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

Image/Video Processing

Temporal Salience Based Human Action Recognition


This paper proposes a new approach for human action recognition exploring the temporal salience. We exploit features over the temporal saliency maps for learning the action representation using a local dense descriptor. This approach automatically guides the descriptor towards the most interesting contents, i.e. the salience region, and obtains the action representation using solely the saliency information.

Paper Details

Authors:
Salah Al-Obaidi and Charith Abhayaratne
Submitted On:
10 May 2019 - 10:56am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:

Document Files

Poster at ICASSP 2019

(27)

Subscribe

[1] Salah Al-Obaidi and Charith Abhayaratne, "Temporal Salience Based Human Action Recognition", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4354. Accessed: Jul. 20, 2019.
@article{4354-19,
url = {http://sigport.org/4354},
author = {Salah Al-Obaidi and Charith Abhayaratne },
publisher = {IEEE SigPort},
title = {Temporal Salience Based Human Action Recognition},
year = {2019} }
TY - EJOUR
T1 - Temporal Salience Based Human Action Recognition
AU - Salah Al-Obaidi and Charith Abhayaratne
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4354
ER -
Salah Al-Obaidi and Charith Abhayaratne. (2019). Temporal Salience Based Human Action Recognition. IEEE SigPort. http://sigport.org/4354
Salah Al-Obaidi and Charith Abhayaratne, 2019. Temporal Salience Based Human Action Recognition. Available at: http://sigport.org/4354.
Salah Al-Obaidi and Charith Abhayaratne. (2019). "Temporal Salience Based Human Action Recognition." Web.
1. Salah Al-Obaidi and Charith Abhayaratne. Temporal Salience Based Human Action Recognition [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4354

NEUROMORPHIC VISION SENSING FOR CNN-BASED ACTION RECOGNITION


Neuromorphic vision sensing (NVS) hardware is now gaining traction as a low-power/high-speed visual sensing technology that circumvents the limitations of conventional active pixel sensing (APS) cameras. While object detection and tracking models have been investigated in conjunction with NVS, there is currently little work on NVS for higher-level semantic tasks, such as action recognition.

Paper Details

Authors:
Aaron Chadha, Yin Bi, Alhabib Abbas, Yiannis Andreopoulos
Submitted On:
10 May 2019 - 9:31am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

NEUROMORPHIC VISION SENSING FOR CNN-BASED ACTION RECOGNITION.pdf

(30)

Subscribe

[1] Aaron Chadha, Yin Bi, Alhabib Abbas, Yiannis Andreopoulos, "NEUROMORPHIC VISION SENSING FOR CNN-BASED ACTION RECOGNITION ", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4328. Accessed: Jul. 20, 2019.
@article{4328-19,
url = {http://sigport.org/4328},
author = {Aaron Chadha; Yin Bi; Alhabib Abbas; Yiannis Andreopoulos },
publisher = {IEEE SigPort},
title = {NEUROMORPHIC VISION SENSING FOR CNN-BASED ACTION RECOGNITION },
year = {2019} }
TY - EJOUR
T1 - NEUROMORPHIC VISION SENSING FOR CNN-BASED ACTION RECOGNITION
AU - Aaron Chadha; Yin Bi; Alhabib Abbas; Yiannis Andreopoulos
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4328
ER -
Aaron Chadha, Yin Bi, Alhabib Abbas, Yiannis Andreopoulos. (2019). NEUROMORPHIC VISION SENSING FOR CNN-BASED ACTION RECOGNITION . IEEE SigPort. http://sigport.org/4328
Aaron Chadha, Yin Bi, Alhabib Abbas, Yiannis Andreopoulos, 2019. NEUROMORPHIC VISION SENSING FOR CNN-BASED ACTION RECOGNITION . Available at: http://sigport.org/4328.
Aaron Chadha, Yin Bi, Alhabib Abbas, Yiannis Andreopoulos. (2019). "NEUROMORPHIC VISION SENSING FOR CNN-BASED ACTION RECOGNITION ." Web.
1. Aaron Chadha, Yin Bi, Alhabib Abbas, Yiannis Andreopoulos. NEUROMORPHIC VISION SENSING FOR CNN-BASED ACTION RECOGNITION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4328

Motion-Adapted Three-Dimensional Frequency Selective Extrapolation

Paper Details

Authors:
Andreas Spruck, Markus Jonscher, Jürgen Seiler, André Kaup
Submitted On:
10 May 2019 - 4:08am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster_ICASSP.pdf

(17)

Subscribe

[1] Andreas Spruck, Markus Jonscher, Jürgen Seiler, André Kaup, "Motion-Adapted Three-Dimensional Frequency Selective Extrapolation", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4286. Accessed: Jul. 20, 2019.
@article{4286-19,
url = {http://sigport.org/4286},
author = {Andreas Spruck; Markus Jonscher; Jürgen Seiler; André Kaup },
publisher = {IEEE SigPort},
title = {Motion-Adapted Three-Dimensional Frequency Selective Extrapolation},
year = {2019} }
TY - EJOUR
T1 - Motion-Adapted Three-Dimensional Frequency Selective Extrapolation
AU - Andreas Spruck; Markus Jonscher; Jürgen Seiler; André Kaup
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4286
ER -
Andreas Spruck, Markus Jonscher, Jürgen Seiler, André Kaup. (2019). Motion-Adapted Three-Dimensional Frequency Selective Extrapolation. IEEE SigPort. http://sigport.org/4286
Andreas Spruck, Markus Jonscher, Jürgen Seiler, André Kaup, 2019. Motion-Adapted Three-Dimensional Frequency Selective Extrapolation. Available at: http://sigport.org/4286.
Andreas Spruck, Markus Jonscher, Jürgen Seiler, André Kaup. (2019). "Motion-Adapted Three-Dimensional Frequency Selective Extrapolation." Web.
1. Andreas Spruck, Markus Jonscher, Jürgen Seiler, André Kaup. Motion-Adapted Three-Dimensional Frequency Selective Extrapolation [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4286

E-CNN: Accurate Spherical Camera Rotation Estimation via Uniformization of Distorted Optical Flow Fields


Spherical cameras, which can acquire all-round information, are effective to estimate rotation for robotic applications. Recently, Convolutional Neural Networks have shown great robustness in solving such regression problems. However they are designed for planar images and cannot deal with the non-uniform distortion present in spherical images, when expressed in the planar equirectangular projection. This can lower the accuracy of motion estimation. In this research, we propose an Equirectangular-Convolutional Neural Network (E-CNN) to solve this issue.

Paper Details

Authors:
Alessandro Moro, Ren Komatsu, Atsushi Yamashita, Hajime Asama
Submitted On:
10 May 2019 - 4:16am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp2019_poster_dabaekim.pdf

(24)

Keywords

Additional Categories

Subscribe

[1] Alessandro Moro, Ren Komatsu, Atsushi Yamashita, Hajime Asama, "E-CNN: Accurate Spherical Camera Rotation Estimation via Uniformization of Distorted Optical Flow Fields", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4285. Accessed: Jul. 20, 2019.
@article{4285-19,
url = {http://sigport.org/4285},
author = {Alessandro Moro; Ren Komatsu; Atsushi Yamashita; Hajime Asama },
publisher = {IEEE SigPort},
title = {E-CNN: Accurate Spherical Camera Rotation Estimation via Uniformization of Distorted Optical Flow Fields},
year = {2019} }
TY - EJOUR
T1 - E-CNN: Accurate Spherical Camera Rotation Estimation via Uniformization of Distorted Optical Flow Fields
AU - Alessandro Moro; Ren Komatsu; Atsushi Yamashita; Hajime Asama
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4285
ER -
Alessandro Moro, Ren Komatsu, Atsushi Yamashita, Hajime Asama. (2019). E-CNN: Accurate Spherical Camera Rotation Estimation via Uniformization of Distorted Optical Flow Fields. IEEE SigPort. http://sigport.org/4285
Alessandro Moro, Ren Komatsu, Atsushi Yamashita, Hajime Asama, 2019. E-CNN: Accurate Spherical Camera Rotation Estimation via Uniformization of Distorted Optical Flow Fields. Available at: http://sigport.org/4285.
Alessandro Moro, Ren Komatsu, Atsushi Yamashita, Hajime Asama. (2019). "E-CNN: Accurate Spherical Camera Rotation Estimation via Uniformization of Distorted Optical Flow Fields." Web.
1. Alessandro Moro, Ren Komatsu, Atsushi Yamashita, Hajime Asama. E-CNN: Accurate Spherical Camera Rotation Estimation via Uniformization of Distorted Optical Flow Fields [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4285

FROM TV-L1 TO GATED RECURRENT NETS

Paper Details

Authors:
Submitted On:
9 May 2019 - 11:05pm
Short Link:
Type:
Event:
Paper Code:

Document Files

poster_3151.pdf

(17)

Subscribe

[1] , "FROM TV-L1 TO GATED RECURRENT NETS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4260. Accessed: Jul. 20, 2019.
@article{4260-19,
url = {http://sigport.org/4260},
author = { },
publisher = {IEEE SigPort},
title = {FROM TV-L1 TO GATED RECURRENT NETS},
year = {2019} }
TY - EJOUR
T1 - FROM TV-L1 TO GATED RECURRENT NETS
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4260
ER -
. (2019). FROM TV-L1 TO GATED RECURRENT NETS. IEEE SigPort. http://sigport.org/4260
, 2019. FROM TV-L1 TO GATED RECURRENT NETS. Available at: http://sigport.org/4260.
. (2019). "FROM TV-L1 TO GATED RECURRENT NETS." Web.
1. . FROM TV-L1 TO GATED RECURRENT NETS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4260

FROM TV-L1 TO GATED RECURRENT NETS

Paper Details

Authors:
Submitted On:
9 May 2019 - 11:05pm
Short Link:
Type:
Event:
Paper Code:

Document Files

poster_3151.pdf

(15)

Subscribe

[1] , "FROM TV-L1 TO GATED RECURRENT NETS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4259. Accessed: Jul. 20, 2019.
@article{4259-19,
url = {http://sigport.org/4259},
author = { },
publisher = {IEEE SigPort},
title = {FROM TV-L1 TO GATED RECURRENT NETS},
year = {2019} }
TY - EJOUR
T1 - FROM TV-L1 TO GATED RECURRENT NETS
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4259
ER -
. (2019). FROM TV-L1 TO GATED RECURRENT NETS. IEEE SigPort. http://sigport.org/4259
, 2019. FROM TV-L1 TO GATED RECURRENT NETS. Available at: http://sigport.org/4259.
. (2019). "FROM TV-L1 TO GATED RECURRENT NETS." Web.
1. . FROM TV-L1 TO GATED RECURRENT NETS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4259

Blind Quality Assessment for 3D-Synthesized Images by Measuring Geometric Distortions and Image Complexity


Free viewpoint video (FVV), owing to its comprehensive applications in immersive entertainment, remote surveillance and distanced education, has received extensive attention and been regarded as a new important direction of video technology development. Depth image-based rendering (DIBR) technologies are employed to synthesize FVV images in the “blind” environment. Therefore, a real-time reliable blind quality assessment metric is urgently required. However, existing stste-of-art quality assessment methods are limited to estimate geometric distortions generated by DIBR.

Paper Details

Authors:
Guangcheng Wang, Zhongyuan Wang, Ke Gu, Zhifang Xia
Submitted On:
9 May 2019 - 10:49pm
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

poster

(18)

Subscribe

[1] Guangcheng Wang, Zhongyuan Wang, Ke Gu, Zhifang Xia, "Blind Quality Assessment for 3D-Synthesized Images by Measuring Geometric Distortions and Image Complexity", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4253. Accessed: Jul. 20, 2019.
@article{4253-19,
url = {http://sigport.org/4253},
author = {Guangcheng Wang; Zhongyuan Wang; Ke Gu; Zhifang Xia },
publisher = {IEEE SigPort},
title = {Blind Quality Assessment for 3D-Synthesized Images by Measuring Geometric Distortions and Image Complexity},
year = {2019} }
TY - EJOUR
T1 - Blind Quality Assessment for 3D-Synthesized Images by Measuring Geometric Distortions and Image Complexity
AU - Guangcheng Wang; Zhongyuan Wang; Ke Gu; Zhifang Xia
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4253
ER -
Guangcheng Wang, Zhongyuan Wang, Ke Gu, Zhifang Xia. (2019). Blind Quality Assessment for 3D-Synthesized Images by Measuring Geometric Distortions and Image Complexity. IEEE SigPort. http://sigport.org/4253
Guangcheng Wang, Zhongyuan Wang, Ke Gu, Zhifang Xia, 2019. Blind Quality Assessment for 3D-Synthesized Images by Measuring Geometric Distortions and Image Complexity. Available at: http://sigport.org/4253.
Guangcheng Wang, Zhongyuan Wang, Ke Gu, Zhifang Xia. (2019). "Blind Quality Assessment for 3D-Synthesized Images by Measuring Geometric Distortions and Image Complexity." Web.
1. Guangcheng Wang, Zhongyuan Wang, Ke Gu, Zhifang Xia. Blind Quality Assessment for 3D-Synthesized Images by Measuring Geometric Distortions and Image Complexity [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4253

Fast Edge Preserving 2D Smoothing Filter using Indicator Function


Edge-preserving smoothing filter smoothes the textures while it preserves the information of sharp edges. In image processing, this filter is used as a fundamental process of many applications. In this paper, we propose a new approach for edge-preserving smoothing filter. Our method uses 2D filter to smooth images and we apply indicator function to restrict the range of filtered pixels for edge-preserving. To define the indicator function, we recalculate the distance between each pixel by using edge information. The nearby pixels in the new domain are used for smoothing.

Paper Details

Authors:
Ryo Abiko, Masaaki Ikehara
Submitted On:
9 May 2019 - 9:55pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp_smoothing.pdf

(18)

Subscribe

[1] Ryo Abiko, Masaaki Ikehara, "Fast Edge Preserving 2D Smoothing Filter using Indicator Function", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4251. Accessed: Jul. 20, 2019.
@article{4251-19,
url = {http://sigport.org/4251},
author = {Ryo Abiko; Masaaki Ikehara },
publisher = {IEEE SigPort},
title = {Fast Edge Preserving 2D Smoothing Filter using Indicator Function},
year = {2019} }
TY - EJOUR
T1 - Fast Edge Preserving 2D Smoothing Filter using Indicator Function
AU - Ryo Abiko; Masaaki Ikehara
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4251
ER -
Ryo Abiko, Masaaki Ikehara. (2019). Fast Edge Preserving 2D Smoothing Filter using Indicator Function. IEEE SigPort. http://sigport.org/4251
Ryo Abiko, Masaaki Ikehara, 2019. Fast Edge Preserving 2D Smoothing Filter using Indicator Function. Available at: http://sigport.org/4251.
Ryo Abiko, Masaaki Ikehara. (2019). "Fast Edge Preserving 2D Smoothing Filter using Indicator Function." Web.
1. Ryo Abiko, Masaaki Ikehara. Fast Edge Preserving 2D Smoothing Filter using Indicator Function [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4251

Image reconstruction by orthogonal moments derived by the parity of polynomial


Moments are a kind of classical feature descriptors for image analysis. Orthogonal moments, due to their computation
efficiency and numerical stability, have been widely developed.We propose a set of orthogonal polynomials which are
derived from the parity of Hermite polynomials. The new orthogonal polynomials are composed of either odd orders
or even ones of Hermite polynomials. They, however, are orthogonal in different domains. The corresponding orthogonal

Paper Details

Authors:
Bo Yang, Wei Tang, Xiaofeng Chen
Submitted On:
12 May 2019 - 3:16pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Presentation_ICASSP_2019.pdf

(13)

Subscribe

[1] Bo Yang, Wei Tang, Xiaofeng Chen, "Image reconstruction by orthogonal moments derived by the parity of polynomial", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4217. Accessed: Jul. 20, 2019.
@article{4217-19,
url = {http://sigport.org/4217},
author = {Bo Yang; Wei Tang; Xiaofeng Chen },
publisher = {IEEE SigPort},
title = {Image reconstruction by orthogonal moments derived by the parity of polynomial},
year = {2019} }
TY - EJOUR
T1 - Image reconstruction by orthogonal moments derived by the parity of polynomial
AU - Bo Yang; Wei Tang; Xiaofeng Chen
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4217
ER -
Bo Yang, Wei Tang, Xiaofeng Chen. (2019). Image reconstruction by orthogonal moments derived by the parity of polynomial. IEEE SigPort. http://sigport.org/4217
Bo Yang, Wei Tang, Xiaofeng Chen, 2019. Image reconstruction by orthogonal moments derived by the parity of polynomial. Available at: http://sigport.org/4217.
Bo Yang, Wei Tang, Xiaofeng Chen. (2019). "Image reconstruction by orthogonal moments derived by the parity of polynomial." Web.
1. Bo Yang, Wei Tang, Xiaofeng Chen. Image reconstruction by orthogonal moments derived by the parity of polynomial [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4217

The Limitation and Practical Acceleration of Stochastic Gradient Algorithms in Inverse Problems


In this work we investigate the practicability of stochastic gradient descent and recently introduced variants with variance-reduction techniques in imaging inverse problems, such as space-varying image deblurring. Such algorithms have been shown in machine learning literature to have optimal complexities in theory, and provide great improvement empirically over the full gradient methods. Surprisingly, in some tasks such as image deblurring, many of such methods fail to converge faster than the accelerated full gradient method (FISTA), even in terms of epoch counts.

Paper Details

Authors:
Junqi Tang, Karen Egiazarian, Mike Davies
Submitted On:
14 May 2019 - 6:05pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_Junqi

(15)

Subscribe

[1] Junqi Tang, Karen Egiazarian, Mike Davies, "The Limitation and Practical Acceleration of Stochastic Gradient Algorithms in Inverse Problems", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4207. Accessed: Jul. 20, 2019.
@article{4207-19,
url = {http://sigport.org/4207},
author = {Junqi Tang; Karen Egiazarian; Mike Davies },
publisher = {IEEE SigPort},
title = {The Limitation and Practical Acceleration of Stochastic Gradient Algorithms in Inverse Problems},
year = {2019} }
TY - EJOUR
T1 - The Limitation and Practical Acceleration of Stochastic Gradient Algorithms in Inverse Problems
AU - Junqi Tang; Karen Egiazarian; Mike Davies
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4207
ER -
Junqi Tang, Karen Egiazarian, Mike Davies. (2019). The Limitation and Practical Acceleration of Stochastic Gradient Algorithms in Inverse Problems. IEEE SigPort. http://sigport.org/4207
Junqi Tang, Karen Egiazarian, Mike Davies, 2019. The Limitation and Practical Acceleration of Stochastic Gradient Algorithms in Inverse Problems. Available at: http://sigport.org/4207.
Junqi Tang, Karen Egiazarian, Mike Davies. (2019). "The Limitation and Practical Acceleration of Stochastic Gradient Algorithms in Inverse Problems." Web.
1. Junqi Tang, Karen Egiazarian, Mike Davies. The Limitation and Practical Acceleration of Stochastic Gradient Algorithms in Inverse Problems [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4207

Pages