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

Image/Video Processing

Making Third Person Techniques Recognize First-Person Actions in Egocentric Videos


We focus on first-person action recognition from egocentric videos. Unlike third person domain, researchers have divided first-person actions into two categories: involving hand-object interactions and the ones without, and developed separate techniques for the two action categories. Further, it has been argued that traditional cues used for third person action recognition do not suffice, and egocentric specific features, such as head motion and handled objects have been used for such actions.

Paper Details

Authors:
Pravin Nagar, Divam Gupta, Chetan Arora
Submitted On:
6 October 2018 - 4:37am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Unified approach of recognizing multiple first-person action categories.

(35)

Subscribe

[1] Pravin Nagar, Divam Gupta, Chetan Arora, "Making Third Person Techniques Recognize First-Person Actions in Egocentric Videos", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3569. Accessed: Apr. 25, 2019.
@article{3569-18,
url = {http://sigport.org/3569},
author = {Pravin Nagar; Divam Gupta; Chetan Arora },
publisher = {IEEE SigPort},
title = {Making Third Person Techniques Recognize First-Person Actions in Egocentric Videos},
year = {2018} }
TY - EJOUR
T1 - Making Third Person Techniques Recognize First-Person Actions in Egocentric Videos
AU - Pravin Nagar; Divam Gupta; Chetan Arora
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3569
ER -
Pravin Nagar, Divam Gupta, Chetan Arora. (2018). Making Third Person Techniques Recognize First-Person Actions in Egocentric Videos. IEEE SigPort. http://sigport.org/3569
Pravin Nagar, Divam Gupta, Chetan Arora, 2018. Making Third Person Techniques Recognize First-Person Actions in Egocentric Videos. Available at: http://sigport.org/3569.
Pravin Nagar, Divam Gupta, Chetan Arora. (2018). "Making Third Person Techniques Recognize First-Person Actions in Egocentric Videos." Web.
1. Pravin Nagar, Divam Gupta, Chetan Arora. Making Third Person Techniques Recognize First-Person Actions in Egocentric Videos [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3569

CONFIDENCE ANALYSIS FOR BREAST MASS IMAGE CLASSIFICATION


Computer-aided diagnosis (CAD) has great potential in providing real benefits to doctors and patients. Recent studies have, however, found lack of trust in CAD by radiologists in clinical diagnostic decision making. One of the main reasons is the lack of an appropriate confidence measure. This paper presents the first-ever study of classification confidence in the context of breast mass classification.

Paper Details

Authors:
Andrik Rampun, Hui Wang, Bryan Scotney, Philip Morrow, Reyer Zwiggelaar
Submitted On:
6 October 2018 - 3:12am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Paper 1991: Confidence Analysis for Breast Mass Image Classification

(47)

Subscribe

[1] Andrik Rampun, Hui Wang, Bryan Scotney, Philip Morrow, Reyer Zwiggelaar, "CONFIDENCE ANALYSIS FOR BREAST MASS IMAGE CLASSIFICATION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3566. Accessed: Apr. 25, 2019.
@article{3566-18,
url = {http://sigport.org/3566},
author = {Andrik Rampun; Hui Wang; Bryan Scotney; Philip Morrow; Reyer Zwiggelaar },
publisher = {IEEE SigPort},
title = {CONFIDENCE ANALYSIS FOR BREAST MASS IMAGE CLASSIFICATION},
year = {2018} }
TY - EJOUR
T1 - CONFIDENCE ANALYSIS FOR BREAST MASS IMAGE CLASSIFICATION
AU - Andrik Rampun; Hui Wang; Bryan Scotney; Philip Morrow; Reyer Zwiggelaar
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3566
ER -
Andrik Rampun, Hui Wang, Bryan Scotney, Philip Morrow, Reyer Zwiggelaar. (2018). CONFIDENCE ANALYSIS FOR BREAST MASS IMAGE CLASSIFICATION. IEEE SigPort. http://sigport.org/3566
Andrik Rampun, Hui Wang, Bryan Scotney, Philip Morrow, Reyer Zwiggelaar, 2018. CONFIDENCE ANALYSIS FOR BREAST MASS IMAGE CLASSIFICATION. Available at: http://sigport.org/3566.
Andrik Rampun, Hui Wang, Bryan Scotney, Philip Morrow, Reyer Zwiggelaar. (2018). "CONFIDENCE ANALYSIS FOR BREAST MASS IMAGE CLASSIFICATION." Web.
1. Andrik Rampun, Hui Wang, Bryan Scotney, Philip Morrow, Reyer Zwiggelaar. CONFIDENCE ANALYSIS FOR BREAST MASS IMAGE CLASSIFICATION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3566

Discriminative Autoencoder

Paper Details

Authors:
Dipti Prasad Mukherjee
Submitted On:
6 October 2018 - 2:35am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster ICIP Final.pdf

(4)

Subscribe

[1] Dipti Prasad Mukherjee, "Discriminative Autoencoder", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3563. Accessed: Apr. 25, 2019.
@article{3563-18,
url = {http://sigport.org/3563},
author = {Dipti Prasad Mukherjee },
publisher = {IEEE SigPort},
title = {Discriminative Autoencoder},
year = {2018} }
TY - EJOUR
T1 - Discriminative Autoencoder
AU - Dipti Prasad Mukherjee
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3563
ER -
Dipti Prasad Mukherjee. (2018). Discriminative Autoencoder. IEEE SigPort. http://sigport.org/3563
Dipti Prasad Mukherjee, 2018. Discriminative Autoencoder. Available at: http://sigport.org/3563.
Dipti Prasad Mukherjee. (2018). "Discriminative Autoencoder." Web.
1. Dipti Prasad Mukherjee. Discriminative Autoencoder [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3563

RECOVERING TEXTURE OF DENOISED IMAGE VIA ITS STATISTICAL ANALYSIS

Paper Details

Authors:
Yuta Saito, Takamichi Miyata
Submitted On:
5 October 2018 - 10:22pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIPposter.pdf

(40)

Subscribe

[1] Yuta Saito, Takamichi Miyata, "RECOVERING TEXTURE OF DENOISED IMAGE VIA ITS STATISTICAL ANALYSIS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3559. Accessed: Apr. 25, 2019.
@article{3559-18,
url = {http://sigport.org/3559},
author = {Yuta Saito; Takamichi Miyata },
publisher = {IEEE SigPort},
title = {RECOVERING TEXTURE OF DENOISED IMAGE VIA ITS STATISTICAL ANALYSIS},
year = {2018} }
TY - EJOUR
T1 - RECOVERING TEXTURE OF DENOISED IMAGE VIA ITS STATISTICAL ANALYSIS
AU - Yuta Saito; Takamichi Miyata
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3559
ER -
Yuta Saito, Takamichi Miyata. (2018). RECOVERING TEXTURE OF DENOISED IMAGE VIA ITS STATISTICAL ANALYSIS. IEEE SigPort. http://sigport.org/3559
Yuta Saito, Takamichi Miyata, 2018. RECOVERING TEXTURE OF DENOISED IMAGE VIA ITS STATISTICAL ANALYSIS. Available at: http://sigport.org/3559.
Yuta Saito, Takamichi Miyata. (2018). "RECOVERING TEXTURE OF DENOISED IMAGE VIA ITS STATISTICAL ANALYSIS." Web.
1. Yuta Saito, Takamichi Miyata. RECOVERING TEXTURE OF DENOISED IMAGE VIA ITS STATISTICAL ANALYSIS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3559

An Iterative Denoising and Backward Projections Method


Inverse problems appear in many applications, such as image deblurring and inpainting. The common approach to address them is to design a specific algorithm for each problem. The Plug-and-Play (P&P) framework, which has been recently introduced, allows solving general inverse problems by leveraging the impressive capabilities of existing denoising algorithms. While this fresh strategy has found many applications, a burdensome parameter tuning is often required in order to obtain high-quality results.

Paper Details

Authors:
Tom Tirer, Raja Giryes
Submitted On:
5 October 2018 - 5:13pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

IDBP - ICIP Slides.pdf

(14)

Subscribe

[1] Tom Tirer, Raja Giryes, "An Iterative Denoising and Backward Projections Method", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3556. Accessed: Apr. 25, 2019.
@article{3556-18,
url = {http://sigport.org/3556},
author = {Tom Tirer; Raja Giryes },
publisher = {IEEE SigPort},
title = {An Iterative Denoising and Backward Projections Method},
year = {2018} }
TY - EJOUR
T1 - An Iterative Denoising and Backward Projections Method
AU - Tom Tirer; Raja Giryes
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3556
ER -
Tom Tirer, Raja Giryes. (2018). An Iterative Denoising and Backward Projections Method. IEEE SigPort. http://sigport.org/3556
Tom Tirer, Raja Giryes, 2018. An Iterative Denoising and Backward Projections Method. Available at: http://sigport.org/3556.
Tom Tirer, Raja Giryes. (2018). "An Iterative Denoising and Backward Projections Method." Web.
1. Tom Tirer, Raja Giryes. An Iterative Denoising and Backward Projections Method [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3556

Plenoptic Toolbox 2.0 - Benchmarking of Depth Estimation Methods for MLA-Based Focused Plenoptic Cameras


MLA-based focused plenoptic cameras, also called type 2.0 cameras, have advantages over type 1.0 plenoptic cameras, because of their better inherent spatial image resolution and their compromise between depth of focus and angular resolution. However, they are more difficult to process since they require a depth estimation first to compute the all-in-focus image from the raw MLA image data. Current toolboxes for plenoptic cameras only support the type 1.0 cameras (like Lytro) and cannot handle type 2.0 cameras (like Raytrix).

Paper Details

Authors:
Luca Palmieri, Ron Op Het Veld, Reinhard Koch
Submitted On:
5 October 2018 - 4:15pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Plenoptic Toolbox

(51)

Subscribe

[1] Luca Palmieri, Ron Op Het Veld, Reinhard Koch, "Plenoptic Toolbox 2.0 - Benchmarking of Depth Estimation Methods for MLA-Based Focused Plenoptic Cameras", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3555. Accessed: Apr. 25, 2019.
@article{3555-18,
url = {http://sigport.org/3555},
author = {Luca Palmieri; Ron Op Het Veld; Reinhard Koch },
publisher = {IEEE SigPort},
title = {Plenoptic Toolbox 2.0 - Benchmarking of Depth Estimation Methods for MLA-Based Focused Plenoptic Cameras},
year = {2018} }
TY - EJOUR
T1 - Plenoptic Toolbox 2.0 - Benchmarking of Depth Estimation Methods for MLA-Based Focused Plenoptic Cameras
AU - Luca Palmieri; Ron Op Het Veld; Reinhard Koch
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3555
ER -
Luca Palmieri, Ron Op Het Veld, Reinhard Koch. (2018). Plenoptic Toolbox 2.0 - Benchmarking of Depth Estimation Methods for MLA-Based Focused Plenoptic Cameras. IEEE SigPort. http://sigport.org/3555
Luca Palmieri, Ron Op Het Veld, Reinhard Koch, 2018. Plenoptic Toolbox 2.0 - Benchmarking of Depth Estimation Methods for MLA-Based Focused Plenoptic Cameras. Available at: http://sigport.org/3555.
Luca Palmieri, Ron Op Het Veld, Reinhard Koch. (2018). "Plenoptic Toolbox 2.0 - Benchmarking of Depth Estimation Methods for MLA-Based Focused Plenoptic Cameras." Web.
1. Luca Palmieri, Ron Op Het Veld, Reinhard Koch. Plenoptic Toolbox 2.0 - Benchmarking of Depth Estimation Methods for MLA-Based Focused Plenoptic Cameras [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3555

DEFORMABLE MOTION 3D RECONSTRUCTION BY UNION OF REGULARIZED SUBSPACES


This paper presents an approach to jointly retrieve camera pose, time-varying 3D shape, and automatic clustering based on motion primitives, from incomplete 2D trajectories in a monocular video. We introduce the concept of order-varying temporal regularization in order to exploit video data, that can be indistinctly applied to the 3D shape evolution as well as to the similarities between images. This results in a union of regularized subspaces which effectively encodes the 3D shape deformation.

Paper Details

Authors:
Antonio Agudo and Francesc Moreno-Noguer
Submitted On:
5 October 2018 - 4:01pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster

(34)

Subscribe

[1] Antonio Agudo and Francesc Moreno-Noguer, "DEFORMABLE MOTION 3D RECONSTRUCTION BY UNION OF REGULARIZED SUBSPACES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3553. Accessed: Apr. 25, 2019.
@article{3553-18,
url = {http://sigport.org/3553},
author = {Antonio Agudo and Francesc Moreno-Noguer },
publisher = {IEEE SigPort},
title = {DEFORMABLE MOTION 3D RECONSTRUCTION BY UNION OF REGULARIZED SUBSPACES},
year = {2018} }
TY - EJOUR
T1 - DEFORMABLE MOTION 3D RECONSTRUCTION BY UNION OF REGULARIZED SUBSPACES
AU - Antonio Agudo and Francesc Moreno-Noguer
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3553
ER -
Antonio Agudo and Francesc Moreno-Noguer. (2018). DEFORMABLE MOTION 3D RECONSTRUCTION BY UNION OF REGULARIZED SUBSPACES. IEEE SigPort. http://sigport.org/3553
Antonio Agudo and Francesc Moreno-Noguer, 2018. DEFORMABLE MOTION 3D RECONSTRUCTION BY UNION OF REGULARIZED SUBSPACES. Available at: http://sigport.org/3553.
Antonio Agudo and Francesc Moreno-Noguer. (2018). "DEFORMABLE MOTION 3D RECONSTRUCTION BY UNION OF REGULARIZED SUBSPACES." Web.
1. Antonio Agudo and Francesc Moreno-Noguer. DEFORMABLE MOTION 3D RECONSTRUCTION BY UNION OF REGULARIZED SUBSPACES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3553

Motion Estimation and Deblurring of Fast Moving Objects


Image deblurring is one of the standard problems in image processing.
Recently, this area of research is dominated by blind deblurring, where neither the sharp image nor the blur are known.
The majority of works, however, target scenarios where the captured scene is static and the blur is caused by camera motion, i.e. the whole image is blurred.
In this work we address a similar yet different scenario: an object moves in front of a static background.
Such object is blurred due to motion while the background is sharp and partially occluded by the object.

Paper Details

Authors:
Jan Kotera, Filip Šroubek
Submitted On:
5 October 2018 - 3:54pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icip 2018 poster

(33)

Subscribe

[1] Jan Kotera, Filip Šroubek, "Motion Estimation and Deblurring of Fast Moving Objects", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3552. Accessed: Apr. 25, 2019.
@article{3552-18,
url = {http://sigport.org/3552},
author = {Jan Kotera; Filip Šroubek },
publisher = {IEEE SigPort},
title = {Motion Estimation and Deblurring of Fast Moving Objects},
year = {2018} }
TY - EJOUR
T1 - Motion Estimation and Deblurring of Fast Moving Objects
AU - Jan Kotera; Filip Šroubek
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3552
ER -
Jan Kotera, Filip Šroubek. (2018). Motion Estimation and Deblurring of Fast Moving Objects. IEEE SigPort. http://sigport.org/3552
Jan Kotera, Filip Šroubek, 2018. Motion Estimation and Deblurring of Fast Moving Objects. Available at: http://sigport.org/3552.
Jan Kotera, Filip Šroubek. (2018). "Motion Estimation and Deblurring of Fast Moving Objects." Web.
1. Jan Kotera, Filip Šroubek. Motion Estimation and Deblurring of Fast Moving Objects [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3552

Anisotropic Partial Differential Equation based Video Saliency Detection


In this paper, we propose a novel video saliency detection method using the Partial Differential Equations (PDEs). We first form a static adaptive anisotropic PDE model from the unpredicted frames of the video using a detection map and a saliency seeds set of most attractive image elements. At the same time, we also extract motion features from the predicted frames of the video to generate motion saliency map. Then, we combine these two maps to obtain the final saliency map (video).

Paper Details

Authors:
Wai Lam Hoo, Chee Seng Chan
Submitted On:
5 October 2018 - 2:49pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2018_id2644

(522)

Subscribe

[1] Wai Lam Hoo, Chee Seng Chan, "Anisotropic Partial Differential Equation based Video Saliency Detection", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3551. Accessed: Apr. 25, 2019.
@article{3551-18,
url = {http://sigport.org/3551},
author = {Wai Lam Hoo; Chee Seng Chan },
publisher = {IEEE SigPort},
title = {Anisotropic Partial Differential Equation based Video Saliency Detection},
year = {2018} }
TY - EJOUR
T1 - Anisotropic Partial Differential Equation based Video Saliency Detection
AU - Wai Lam Hoo; Chee Seng Chan
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3551
ER -
Wai Lam Hoo, Chee Seng Chan. (2018). Anisotropic Partial Differential Equation based Video Saliency Detection. IEEE SigPort. http://sigport.org/3551
Wai Lam Hoo, Chee Seng Chan, 2018. Anisotropic Partial Differential Equation based Video Saliency Detection. Available at: http://sigport.org/3551.
Wai Lam Hoo, Chee Seng Chan. (2018). "Anisotropic Partial Differential Equation based Video Saliency Detection." Web.
1. Wai Lam Hoo, Chee Seng Chan. Anisotropic Partial Differential Equation based Video Saliency Detection [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3551

AN ADVANCED VISIBILITY RESTORATION TECHNIQUE FOR UNDERWATER IMAGES

Paper Details

Authors:
TAPAN KUMAR GANDHI, B.K. PANIGRAHI
Submitted On:
5 October 2018 - 1:46pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP_Poster.pdf

(36)

Subscribe

[1] TAPAN KUMAR GANDHI, B.K. PANIGRAHI, "AN ADVANCED VISIBILITY RESTORATION TECHNIQUE FOR UNDERWATER IMAGES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3550. Accessed: Apr. 25, 2019.
@article{3550-18,
url = {http://sigport.org/3550},
author = {TAPAN KUMAR GANDHI; B.K. PANIGRAHI },
publisher = {IEEE SigPort},
title = {AN ADVANCED VISIBILITY RESTORATION TECHNIQUE FOR UNDERWATER IMAGES},
year = {2018} }
TY - EJOUR
T1 - AN ADVANCED VISIBILITY RESTORATION TECHNIQUE FOR UNDERWATER IMAGES
AU - TAPAN KUMAR GANDHI; B.K. PANIGRAHI
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3550
ER -
TAPAN KUMAR GANDHI, B.K. PANIGRAHI. (2018). AN ADVANCED VISIBILITY RESTORATION TECHNIQUE FOR UNDERWATER IMAGES. IEEE SigPort. http://sigport.org/3550
TAPAN KUMAR GANDHI, B.K. PANIGRAHI, 2018. AN ADVANCED VISIBILITY RESTORATION TECHNIQUE FOR UNDERWATER IMAGES. Available at: http://sigport.org/3550.
TAPAN KUMAR GANDHI, B.K. PANIGRAHI. (2018). "AN ADVANCED VISIBILITY RESTORATION TECHNIQUE FOR UNDERWATER IMAGES." Web.
1. TAPAN KUMAR GANDHI, B.K. PANIGRAHI. AN ADVANCED VISIBILITY RESTORATION TECHNIQUE FOR UNDERWATER IMAGES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3550

Pages