPARATION OF MULTI-VIEW IMAGES UNDER VARYING ILLUMINATION", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2152. Accessed: Oct. 19, 2017.
@article{2152-17,
url = {http://sigport.org/2152},
author = {Kouki Takechi; Takahiro Okabe },
publisher = {IEEE SigPort},
title = {DIFFUSE-SPECULAR SEPARATION OF MULTI-VIEW IMAGES UNDER VARYING ILLUMINATION},
year = {2017} }
TY - EJOUR
T1 - DIFFUSE-SPECULAR SEPARATION OF MULTI-VIEW IMAGES UNDER VARYING ILLUMINATION
AU - Kouki Takechi; Takahiro Okabe
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2152
ER -
Kouki Takechi, Takahiro Okabe. (2017). DIFFUSE-SPECULAR SEPARATION OF MULTI-VIEW IMAGES UNDER VARYING ILLUMINATION. IEEE SigPort. http://sigport.org/2152
Kouki Takechi, Takahiro Okabe, 2017. DIFFUSE-SPECULAR SEPARATION OF MULTI-VIEW IMAGES UNDER VARYING ILLUMINATION. Available at: http://sigport.org/2152.
Kouki Takechi, Takahiro Okabe. (2017). "DIFFUSE-SPECULAR SEPARATION OF MULTI-VIEW IMAGES UNDER VARYING ILLUMINATION." Web.
1. Kouki Takechi, Takahiro Okabe. DIFFUSE-SPECULAR SEPARATION OF MULTI-VIEW IMAGES UNDER VARYING ILLUMINATION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2152

Object localization by optimizing convolutional neural network detection score using generic edge features


In this research, we propose an object localization method to boost the performance of current object detection techniques. This method utilizes the image edge information as a clue to determine the location of the objects. The Generic Edge Tokens (GETs) of the image are extracted based on the perceptual organization elements of human vision. These edge tokens are parsed according to the Best First Search algorithm to fine-tune the location of objects, where the objective function is the detection score returned by the Deep Convolutional Neural Network.

Paper Details

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

Document Files

Feathertheme.pdf

(13 downloads)

Keywords

Subscribe

[1] Qigang Gao, "Object localization by optimizing convolutional neural network detection score using generic edge features", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2151. Accessed: Oct. 19, 2017.
@article{2151-17,
url = {http://sigport.org/2151},
author = {Qigang Gao },
publisher = {IEEE SigPort},
title = {Object localization by optimizing convolutional neural network detection score using generic edge features},
year = {2017} }
TY - EJOUR
T1 - Object localization by optimizing convolutional neural network detection score using generic edge features
AU - Qigang Gao
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2151
ER -
Qigang Gao. (2017). Object localization by optimizing convolutional neural network detection score using generic edge features. IEEE SigPort. http://sigport.org/2151
Qigang Gao, 2017. Object localization by optimizing convolutional neural network detection score using generic edge features. Available at: http://sigport.org/2151.
Qigang Gao. (2017). "Object localization by optimizing convolutional neural network detection score using generic edge features." Web.
1. Qigang Gao. Object localization by optimizing convolutional neural network detection score using generic edge features [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2151

Pages