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

Image/Video Processing

#1016 DO WE REALLY NEED MORE TRAINING DATA FOR OBJECT LOCALIZATION

Paper Details

Authors:
Hongyang Li, Yu Liu1, Xin Zhang, Zhecheng An, Jingjing Wang, Yibo Chen,Jihong Tong
Submitted On:
15 September 2017 - 12:11pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

#1016_ DO WE REALLY NEED MORE TRAINING DATA FOR OBJECT LOCALIZATION .pdf

(12 downloads)

Keywords

Subscribe

[1] Hongyang Li, Yu Liu1, Xin Zhang, Zhecheng An, Jingjing Wang, Yibo Chen,Jihong Tong , "#1016 DO WE REALLY NEED MORE TRAINING DATA FOR OBJECT LOCALIZATION ", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2150. Accessed: Oct. 19, 2017.
@article{2150-17,
url = {http://sigport.org/2150},
author = {Hongyang Li; Yu Liu1; Xin Zhang; Zhecheng An; Jingjing Wang; Yibo Chen;Jihong Tong },
publisher = {IEEE SigPort},
title = {#1016 DO WE REALLY NEED MORE TRAINING DATA FOR OBJECT LOCALIZATION },
year = {2017} }
TY - EJOUR
T1 - #1016 DO WE REALLY NEED MORE TRAINING DATA FOR OBJECT LOCALIZATION
AU - Hongyang Li; Yu Liu1; Xin Zhang; Zhecheng An; Jingjing Wang; Yibo Chen;Jihong Tong
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2150
ER -
Hongyang Li, Yu Liu1, Xin Zhang, Zhecheng An, Jingjing Wang, Yibo Chen,Jihong Tong . (2017). #1016 DO WE REALLY NEED MORE TRAINING DATA FOR OBJECT LOCALIZATION . IEEE SigPort. http://sigport.org/2150
Hongyang Li, Yu Liu1, Xin Zhang, Zhecheng An, Jingjing Wang, Yibo Chen,Jihong Tong , 2017. #1016 DO WE REALLY NEED MORE TRAINING DATA FOR OBJECT LOCALIZATION . Available at: http://sigport.org/2150.
Hongyang Li, Yu Liu1, Xin Zhang, Zhecheng An, Jingjing Wang, Yibo Chen,Jihong Tong . (2017). "#1016 DO WE REALLY NEED MORE TRAINING DATA FOR OBJECT LOCALIZATION ." Web.
1. Hongyang Li, Yu Liu1, Xin Zhang, Zhecheng An, Jingjing Wang, Yibo Chen,Jihong Tong . #1016 DO WE REALLY NEED MORE TRAINING DATA FOR OBJECT LOCALIZATION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2150

A HIERARCHICAL FEATURE MODEL FOR MULTI-TARGET TRACKING


We proposed a novel and a Hierarchical Feature Model (HFM) for multi-target tracking. The traditional tracking algorithms
use handcrafted features that cannot track targets accurately when the target model changes due to articulation,
different illuminations and perspective distortions. Our HFM explore deep features to model the appearance of targets.
Then, we explore an unsupervised dimensionality reduction for sparse representation of the feature vectors to cope

Paper Details

Authors:
Ahmed Kedir Mohammed, Faouzi Alaya Cheikh, Zhaohui Wang
Submitted On:
15 September 2017 - 11:58am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster

(16 downloads)

Keywords

Subscribe

[1] Ahmed Kedir Mohammed, Faouzi Alaya Cheikh, Zhaohui Wang, "A HIERARCHICAL FEATURE MODEL FOR MULTI-TARGET TRACKING", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2149. Accessed: Oct. 19, 2017.
@article{2149-17,
url = {http://sigport.org/2149},
author = {Ahmed Kedir Mohammed; Faouzi Alaya Cheikh; Zhaohui Wang },
publisher = {IEEE SigPort},
title = {A HIERARCHICAL FEATURE MODEL FOR MULTI-TARGET TRACKING},
year = {2017} }
TY - EJOUR
T1 - A HIERARCHICAL FEATURE MODEL FOR MULTI-TARGET TRACKING
AU - Ahmed Kedir Mohammed; Faouzi Alaya Cheikh; Zhaohui Wang
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2149
ER -
Ahmed Kedir Mohammed, Faouzi Alaya Cheikh, Zhaohui Wang. (2017). A HIERARCHICAL FEATURE MODEL FOR MULTI-TARGET TRACKING. IEEE SigPort. http://sigport.org/2149
Ahmed Kedir Mohammed, Faouzi Alaya Cheikh, Zhaohui Wang, 2017. A HIERARCHICAL FEATURE MODEL FOR MULTI-TARGET TRACKING. Available at: http://sigport.org/2149.
Ahmed Kedir Mohammed, Faouzi Alaya Cheikh, Zhaohui Wang. (2017). "A HIERARCHICAL FEATURE MODEL FOR MULTI-TARGET TRACKING." Web.
1. Ahmed Kedir Mohammed, Faouzi Alaya Cheikh, Zhaohui Wang. A HIERARCHICAL FEATURE MODEL FOR MULTI-TARGET TRACKING [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2149

Paper1134 WIDE-ANGLE IMAGE STITCHING USING MULTI-HOMOGRAPHY WARPING

Paper Details

Authors:
Bin Xu, Yunde Jia
Submitted On:
15 September 2017 - 11:38am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2017-Paper1134-Slides

(18 downloads)

Keywords

Subscribe

[1] Bin Xu, Yunde Jia, "Paper1134 WIDE-ANGLE IMAGE STITCHING USING MULTI-HOMOGRAPHY WARPING", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2143. Accessed: Oct. 19, 2017.
@article{2143-17,
url = {http://sigport.org/2143},
author = {Bin Xu; Yunde Jia },
publisher = {IEEE SigPort},
title = {Paper1134 WIDE-ANGLE IMAGE STITCHING USING MULTI-HOMOGRAPHY WARPING},
year = {2017} }
TY - EJOUR
T1 - Paper1134 WIDE-ANGLE IMAGE STITCHING USING MULTI-HOMOGRAPHY WARPING
AU - Bin Xu; Yunde Jia
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2143
ER -
Bin Xu, Yunde Jia. (2017). Paper1134 WIDE-ANGLE IMAGE STITCHING USING MULTI-HOMOGRAPHY WARPING. IEEE SigPort. http://sigport.org/2143
Bin Xu, Yunde Jia, 2017. Paper1134 WIDE-ANGLE IMAGE STITCHING USING MULTI-HOMOGRAPHY WARPING. Available at: http://sigport.org/2143.
Bin Xu, Yunde Jia. (2017). "Paper1134 WIDE-ANGLE IMAGE STITCHING USING MULTI-HOMOGRAPHY WARPING." Web.
1. Bin Xu, Yunde Jia. Paper1134 WIDE-ANGLE IMAGE STITCHING USING MULTI-HOMOGRAPHY WARPING [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2143

GraDED_ICIP17

Paper Details

Authors:
Tamal Batabyal, Rituparna Sarkar, Scott T. Acton
Submitted On:
15 September 2017 - 11:28am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Graph-based dictionary learning for event detection (Prof. Scott T. Acton, University of Virginia))

(13 downloads)

Keywords

Subscribe

[1] Tamal Batabyal, Rituparna Sarkar, Scott T. Acton, "GraDED_ICIP17", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2142. Accessed: Oct. 19, 2017.
@article{2142-17,
url = {http://sigport.org/2142},
author = {Tamal Batabyal; Rituparna Sarkar; Scott T. Acton },
publisher = {IEEE SigPort},
title = {GraDED_ICIP17},
year = {2017} }
TY - EJOUR
T1 - GraDED_ICIP17
AU - Tamal Batabyal; Rituparna Sarkar; Scott T. Acton
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2142
ER -
Tamal Batabyal, Rituparna Sarkar, Scott T. Acton. (2017). GraDED_ICIP17. IEEE SigPort. http://sigport.org/2142
Tamal Batabyal, Rituparna Sarkar, Scott T. Acton, 2017. GraDED_ICIP17. Available at: http://sigport.org/2142.
Tamal Batabyal, Rituparna Sarkar, Scott T. Acton. (2017). "GraDED_ICIP17." Web.
1. Tamal Batabyal, Rituparna Sarkar, Scott T. Acton. GraDED_ICIP17 [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2142

CGAN-Plankton: Towards Large-scale Imbalanced Class Generation and Fine-Grained Classification

Paper Details

Authors:
Chao Wang, Zhibin Yu, Haiyong Zheng, Nan Wang, Bing Zheng
Submitted On:
15 September 2017 - 11:14am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2017_paper_1866.pdf

(24 downloads)

Keywords

Subscribe

[1] Chao Wang, Zhibin Yu, Haiyong Zheng, Nan Wang, Bing Zheng, "CGAN-Plankton: Towards Large-scale Imbalanced Class Generation and Fine-Grained Classification", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2141. Accessed: Oct. 19, 2017.
@article{2141-17,
url = {http://sigport.org/2141},
author = {Chao Wang; Zhibin Yu; Haiyong Zheng; Nan Wang; Bing Zheng },
publisher = {IEEE SigPort},
title = {CGAN-Plankton: Towards Large-scale Imbalanced Class Generation and Fine-Grained Classification},
year = {2017} }
TY - EJOUR
T1 - CGAN-Plankton: Towards Large-scale Imbalanced Class Generation and Fine-Grained Classification
AU - Chao Wang; Zhibin Yu; Haiyong Zheng; Nan Wang; Bing Zheng
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2141
ER -
Chao Wang, Zhibin Yu, Haiyong Zheng, Nan Wang, Bing Zheng. (2017). CGAN-Plankton: Towards Large-scale Imbalanced Class Generation and Fine-Grained Classification. IEEE SigPort. http://sigport.org/2141
Chao Wang, Zhibin Yu, Haiyong Zheng, Nan Wang, Bing Zheng, 2017. CGAN-Plankton: Towards Large-scale Imbalanced Class Generation and Fine-Grained Classification. Available at: http://sigport.org/2141.
Chao Wang, Zhibin Yu, Haiyong Zheng, Nan Wang, Bing Zheng. (2017). "CGAN-Plankton: Towards Large-scale Imbalanced Class Generation and Fine-Grained Classification." Web.
1. Chao Wang, Zhibin Yu, Haiyong Zheng, Nan Wang, Bing Zheng. CGAN-Plankton: Towards Large-scale Imbalanced Class Generation and Fine-Grained Classification [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2141

Context-aware cascade network for semantic labeling in VHR image


Semantic labeling for the very high resolution (VHR) image of urban areas is challenging, because of many complex man-made objects with different materials and fine-structured ob-jects located together. Under the framework of convolutional neural networks (CNNs), this paper proposes a novel end-to-end network for semantic labeling.

Paper Details

Authors:
Yongcheng Liu, Bin Fan, Lingfeng Wang, Jun Bai, Shiming Xiang, Chunhong Pan
Submitted On:
15 September 2017 - 9:54am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2017ICIP_Lecture.pdf

(17 downloads)

Keywords

Additional Categories

Subscribe

[1] Yongcheng Liu, Bin Fan, Lingfeng Wang, Jun Bai, Shiming Xiang, Chunhong Pan, "Context-aware cascade network for semantic labeling in VHR image", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2136. Accessed: Oct. 19, 2017.
@article{2136-17,
url = {http://sigport.org/2136},
author = {Yongcheng Liu; Bin Fan; Lingfeng Wang; Jun Bai; Shiming Xiang; Chunhong Pan },
publisher = {IEEE SigPort},
title = {Context-aware cascade network for semantic labeling in VHR image},
year = {2017} }
TY - EJOUR
T1 - Context-aware cascade network for semantic labeling in VHR image
AU - Yongcheng Liu; Bin Fan; Lingfeng Wang; Jun Bai; Shiming Xiang; Chunhong Pan
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2136
ER -
Yongcheng Liu, Bin Fan, Lingfeng Wang, Jun Bai, Shiming Xiang, Chunhong Pan. (2017). Context-aware cascade network for semantic labeling in VHR image. IEEE SigPort. http://sigport.org/2136
Yongcheng Liu, Bin Fan, Lingfeng Wang, Jun Bai, Shiming Xiang, Chunhong Pan, 2017. Context-aware cascade network for semantic labeling in VHR image. Available at: http://sigport.org/2136.
Yongcheng Liu, Bin Fan, Lingfeng Wang, Jun Bai, Shiming Xiang, Chunhong Pan. (2017). "Context-aware cascade network for semantic labeling in VHR image." Web.
1. Yongcheng Liu, Bin Fan, Lingfeng Wang, Jun Bai, Shiming Xiang, Chunhong Pan. Context-aware cascade network for semantic labeling in VHR image [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2136

A New Fusion Method For Remote Sensing Images Based On Salient Region Extraction

Paper Details

Authors:
Submitted On:
15 September 2017 - 9:09am
Short Link:
Type:
Event:

Document Files

ICIP2017_1924.pdf

(9 downloads)

Keywords

Subscribe

[1] , "A New Fusion Method For Remote Sensing Images Based On Salient Region Extraction", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2134. Accessed: Oct. 19, 2017.
@article{2134-17,
url = {http://sigport.org/2134},
author = { },
publisher = {IEEE SigPort},
title = {A New Fusion Method For Remote Sensing Images Based On Salient Region Extraction},
year = {2017} }
TY - EJOUR
T1 - A New Fusion Method For Remote Sensing Images Based On Salient Region Extraction
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2134
ER -
. (2017). A New Fusion Method For Remote Sensing Images Based On Salient Region Extraction. IEEE SigPort. http://sigport.org/2134
, 2017. A New Fusion Method For Remote Sensing Images Based On Salient Region Extraction. Available at: http://sigport.org/2134.
. (2017). "A New Fusion Method For Remote Sensing Images Based On Salient Region Extraction." Web.
1. . A New Fusion Method For Remote Sensing Images Based On Salient Region Extraction [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2134

ACCURATE MESH-BASED ALIGNMENT FOR GROUND AND AERIAL MULTI-VIEW STEREO MODELS


We propose a method for accurate alignment of ground and aerial multi-view stereo (MVS) models. We achieve this goal by reconstructing the surface meshes from MVS point clouds generated by aerial and ground images respectively, and then iteratively removing the gap between them. The key issue is how to establish reliable correspondences between two meshes.

Paper Details

Authors:
Yang Zhou, Shuhan shen, Xiang Gao, Zhanyi Hu
Submitted On:
15 September 2017 - 8:51am
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

ICIP_poster.pdf

(12 downloads)

Keywords

Additional Categories

Subscribe

[1] Yang Zhou, Shuhan shen, Xiang Gao, Zhanyi Hu, "ACCURATE MESH-BASED ALIGNMENT FOR GROUND AND AERIAL MULTI-VIEW STEREO MODELS", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2130. Accessed: Oct. 19, 2017.
@article{2130-17,
url = {http://sigport.org/2130},
author = {Yang Zhou; Shuhan shen; Xiang Gao; Zhanyi Hu },
publisher = {IEEE SigPort},
title = {ACCURATE MESH-BASED ALIGNMENT FOR GROUND AND AERIAL MULTI-VIEW STEREO MODELS},
year = {2017} }
TY - EJOUR
T1 - ACCURATE MESH-BASED ALIGNMENT FOR GROUND AND AERIAL MULTI-VIEW STEREO MODELS
AU - Yang Zhou; Shuhan shen; Xiang Gao; Zhanyi Hu
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2130
ER -
Yang Zhou, Shuhan shen, Xiang Gao, Zhanyi Hu. (2017). ACCURATE MESH-BASED ALIGNMENT FOR GROUND AND AERIAL MULTI-VIEW STEREO MODELS. IEEE SigPort. http://sigport.org/2130
Yang Zhou, Shuhan shen, Xiang Gao, Zhanyi Hu, 2017. ACCURATE MESH-BASED ALIGNMENT FOR GROUND AND AERIAL MULTI-VIEW STEREO MODELS. Available at: http://sigport.org/2130.
Yang Zhou, Shuhan shen, Xiang Gao, Zhanyi Hu. (2017). "ACCURATE MESH-BASED ALIGNMENT FOR GROUND AND AERIAL MULTI-VIEW STEREO MODELS." Web.
1. Yang Zhou, Shuhan shen, Xiang Gao, Zhanyi Hu. ACCURATE MESH-BASED ALIGNMENT FOR GROUND AND AERIAL MULTI-VIEW STEREO MODELS [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2130

COMPLEX COEFFICIENT REPRESENTATION FOR IIR BILATERAL FILTER


In this paper, we propose an infinite impulse response (IIR)
filtering with complex coefficients for Euclid distance based
filtering, e.g. bilateral filtering. Recursive filtering of edgepreserving
filtering is the most efficient filtering. Recursive
bilateral filtering and domain transform filtering belong to
this type. These filters measure the difference between pixel
intensities by geodesic distance. Also, these filters do not
have separability. The aspects make the filter sensitive to

Paper Details

Authors:
Norishige Fukushima, Kenjiro Sugimoto, Sei-ichiro Kamata
Submitted On:
15 September 2017 - 8:43am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icip_fukushima.pdf

(11 downloads)

Keywords

Subscribe

[1] Norishige Fukushima, Kenjiro Sugimoto, Sei-ichiro Kamata, "COMPLEX COEFFICIENT REPRESENTATION FOR IIR BILATERAL FILTER", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2129. Accessed: Oct. 19, 2017.
@article{2129-17,
url = {http://sigport.org/2129},
author = {Norishige Fukushima; Kenjiro Sugimoto; Sei-ichiro Kamata },
publisher = {IEEE SigPort},
title = {COMPLEX COEFFICIENT REPRESENTATION FOR IIR BILATERAL FILTER},
year = {2017} }
TY - EJOUR
T1 - COMPLEX COEFFICIENT REPRESENTATION FOR IIR BILATERAL FILTER
AU - Norishige Fukushima; Kenjiro Sugimoto; Sei-ichiro Kamata
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2129
ER -
Norishige Fukushima, Kenjiro Sugimoto, Sei-ichiro Kamata. (2017). COMPLEX COEFFICIENT REPRESENTATION FOR IIR BILATERAL FILTER. IEEE SigPort. http://sigport.org/2129
Norishige Fukushima, Kenjiro Sugimoto, Sei-ichiro Kamata, 2017. COMPLEX COEFFICIENT REPRESENTATION FOR IIR BILATERAL FILTER. Available at: http://sigport.org/2129.
Norishige Fukushima, Kenjiro Sugimoto, Sei-ichiro Kamata. (2017). "COMPLEX COEFFICIENT REPRESENTATION FOR IIR BILATERAL FILTER." Web.
1. Norishige Fukushima, Kenjiro Sugimoto, Sei-ichiro Kamata. COMPLEX COEFFICIENT REPRESENTATION FOR IIR BILATERAL FILTER [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2129

Trademark Image Retrieval Using Hierarchical Region Feature Description


A novel trademark image retrieval(TIR) method is proposed in this work. The proposed approach commences with region partitioning through rotationally capturing multi-level regions of an image in a hierarchical manner, and then an effective region measurement is used as shape description of the regions generated from region partitioning stage. A shifting feature matching strategy is used to evaluate the similarity between the query and database images. The experimental results on the standard shape databases demonstrate its superiority performance over the state-of-the-art approaches.

Paper Details

Authors:
Feng Liu,Bin Wang,Fanqing Zeng
Submitted On:
15 September 2017 - 7:45am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

paper3209_poster.pdf

(10 downloads)

Keywords

Subscribe

[1] Feng Liu,Bin Wang,Fanqing Zeng, "Trademark Image Retrieval Using Hierarchical Region Feature Description", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2127. Accessed: Oct. 19, 2017.
@article{2127-17,
url = {http://sigport.org/2127},
author = {Feng Liu;Bin Wang;Fanqing Zeng },
publisher = {IEEE SigPort},
title = {Trademark Image Retrieval Using Hierarchical Region Feature Description},
year = {2017} }
TY - EJOUR
T1 - Trademark Image Retrieval Using Hierarchical Region Feature Description
AU - Feng Liu;Bin Wang;Fanqing Zeng
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2127
ER -
Feng Liu,Bin Wang,Fanqing Zeng. (2017). Trademark Image Retrieval Using Hierarchical Region Feature Description. IEEE SigPort. http://sigport.org/2127
Feng Liu,Bin Wang,Fanqing Zeng, 2017. Trademark Image Retrieval Using Hierarchical Region Feature Description. Available at: http://sigport.org/2127.
Feng Liu,Bin Wang,Fanqing Zeng. (2017). "Trademark Image Retrieval Using Hierarchical Region Feature Description." Web.
1. Feng Liu,Bin Wang,Fanqing Zeng. Trademark Image Retrieval Using Hierarchical Region Feature Description [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2127

Pages