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

Multimedia computing systems and applications

A DEEP REINFORCEMENT LEARNING FRAMEWORK FOR IDENTIFYING FUNNY SCENES IN MOVIES


This paper presents a novel deep Reinforcement Learning (RL)framework for classifying movie scenes based on affect using the face images detected in the video stream as input. Extracting affective information from the video is a challenging task modulating complex visual and temporal representations intertwined with the complex aspects of human perception and information integration. This also makes it difficult to collect a large annotated corpus restricting the use of supervised learning methods.

Paper Details

Authors:
Submitted On:
24 April 2018 - 2:53pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icasspRLfunnyscenePoster

(84 downloads)

Subscribe

[1] , "A DEEP REINFORCEMENT LEARNING FRAMEWORK FOR IDENTIFYING FUNNY SCENES IN MOVIES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3172. Accessed: Oct. 16, 2018.
@article{3172-18,
url = {http://sigport.org/3172},
author = { },
publisher = {IEEE SigPort},
title = {A DEEP REINFORCEMENT LEARNING FRAMEWORK FOR IDENTIFYING FUNNY SCENES IN MOVIES},
year = {2018} }
TY - EJOUR
T1 - A DEEP REINFORCEMENT LEARNING FRAMEWORK FOR IDENTIFYING FUNNY SCENES IN MOVIES
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3172
ER -
. (2018). A DEEP REINFORCEMENT LEARNING FRAMEWORK FOR IDENTIFYING FUNNY SCENES IN MOVIES. IEEE SigPort. http://sigport.org/3172
, 2018. A DEEP REINFORCEMENT LEARNING FRAMEWORK FOR IDENTIFYING FUNNY SCENES IN MOVIES. Available at: http://sigport.org/3172.
. (2018). "A DEEP REINFORCEMENT LEARNING FRAMEWORK FOR IDENTIFYING FUNNY SCENES IN MOVIES." Web.
1. . A DEEP REINFORCEMENT LEARNING FRAMEWORK FOR IDENTIFYING FUNNY SCENES IN MOVIES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3172

A CASCADED FRAMEWORK FOR MODEL-BASED 3D FACE RECONSTRUCTION


This paper presents a general framework for model-based 3D face reconstruction from a single image, which can incorporate mature face alignment methods and utilize their properties. In the proposed framework, the final model parameters, i.e., mostly including pose, identity and expression, are achieved by estimating updating the face landmarks and 3D face model parameter alternately. In addition, we propose the parameter augmented regression method (PARM) as an novel derivation of the framework.

Paper Details

Authors:
Pengrui Wang, Wujun Che, Bo Xu
Submitted On:
20 April 2018 - 2:51am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster_PARM_wang.pdf

(98 downloads)

Subscribe

[1] Pengrui Wang, Wujun Che, Bo Xu, "A CASCADED FRAMEWORK FOR MODEL-BASED 3D FACE RECONSTRUCTION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3087. Accessed: Oct. 16, 2018.
@article{3087-18,
url = {http://sigport.org/3087},
author = {Pengrui Wang; Wujun Che; Bo Xu },
publisher = {IEEE SigPort},
title = {A CASCADED FRAMEWORK FOR MODEL-BASED 3D FACE RECONSTRUCTION},
year = {2018} }
TY - EJOUR
T1 - A CASCADED FRAMEWORK FOR MODEL-BASED 3D FACE RECONSTRUCTION
AU - Pengrui Wang; Wujun Che; Bo Xu
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3087
ER -
Pengrui Wang, Wujun Che, Bo Xu. (2018). A CASCADED FRAMEWORK FOR MODEL-BASED 3D FACE RECONSTRUCTION. IEEE SigPort. http://sigport.org/3087
Pengrui Wang, Wujun Che, Bo Xu, 2018. A CASCADED FRAMEWORK FOR MODEL-BASED 3D FACE RECONSTRUCTION. Available at: http://sigport.org/3087.
Pengrui Wang, Wujun Che, Bo Xu. (2018). "A CASCADED FRAMEWORK FOR MODEL-BASED 3D FACE RECONSTRUCTION." Web.
1. Pengrui Wang, Wujun Che, Bo Xu. A CASCADED FRAMEWORK FOR MODEL-BASED 3D FACE RECONSTRUCTION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3087

CORRELATION-BASED FACE DETECTION FOR RECOGNIZING FACES IN VIDEOS

Paper Details

Authors:
Submitted On:
12 April 2018 - 11:36am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

HENG_POSTER.pdf

(65 downloads)

Subscribe

[1] , "CORRELATION-BASED FACE DETECTION FOR RECOGNIZING FACES IN VIDEOS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2407. Accessed: Oct. 16, 2018.
@article{2407-18,
url = {http://sigport.org/2407},
author = { },
publisher = {IEEE SigPort},
title = {CORRELATION-BASED FACE DETECTION FOR RECOGNIZING FACES IN VIDEOS},
year = {2018} }
TY - EJOUR
T1 - CORRELATION-BASED FACE DETECTION FOR RECOGNIZING FACES IN VIDEOS
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2407
ER -
. (2018). CORRELATION-BASED FACE DETECTION FOR RECOGNIZING FACES IN VIDEOS. IEEE SigPort. http://sigport.org/2407
, 2018. CORRELATION-BASED FACE DETECTION FOR RECOGNIZING FACES IN VIDEOS. Available at: http://sigport.org/2407.
. (2018). "CORRELATION-BASED FACE DETECTION FOR RECOGNIZING FACES IN VIDEOS." Web.
1. . CORRELATION-BASED FACE DETECTION FOR RECOGNIZING FACES IN VIDEOS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2407

Detecting Photorealistic Computer Graphics using Convolutional Neural Networks

Paper Details

Authors:
Submitted On:
16 September 2017 - 9:30pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2018_icip.pdf

(137 downloads)

Subscribe

[1] , "Detecting Photorealistic Computer Graphics using Convolutional Neural Networks", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2204. Accessed: Oct. 16, 2018.
@article{2204-17,
url = {http://sigport.org/2204},
author = { },
publisher = {IEEE SigPort},
title = {Detecting Photorealistic Computer Graphics using Convolutional Neural Networks},
year = {2017} }
TY - EJOUR
T1 - Detecting Photorealistic Computer Graphics using Convolutional Neural Networks
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2204
ER -
. (2017). Detecting Photorealistic Computer Graphics using Convolutional Neural Networks. IEEE SigPort. http://sigport.org/2204
, 2017. Detecting Photorealistic Computer Graphics using Convolutional Neural Networks. Available at: http://sigport.org/2204.
. (2017). "Detecting Photorealistic Computer Graphics using Convolutional Neural Networks." Web.
1. . Detecting Photorealistic Computer Graphics using Convolutional Neural Networks [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2204

PIX2NVS: Parameterized Conversion of Pixel-domain Video Streams to Neuromorphic Vision Streams

Paper Details

Authors:
Submitted On:
14 September 2017 - 6:45am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2017_2371_Yin_Slides

(112 downloads)

Subscribe

[1] , "PIX2NVS: Parameterized Conversion of Pixel-domain Video Streams to Neuromorphic Vision Streams", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2012. Accessed: Oct. 16, 2018.
@article{2012-17,
url = {http://sigport.org/2012},
author = { },
publisher = {IEEE SigPort},
title = {PIX2NVS: Parameterized Conversion of Pixel-domain Video Streams to Neuromorphic Vision Streams},
year = {2017} }
TY - EJOUR
T1 - PIX2NVS: Parameterized Conversion of Pixel-domain Video Streams to Neuromorphic Vision Streams
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2012
ER -
. (2017). PIX2NVS: Parameterized Conversion of Pixel-domain Video Streams to Neuromorphic Vision Streams. IEEE SigPort. http://sigport.org/2012
, 2017. PIX2NVS: Parameterized Conversion of Pixel-domain Video Streams to Neuromorphic Vision Streams. Available at: http://sigport.org/2012.
. (2017). "PIX2NVS: Parameterized Conversion of Pixel-domain Video Streams to Neuromorphic Vision Streams." Web.
1. . PIX2NVS: Parameterized Conversion of Pixel-domain Video Streams to Neuromorphic Vision Streams [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2012

A Novel Kinect V2 Registration Method For Large-Displacement Environments Using Camera And Scene Constraints


In a lot of multi-Kinect V2-based systems, the registration of these Kinect V2 sensors is an important step which directly affects the system precision. The coarse-to-fine method using calibration objects is an effective way to solve the Kinect V2 registration problem. However, for the registration of Kinect V2 cameras with large displacements, this kind of method may fail. To this end, a novel Kinect V2 registration method, which is also based on the coarse-to-fine framework, is proposed by using camera and scene constraints.

Paper Details

Authors:
Sandro Esquivel, Reinhard Koch, Matthias Ziegler, Frederik Zilly, Joachim Keinert
Submitted On:
19 April 2018 - 11:16am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2017.09.19ICIP.pdf

(160 downloads)

Subscribe

[1] Sandro Esquivel, Reinhard Koch, Matthias Ziegler, Frederik Zilly, Joachim Keinert, "A Novel Kinect V2 Registration Method For Large-Displacement Environments Using Camera And Scene Constraints", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1849. Accessed: Oct. 16, 2018.
@article{1849-17,
url = {http://sigport.org/1849},
author = {Sandro Esquivel; Reinhard Koch; Matthias Ziegler; Frederik Zilly; Joachim Keinert },
publisher = {IEEE SigPort},
title = {A Novel Kinect V2 Registration Method For Large-Displacement Environments Using Camera And Scene Constraints},
year = {2017} }
TY - EJOUR
T1 - A Novel Kinect V2 Registration Method For Large-Displacement Environments Using Camera And Scene Constraints
AU - Sandro Esquivel; Reinhard Koch; Matthias Ziegler; Frederik Zilly; Joachim Keinert
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1849
ER -
Sandro Esquivel, Reinhard Koch, Matthias Ziegler, Frederik Zilly, Joachim Keinert. (2017). A Novel Kinect V2 Registration Method For Large-Displacement Environments Using Camera And Scene Constraints. IEEE SigPort. http://sigport.org/1849
Sandro Esquivel, Reinhard Koch, Matthias Ziegler, Frederik Zilly, Joachim Keinert, 2017. A Novel Kinect V2 Registration Method For Large-Displacement Environments Using Camera And Scene Constraints. Available at: http://sigport.org/1849.
Sandro Esquivel, Reinhard Koch, Matthias Ziegler, Frederik Zilly, Joachim Keinert. (2017). "A Novel Kinect V2 Registration Method For Large-Displacement Environments Using Camera And Scene Constraints." Web.
1. Sandro Esquivel, Reinhard Koch, Matthias Ziegler, Frederik Zilly, Joachim Keinert. A Novel Kinect V2 Registration Method For Large-Displacement Environments Using Camera And Scene Constraints [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1849

TRACKING HIERARCHICAL STRUCTURE OF WEB VIDEO GROUPS BASED ON SALIENT KEYWORD MATCHING INCLUDING SEMANTIC BROADNESS ESTIMATION


This paper presents a novel method to track the hierarchical structure of Web video groups on the basis of salient keyword matching including semantic broadness estimation. To the best of our knowledge, this paper is the first work to perform extraction and tracking of the hierarchical structure simultaneously. Specifically, the proposed method first extracts the hierarchical structure of Web video groups and salient keywords of them on the basis of an improved scheme of our previously reported method.

Paper Details

Authors:
Ryosuke Harakawa,Takahiro Ogawa,Miki Haseyama
Submitted On:
6 December 2016 - 6:46pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

harakawa_globalsip2016.pdf

(277 downloads)

Subscribe

[1] Ryosuke Harakawa,Takahiro Ogawa,Miki Haseyama, "TRACKING HIERARCHICAL STRUCTURE OF WEB VIDEO GROUPS BASED ON SALIENT KEYWORD MATCHING INCLUDING SEMANTIC BROADNESS ESTIMATION", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1375. Accessed: Oct. 16, 2018.
@article{1375-16,
url = {http://sigport.org/1375},
author = {Ryosuke Harakawa;Takahiro Ogawa;Miki Haseyama },
publisher = {IEEE SigPort},
title = {TRACKING HIERARCHICAL STRUCTURE OF WEB VIDEO GROUPS BASED ON SALIENT KEYWORD MATCHING INCLUDING SEMANTIC BROADNESS ESTIMATION},
year = {2016} }
TY - EJOUR
T1 - TRACKING HIERARCHICAL STRUCTURE OF WEB VIDEO GROUPS BASED ON SALIENT KEYWORD MATCHING INCLUDING SEMANTIC BROADNESS ESTIMATION
AU - Ryosuke Harakawa;Takahiro Ogawa;Miki Haseyama
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1375
ER -
Ryosuke Harakawa,Takahiro Ogawa,Miki Haseyama. (2016). TRACKING HIERARCHICAL STRUCTURE OF WEB VIDEO GROUPS BASED ON SALIENT KEYWORD MATCHING INCLUDING SEMANTIC BROADNESS ESTIMATION. IEEE SigPort. http://sigport.org/1375
Ryosuke Harakawa,Takahiro Ogawa,Miki Haseyama, 2016. TRACKING HIERARCHICAL STRUCTURE OF WEB VIDEO GROUPS BASED ON SALIENT KEYWORD MATCHING INCLUDING SEMANTIC BROADNESS ESTIMATION. Available at: http://sigport.org/1375.
Ryosuke Harakawa,Takahiro Ogawa,Miki Haseyama. (2016). "TRACKING HIERARCHICAL STRUCTURE OF WEB VIDEO GROUPS BASED ON SALIENT KEYWORD MATCHING INCLUDING SEMANTIC BROADNESS ESTIMATION." Web.
1. Ryosuke Harakawa,Takahiro Ogawa,Miki Haseyama. TRACKING HIERARCHICAL STRUCTURE OF WEB VIDEO GROUPS BASED ON SALIENT KEYWORD MATCHING INCLUDING SEMANTIC BROADNESS ESTIMATION [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1375

Multimedia Content Creation using Global Network Cameras: The Making of CAM2


slides.pdf

PDF icon slides.pdf (1029 downloads)

Paper Details

Authors:
Youngsol Koh, Everett Berry, Kyle McNulty, Yung-Hsiang Lu, Edward J. Delp
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

slides.pdf

(1029 downloads)

Subscribe

[1] Youngsol Koh, Everett Berry, Kyle McNulty, Yung-Hsiang Lu, Edward J. Delp, "Multimedia Content Creation using Global Network Cameras: The Making of CAM2", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/408. Accessed: Oct. 16, 2018.
@article{408-15,
url = {http://sigport.org/408},
author = {Youngsol Koh; Everett Berry; Kyle McNulty; Yung-Hsiang Lu; Edward J. Delp },
publisher = {IEEE SigPort},
title = {Multimedia Content Creation using Global Network Cameras: The Making of CAM2},
year = {2015} }
TY - EJOUR
T1 - Multimedia Content Creation using Global Network Cameras: The Making of CAM2
AU - Youngsol Koh; Everett Berry; Kyle McNulty; Yung-Hsiang Lu; Edward J. Delp
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/408
ER -
Youngsol Koh, Everett Berry, Kyle McNulty, Yung-Hsiang Lu, Edward J. Delp. (2015). Multimedia Content Creation using Global Network Cameras: The Making of CAM2. IEEE SigPort. http://sigport.org/408
Youngsol Koh, Everett Berry, Kyle McNulty, Yung-Hsiang Lu, Edward J. Delp, 2015. Multimedia Content Creation using Global Network Cameras: The Making of CAM2. Available at: http://sigport.org/408.
Youngsol Koh, Everett Berry, Kyle McNulty, Yung-Hsiang Lu, Edward J. Delp. (2015). "Multimedia Content Creation using Global Network Cameras: The Making of CAM2." Web.
1. Youngsol Koh, Everett Berry, Kyle McNulty, Yung-Hsiang Lu, Edward J. Delp. Multimedia Content Creation using Global Network Cameras: The Making of CAM2 [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/408

Gait Analysis using a Single Depth Camera


Gait analysis is often used as part of the rehabilitation program for post-stoke recovery assessment. Since current optical diagnostic and patient assessment tools tend to be expensive and not portable, this paper proposes a novel marker-based tracking system using a single depth camera which provides a cost-effective solution suitable for home and clinic use. The proposed system can simultaneously generate motion patterns even within a complex background using the proposed geometric model-based algorithm and autonomously provide gait analysis results.

Paper Details

Authors:
Minxiang Ye, Cheng Yang, Lina Stankovic, Andrew Kerr
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Minxiang-printed.pdf

(463 downloads)

Subscribe

[1] Minxiang Ye, Cheng Yang, Lina Stankovic, Andrew Kerr, "Gait Analysis using a Single Depth Camera", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/275. Accessed: Oct. 16, 2018.
@article{275-15,
url = {http://sigport.org/275},
author = {Minxiang Ye; Cheng Yang; Lina Stankovic; Andrew Kerr },
publisher = {IEEE SigPort},
title = {Gait Analysis using a Single Depth Camera},
year = {2015} }
TY - EJOUR
T1 - Gait Analysis using a Single Depth Camera
AU - Minxiang Ye; Cheng Yang; Lina Stankovic; Andrew Kerr
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/275
ER -
Minxiang Ye, Cheng Yang, Lina Stankovic, Andrew Kerr. (2015). Gait Analysis using a Single Depth Camera. IEEE SigPort. http://sigport.org/275
Minxiang Ye, Cheng Yang, Lina Stankovic, Andrew Kerr, 2015. Gait Analysis using a Single Depth Camera. Available at: http://sigport.org/275.
Minxiang Ye, Cheng Yang, Lina Stankovic, Andrew Kerr. (2015). "Gait Analysis using a Single Depth Camera." Web.
1. Minxiang Ye, Cheng Yang, Lina Stankovic, Andrew Kerr. Gait Analysis using a Single Depth Camera [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/275