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

Image/Video Storage, Retrieval

Learning Search Path for Region-Level Image Matching

Paper Details

Authors:
Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino
Submitted On:
20 May 2019 - 10:45pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

icassp_19_poster_onkar.pdf

(36)

Subscribe

[1] Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino , "Learning Search Path for Region-Level Image Matching", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4555. Accessed: Aug. 23, 2019.
@article{4555-19,
url = {http://sigport.org/4555},
author = {Onkar Krishna; Go Irie; Xiaomeng Wu; Takahito Kawanishi; Kunio Kashino },
publisher = {IEEE SigPort},
title = {Learning Search Path for Region-Level Image Matching},
year = {2019} }
TY - EJOUR
T1 - Learning Search Path for Region-Level Image Matching
AU - Onkar Krishna; Go Irie; Xiaomeng Wu; Takahito Kawanishi; Kunio Kashino
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4555
ER -
Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino . (2019). Learning Search Path for Region-Level Image Matching. IEEE SigPort. http://sigport.org/4555
Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino , 2019. Learning Search Path for Region-Level Image Matching. Available at: http://sigport.org/4555.
Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino . (2019). "Learning Search Path for Region-Level Image Matching." Web.
1. Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino . Learning Search Path for Region-Level Image Matching [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4555

Learning Search Path for Region-Level Image Matching

Paper Details

Authors:
Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino
Submitted On:
20 May 2019 - 10:45pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP_19 poster

(21)

Subscribe

[1] Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino , "Learning Search Path for Region-Level Image Matching", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4554. Accessed: Aug. 23, 2019.
@article{4554-19,
url = {http://sigport.org/4554},
author = {Onkar Krishna; Go Irie; Xiaomeng Wu; Takahito Kawanishi; Kunio Kashino },
publisher = {IEEE SigPort},
title = {Learning Search Path for Region-Level Image Matching},
year = {2019} }
TY - EJOUR
T1 - Learning Search Path for Region-Level Image Matching
AU - Onkar Krishna; Go Irie; Xiaomeng Wu; Takahito Kawanishi; Kunio Kashino
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4554
ER -
Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino . (2019). Learning Search Path for Region-Level Image Matching. IEEE SigPort. http://sigport.org/4554
Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino , 2019. Learning Search Path for Region-Level Image Matching. Available at: http://sigport.org/4554.
Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino . (2019). "Learning Search Path for Region-Level Image Matching." Web.
1. Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino . Learning Search Path for Region-Level Image Matching [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4554

Gradient Image Super-Resolution for Low-Resolution Image Recognition


In visual object recognition problems essential to surveillance and navigation problems in a variety of military and civilian use cases,low-resolution and low-quality images present great challenges to this problem. Recent advancements in deep learning based methods like EDSR/VDSR have boosted pixel domain image super-resolution(SR) performances significantly in terms of signal to noise ratio(SNR)/mean square error(MSE) metrics of the super-resolved image.

Paper Details

Authors:
Dewan Fahim Noor, Yue Li, Zhu Li, Shuvra Bhattacharyya, George York
Submitted On:
10 May 2019 - 3:40pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Gradient_image_SR_icassp.pdf

(21)

Subscribe

[1] Dewan Fahim Noor, Yue Li, Zhu Li, Shuvra Bhattacharyya, George York, "Gradient Image Super-Resolution for Low-Resolution Image Recognition", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4395. Accessed: Aug. 23, 2019.
@article{4395-19,
url = {http://sigport.org/4395},
author = {Dewan Fahim Noor; Yue Li; Zhu Li; Shuvra Bhattacharyya; George York },
publisher = {IEEE SigPort},
title = {Gradient Image Super-Resolution for Low-Resolution Image Recognition},
year = {2019} }
TY - EJOUR
T1 - Gradient Image Super-Resolution for Low-Resolution Image Recognition
AU - Dewan Fahim Noor; Yue Li; Zhu Li; Shuvra Bhattacharyya; George York
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4395
ER -
Dewan Fahim Noor, Yue Li, Zhu Li, Shuvra Bhattacharyya, George York. (2019). Gradient Image Super-Resolution for Low-Resolution Image Recognition. IEEE SigPort. http://sigport.org/4395
Dewan Fahim Noor, Yue Li, Zhu Li, Shuvra Bhattacharyya, George York, 2019. Gradient Image Super-Resolution for Low-Resolution Image Recognition. Available at: http://sigport.org/4395.
Dewan Fahim Noor, Yue Li, Zhu Li, Shuvra Bhattacharyya, George York. (2019). "Gradient Image Super-Resolution for Low-Resolution Image Recognition." Web.
1. Dewan Fahim Noor, Yue Li, Zhu Li, Shuvra Bhattacharyya, George York. Gradient Image Super-Resolution for Low-Resolution Image Recognition [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4395

CONVOLUTIONAL-SPARSE-CODED DYNAMIC MODE DECOMPOSITION AND ITS APPLICATION TO RIVER STATE ESTIMATION


This work proposes convolutional-sparse-coded dynamic mode decomposition (CSC-DMD) by unifying extended dynamic mode de-

Paper Details

Authors:
Yuhei Kaneko,Shogo Muramatsu,Hiroyasu Yasuda,Kiyoshi Hayasaka,Yu Otake,Shunsuke Ono,Masahiro Yukawa
Submitted On:
10 May 2019 - 10:09am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster_20190514.pdf

(31)

Subscribe

[1] Yuhei Kaneko,Shogo Muramatsu,Hiroyasu Yasuda,Kiyoshi Hayasaka,Yu Otake,Shunsuke Ono,Masahiro Yukawa, "CONVOLUTIONAL-SPARSE-CODED DYNAMIC MODE DECOMPOSITION AND ITS APPLICATION TO RIVER STATE ESTIMATION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4339. Accessed: Aug. 23, 2019.
@article{4339-19,
url = {http://sigport.org/4339},
author = { Yuhei Kaneko;Shogo Muramatsu;Hiroyasu Yasuda;Kiyoshi Hayasaka;Yu Otake;Shunsuke Ono;Masahiro Yukawa },
publisher = {IEEE SigPort},
title = {CONVOLUTIONAL-SPARSE-CODED DYNAMIC MODE DECOMPOSITION AND ITS APPLICATION TO RIVER STATE ESTIMATION},
year = {2019} }
TY - EJOUR
T1 - CONVOLUTIONAL-SPARSE-CODED DYNAMIC MODE DECOMPOSITION AND ITS APPLICATION TO RIVER STATE ESTIMATION
AU - Yuhei Kaneko;Shogo Muramatsu;Hiroyasu Yasuda;Kiyoshi Hayasaka;Yu Otake;Shunsuke Ono;Masahiro Yukawa
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4339
ER -
Yuhei Kaneko,Shogo Muramatsu,Hiroyasu Yasuda,Kiyoshi Hayasaka,Yu Otake,Shunsuke Ono,Masahiro Yukawa. (2019). CONVOLUTIONAL-SPARSE-CODED DYNAMIC MODE DECOMPOSITION AND ITS APPLICATION TO RIVER STATE ESTIMATION. IEEE SigPort. http://sigport.org/4339
Yuhei Kaneko,Shogo Muramatsu,Hiroyasu Yasuda,Kiyoshi Hayasaka,Yu Otake,Shunsuke Ono,Masahiro Yukawa, 2019. CONVOLUTIONAL-SPARSE-CODED DYNAMIC MODE DECOMPOSITION AND ITS APPLICATION TO RIVER STATE ESTIMATION. Available at: http://sigport.org/4339.
Yuhei Kaneko,Shogo Muramatsu,Hiroyasu Yasuda,Kiyoshi Hayasaka,Yu Otake,Shunsuke Ono,Masahiro Yukawa. (2019). "CONVOLUTIONAL-SPARSE-CODED DYNAMIC MODE DECOMPOSITION AND ITS APPLICATION TO RIVER STATE ESTIMATION." Web.
1. Yuhei Kaneko,Shogo Muramatsu,Hiroyasu Yasuda,Kiyoshi Hayasaka,Yu Otake,Shunsuke Ono,Masahiro Yukawa. CONVOLUTIONAL-SPARSE-CODED DYNAMIC MODE DECOMPOSITION AND ITS APPLICATION TO RIVER STATE ESTIMATION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4339

Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks


The task of Language-Based Image Editing (LBIE) aims at generating a target image by editing the source image based on the given language description. The main challenge of LBIE is to disentangle the semantics in image and text and then combine them to generate realistic images. Therefore, the editing performance is heavily dependent on the learned representation.

Paper Details

Authors:
Yuefeng Chen, Yuhong Li, Tao Xiong, Yuan He, Hui Xue
Submitted On:
10 May 2019 - 9:23am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp_poster_改.pdf

(26)

Subscribe

[1] Yuefeng Chen, Yuhong Li, Tao Xiong, Yuan He, Hui Xue, "Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4327. Accessed: Aug. 23, 2019.
@article{4327-19,
url = {http://sigport.org/4327},
author = {Yuefeng Chen; Yuhong Li; Tao Xiong; Yuan He; Hui Xue },
publisher = {IEEE SigPort},
title = {Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks},
year = {2019} }
TY - EJOUR
T1 - Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks
AU - Yuefeng Chen; Yuhong Li; Tao Xiong; Yuan He; Hui Xue
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4327
ER -
Yuefeng Chen, Yuhong Li, Tao Xiong, Yuan He, Hui Xue. (2019). Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks. IEEE SigPort. http://sigport.org/4327
Yuefeng Chen, Yuhong Li, Tao Xiong, Yuan He, Hui Xue, 2019. Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks. Available at: http://sigport.org/4327.
Yuefeng Chen, Yuhong Li, Tao Xiong, Yuan He, Hui Xue. (2019). "Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks." Web.
1. Yuefeng Chen, Yuhong Li, Tao Xiong, Yuan He, Hui Xue. Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4327

Learning Search Path for Region-Level Image Matching

Paper Details

Authors:
Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino
Submitted On:
10 May 2019 - 6:36am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

icassp_19_poster_onkar.pdf

(21)

Subscribe

[1] Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino , "Learning Search Path for Region-Level Image Matching", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4300. Accessed: Aug. 23, 2019.
@article{4300-19,
url = {http://sigport.org/4300},
author = {Onkar Krishna; Go Irie; Xiaomeng Wu; Takahito Kawanishi; Kunio Kashino },
publisher = {IEEE SigPort},
title = {Learning Search Path for Region-Level Image Matching},
year = {2019} }
TY - EJOUR
T1 - Learning Search Path for Region-Level Image Matching
AU - Onkar Krishna; Go Irie; Xiaomeng Wu; Takahito Kawanishi; Kunio Kashino
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4300
ER -
Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino . (2019). Learning Search Path for Region-Level Image Matching. IEEE SigPort. http://sigport.org/4300
Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino , 2019. Learning Search Path for Region-Level Image Matching. Available at: http://sigport.org/4300.
Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino . (2019). "Learning Search Path for Region-Level Image Matching." Web.
1. Onkar Krishna, Go Irie, Xiaomeng Wu, Takahito Kawanishi, Kunio Kashino . Learning Search Path for Region-Level Image Matching [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4300

PROPER GUIDANCE IMAGE GENERATION BASED ON SALIENCY FACTOR FOR BETTER TRANSMISSION REFINEMENT IN IMAGE DEHAZING


Guided image filter is one of the most commonly used ways to refine transmission maps. However, since this filter transfers the structures of the guidance image to the filtering output, when the guidance image is the input image itself, even small textures in the input image will cause the change of transmission, which is obviously contrary to the principle that transmission changes only when scene depth changes. In this paper, saliency detection, which simulates the way human eyes work, is introduced into haze removal to tackle the above issue.

Paper Details

Authors:
Submitted On:
10 May 2019 - 6:30am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2526.pdf

(24)

Subscribe

[1] , "PROPER GUIDANCE IMAGE GENERATION BASED ON SALIENCY FACTOR FOR BETTER TRANSMISSION REFINEMENT IN IMAGE DEHAZING", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4299. Accessed: Aug. 23, 2019.
@article{4299-19,
url = {http://sigport.org/4299},
author = { },
publisher = {IEEE SigPort},
title = {PROPER GUIDANCE IMAGE GENERATION BASED ON SALIENCY FACTOR FOR BETTER TRANSMISSION REFINEMENT IN IMAGE DEHAZING},
year = {2019} }
TY - EJOUR
T1 - PROPER GUIDANCE IMAGE GENERATION BASED ON SALIENCY FACTOR FOR BETTER TRANSMISSION REFINEMENT IN IMAGE DEHAZING
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4299
ER -
. (2019). PROPER GUIDANCE IMAGE GENERATION BASED ON SALIENCY FACTOR FOR BETTER TRANSMISSION REFINEMENT IN IMAGE DEHAZING. IEEE SigPort. http://sigport.org/4299
, 2019. PROPER GUIDANCE IMAGE GENERATION BASED ON SALIENCY FACTOR FOR BETTER TRANSMISSION REFINEMENT IN IMAGE DEHAZING. Available at: http://sigport.org/4299.
. (2019). "PROPER GUIDANCE IMAGE GENERATION BASED ON SALIENCY FACTOR FOR BETTER TRANSMISSION REFINEMENT IN IMAGE DEHAZING." Web.
1. . PROPER GUIDANCE IMAGE GENERATION BASED ON SALIENCY FACTOR FOR BETTER TRANSMISSION REFINEMENT IN IMAGE DEHAZING [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4299

Image Reflection Removal Using The Wasserstein Generative Adversarial Network


Imaging through a semi-transparent material such as glass often suffers from the reflection problem, which degrades the image quality. Reflection removal is a challenging task since it is severely ill-posed. Traditional methods, while all require long computation time on minimizing different objective functions with huge matrices, do not necessarily give satisfactory performance. In this paper, we propose a novel deep-learning based method to allow fast removal of reflection.

Paper Details

Authors:
Tingtian Li, Daniel P.K. Lun
Submitted On:
9 May 2019 - 10:41am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Image Reflection Removal Using The Wasserstein Generative Adversarial Network.pdf

(39)

Subscribe

[1] Tingtian Li, Daniel P.K. Lun, "Image Reflection Removal Using The Wasserstein Generative Adversarial Network", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4190. Accessed: Aug. 23, 2019.
@article{4190-19,
url = {http://sigport.org/4190},
author = {Tingtian Li; Daniel P.K. Lun },
publisher = {IEEE SigPort},
title = {Image Reflection Removal Using The Wasserstein Generative Adversarial Network},
year = {2019} }
TY - EJOUR
T1 - Image Reflection Removal Using The Wasserstein Generative Adversarial Network
AU - Tingtian Li; Daniel P.K. Lun
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4190
ER -
Tingtian Li, Daniel P.K. Lun. (2019). Image Reflection Removal Using The Wasserstein Generative Adversarial Network. IEEE SigPort. http://sigport.org/4190
Tingtian Li, Daniel P.K. Lun, 2019. Image Reflection Removal Using The Wasserstein Generative Adversarial Network. Available at: http://sigport.org/4190.
Tingtian Li, Daniel P.K. Lun. (2019). "Image Reflection Removal Using The Wasserstein Generative Adversarial Network." Web.
1. Tingtian Li, Daniel P.K. Lun. Image Reflection Removal Using The Wasserstein Generative Adversarial Network [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4190

MULTI-SCALE SPATIAL-TEMPORAL NETWORK FOR PERSON RE-IDENTIFICATION

Paper Details

Authors:
Lihuo He, Xinbo Gao, Yuanfei Huang
Submitted On:
8 May 2019 - 9:06am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

paper

(26)

Subscribe

[1] Lihuo He, Xinbo Gao, Yuanfei Huang, "MULTI-SCALE SPATIAL-TEMPORAL NETWORK FOR PERSON RE-IDENTIFICATION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4090. Accessed: Aug. 23, 2019.
@article{4090-19,
url = {http://sigport.org/4090},
author = {Lihuo He; Xinbo Gao; Yuanfei Huang },
publisher = {IEEE SigPort},
title = {MULTI-SCALE SPATIAL-TEMPORAL NETWORK FOR PERSON RE-IDENTIFICATION},
year = {2019} }
TY - EJOUR
T1 - MULTI-SCALE SPATIAL-TEMPORAL NETWORK FOR PERSON RE-IDENTIFICATION
AU - Lihuo He; Xinbo Gao; Yuanfei Huang
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4090
ER -
Lihuo He, Xinbo Gao, Yuanfei Huang. (2019). MULTI-SCALE SPATIAL-TEMPORAL NETWORK FOR PERSON RE-IDENTIFICATION. IEEE SigPort. http://sigport.org/4090
Lihuo He, Xinbo Gao, Yuanfei Huang, 2019. MULTI-SCALE SPATIAL-TEMPORAL NETWORK FOR PERSON RE-IDENTIFICATION. Available at: http://sigport.org/4090.
Lihuo He, Xinbo Gao, Yuanfei Huang. (2019). "MULTI-SCALE SPATIAL-TEMPORAL NETWORK FOR PERSON RE-IDENTIFICATION." Web.
1. Lihuo He, Xinbo Gao, Yuanfei Huang. MULTI-SCALE SPATIAL-TEMPORAL NETWORK FOR PERSON RE-IDENTIFICATION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4090

DEEP TEMPORAL PYRAMID DESIGN FOR ACTION RECOGNITION


Deep convolutional neural networks (CNNs) are nowadays achieving significant leaps in different pattern recognition tasks including action recognition. Current CNNs are increasingly deeper, data-hungrier and this makes their success tributary of the abundance of labeled training data. CNNs also rely on max/average pooling which reduces dimensionality of output layers and hence attenuates their sensitivity to the availability of labeled data.

Paper Details

Authors:
Ahmed Mazari, Hichem Sahbi
Submitted On:
7 May 2019 - 5:45pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Poster_ICASSP19_Action_Recognition.pdf

(24)

Subscribe

[1] Ahmed Mazari, Hichem Sahbi, "DEEP TEMPORAL PYRAMID DESIGN FOR ACTION RECOGNITION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3961. Accessed: Aug. 23, 2019.
@article{3961-19,
url = {http://sigport.org/3961},
author = {Ahmed Mazari; Hichem Sahbi },
publisher = {IEEE SigPort},
title = {DEEP TEMPORAL PYRAMID DESIGN FOR ACTION RECOGNITION},
year = {2019} }
TY - EJOUR
T1 - DEEP TEMPORAL PYRAMID DESIGN FOR ACTION RECOGNITION
AU - Ahmed Mazari; Hichem Sahbi
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3961
ER -
Ahmed Mazari, Hichem Sahbi. (2019). DEEP TEMPORAL PYRAMID DESIGN FOR ACTION RECOGNITION. IEEE SigPort. http://sigport.org/3961
Ahmed Mazari, Hichem Sahbi, 2019. DEEP TEMPORAL PYRAMID DESIGN FOR ACTION RECOGNITION. Available at: http://sigport.org/3961.
Ahmed Mazari, Hichem Sahbi. (2019). "DEEP TEMPORAL PYRAMID DESIGN FOR ACTION RECOGNITION." Web.
1. Ahmed Mazari, Hichem Sahbi. DEEP TEMPORAL PYRAMID DESIGN FOR ACTION RECOGNITION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3961

Pages