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

Image/Video Processing

Feature Extraction using Gaze of Participants for Classifying Gender of Pedestrians in Images

Paper Details

Authors:
Riku Matsumoto, Hiroki Yoshimura,Yoshio Iwai
Submitted On:
18 September 2017 - 4:52am
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

ICIP2017_Feature Extraction using Gaze of Participants for Classifying Gender of Pedestrians in Images.pdf

(37 downloads)

Keywords

Subscribe

[1] Riku Matsumoto, Hiroki Yoshimura,Yoshio Iwai, "Feature Extraction using Gaze of Participants for Classifying Gender of Pedestrians in Images", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2222. Accessed: Dec. 15, 2017.
@article{2222-17,
url = {http://sigport.org/2222},
author = {Riku Matsumoto; Hiroki Yoshimura;Yoshio Iwai },
publisher = {IEEE SigPort},
title = {Feature Extraction using Gaze of Participants for Classifying Gender of Pedestrians in Images},
year = {2017} }
TY - EJOUR
T1 - Feature Extraction using Gaze of Participants for Classifying Gender of Pedestrians in Images
AU - Riku Matsumoto; Hiroki Yoshimura;Yoshio Iwai
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2222
ER -
Riku Matsumoto, Hiroki Yoshimura,Yoshio Iwai. (2017). Feature Extraction using Gaze of Participants for Classifying Gender of Pedestrians in Images. IEEE SigPort. http://sigport.org/2222
Riku Matsumoto, Hiroki Yoshimura,Yoshio Iwai, 2017. Feature Extraction using Gaze of Participants for Classifying Gender of Pedestrians in Images. Available at: http://sigport.org/2222.
Riku Matsumoto, Hiroki Yoshimura,Yoshio Iwai. (2017). "Feature Extraction using Gaze of Participants for Classifying Gender of Pedestrians in Images." Web.
1. Riku Matsumoto, Hiroki Yoshimura,Yoshio Iwai. Feature Extraction using Gaze of Participants for Classifying Gender of Pedestrians in Images [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2222

COMPLEX NONSEPARABLE OVERSAMPLED LAPPED TRANSFORM FOR SPARSE REPRESENTATION OF MILLIMETER WAVE RADAR IMAGE


This work generalizes an existing framework of nonseparable oversampled lapped transforms (NSOLTs) to effectively represent complex-valued images.
The original NSOLTs are lattice-structure-based redundant transforms, which satisfy the linear-phase, compact-supported and real-valued property. The lattice structure is able to constitute a Parseval tight frame with rational redundancy and to generate a dictionary with directional atomic images.
In this study, a generalized structure of NSOLTs is proposed to cover complex-valued atomic images.

Paper Details

Authors:
Satoshi Nagayama, Shogo Muramatsu, Hiroyoshi yamada, Yuuichi Sugiyama
Submitted On:
18 September 2017 - 2:05am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

cnsolt_icip2017.pdf

(23 downloads)

Keywords

Subscribe

[1] Satoshi Nagayama, Shogo Muramatsu, Hiroyoshi yamada, Yuuichi Sugiyama, "COMPLEX NONSEPARABLE OVERSAMPLED LAPPED TRANSFORM FOR SPARSE REPRESENTATION OF MILLIMETER WAVE RADAR IMAGE", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2219. Accessed: Dec. 15, 2017.
@article{2219-17,
url = {http://sigport.org/2219},
author = {Satoshi Nagayama; Shogo Muramatsu; Hiroyoshi yamada; Yuuichi Sugiyama },
publisher = {IEEE SigPort},
title = {COMPLEX NONSEPARABLE OVERSAMPLED LAPPED TRANSFORM FOR SPARSE REPRESENTATION OF MILLIMETER WAVE RADAR IMAGE},
year = {2017} }
TY - EJOUR
T1 - COMPLEX NONSEPARABLE OVERSAMPLED LAPPED TRANSFORM FOR SPARSE REPRESENTATION OF MILLIMETER WAVE RADAR IMAGE
AU - Satoshi Nagayama; Shogo Muramatsu; Hiroyoshi yamada; Yuuichi Sugiyama
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2219
ER -
Satoshi Nagayama, Shogo Muramatsu, Hiroyoshi yamada, Yuuichi Sugiyama. (2017). COMPLEX NONSEPARABLE OVERSAMPLED LAPPED TRANSFORM FOR SPARSE REPRESENTATION OF MILLIMETER WAVE RADAR IMAGE. IEEE SigPort. http://sigport.org/2219
Satoshi Nagayama, Shogo Muramatsu, Hiroyoshi yamada, Yuuichi Sugiyama, 2017. COMPLEX NONSEPARABLE OVERSAMPLED LAPPED TRANSFORM FOR SPARSE REPRESENTATION OF MILLIMETER WAVE RADAR IMAGE. Available at: http://sigport.org/2219.
Satoshi Nagayama, Shogo Muramatsu, Hiroyoshi yamada, Yuuichi Sugiyama. (2017). "COMPLEX NONSEPARABLE OVERSAMPLED LAPPED TRANSFORM FOR SPARSE REPRESENTATION OF MILLIMETER WAVE RADAR IMAGE." Web.
1. Satoshi Nagayama, Shogo Muramatsu, Hiroyoshi yamada, Yuuichi Sugiyama. COMPLEX NONSEPARABLE OVERSAMPLED LAPPED TRANSFORM FOR SPARSE REPRESENTATION OF MILLIMETER WAVE RADAR IMAGE [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2219

MULTIDIMENSIONAL NONSEPARABLE OVERSAMPLED LAPPED TRANSFORMS: THEORY AND DESIGN


This paper extends the theory of the one-dimensional oversampled linear-phase perfect reconstruction filter banks (OLPPRFBs) developed by Gan et al. to multidimensional (MD) cases and proposes MD nonseparable oversampled lapped transforms (NSOLTs). NSOLTs allow us to achieve an overcomplete analysis-synthesis system with nonseparable, symmetric, realvalued, overlapping, and compact-supported filters. The proposed systems are based on lattice structures and the redundancy is flexibly controlled by the number of channels and downsampling ratio.

Paper Details

Authors:
Kosuke Furuya, Naotaka Yuki
Submitted On:
18 September 2017 - 7:34pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Icip2017PosterRev2.pdf

(25 downloads)

Keywords

Subscribe

[1] Kosuke Furuya, Naotaka Yuki, "MULTIDIMENSIONAL NONSEPARABLE OVERSAMPLED LAPPED TRANSFORMS: THEORY AND DESIGN", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2218. Accessed: Dec. 15, 2017.
@article{2218-17,
url = {http://sigport.org/2218},
author = {Kosuke Furuya; Naotaka Yuki },
publisher = {IEEE SigPort},
title = {MULTIDIMENSIONAL NONSEPARABLE OVERSAMPLED LAPPED TRANSFORMS: THEORY AND DESIGN},
year = {2017} }
TY - EJOUR
T1 - MULTIDIMENSIONAL NONSEPARABLE OVERSAMPLED LAPPED TRANSFORMS: THEORY AND DESIGN
AU - Kosuke Furuya; Naotaka Yuki
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2218
ER -
Kosuke Furuya, Naotaka Yuki. (2017). MULTIDIMENSIONAL NONSEPARABLE OVERSAMPLED LAPPED TRANSFORMS: THEORY AND DESIGN. IEEE SigPort. http://sigport.org/2218
Kosuke Furuya, Naotaka Yuki, 2017. MULTIDIMENSIONAL NONSEPARABLE OVERSAMPLED LAPPED TRANSFORMS: THEORY AND DESIGN. Available at: http://sigport.org/2218.
Kosuke Furuya, Naotaka Yuki. (2017). "MULTIDIMENSIONAL NONSEPARABLE OVERSAMPLED LAPPED TRANSFORMS: THEORY AND DESIGN." Web.
1. Kosuke Furuya, Naotaka Yuki. MULTIDIMENSIONAL NONSEPARABLE OVERSAMPLED LAPPED TRANSFORMS: THEORY AND DESIGN [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2218

GAUSSIAN PROCESS DYNAMIC MODELING OF BAT FLAPPING FLIGHT


The flapping flight of bats can serve as an inspiration for flapping-wing air vehicles. Obtaining an understanding of bat flight requires detailed, occlusion-free kinematics data that can only be collected using large numbers of cameras. Here, we have explored the use of low-cost cameras with low frame rates that result in nonlinear, large-baseline motions in image space.

Paper Details

Authors:
Xu Yang, Hui Chen, Andrew Kurdila, and Rolf Müller
Submitted On:
16 September 2017 - 9:22pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2017_GPDMBat_BenderXu_final.pdf

(34 downloads)

Keywords

Subscribe

[1] Xu Yang, Hui Chen, Andrew Kurdila, and Rolf Müller, "GAUSSIAN PROCESS DYNAMIC MODELING OF BAT FLAPPING FLIGHT", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2203. Accessed: Dec. 15, 2017.
@article{2203-17,
url = {http://sigport.org/2203},
author = {Xu Yang; Hui Chen; Andrew Kurdila; and Rolf Müller },
publisher = {IEEE SigPort},
title = {GAUSSIAN PROCESS DYNAMIC MODELING OF BAT FLAPPING FLIGHT},
year = {2017} }
TY - EJOUR
T1 - GAUSSIAN PROCESS DYNAMIC MODELING OF BAT FLAPPING FLIGHT
AU - Xu Yang; Hui Chen; Andrew Kurdila; and Rolf Müller
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2203
ER -
Xu Yang, Hui Chen, Andrew Kurdila, and Rolf Müller. (2017). GAUSSIAN PROCESS DYNAMIC MODELING OF BAT FLAPPING FLIGHT. IEEE SigPort. http://sigport.org/2203
Xu Yang, Hui Chen, Andrew Kurdila, and Rolf Müller, 2017. GAUSSIAN PROCESS DYNAMIC MODELING OF BAT FLAPPING FLIGHT. Available at: http://sigport.org/2203.
Xu Yang, Hui Chen, Andrew Kurdila, and Rolf Müller. (2017). "GAUSSIAN PROCESS DYNAMIC MODELING OF BAT FLAPPING FLIGHT." Web.
1. Xu Yang, Hui Chen, Andrew Kurdila, and Rolf Müller. GAUSSIAN PROCESS DYNAMIC MODELING OF BAT FLAPPING FLIGHT [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2203

BACT-3D: A LEVEL SET SEGMENTATION APPROACH FOR DENSE MULTI-LAYERED 3D BACTERIAL BIOFILMS


In microscopy, new super-resolution methods are emerging that produce three-dimensional images at resolutions ten times smaller than that provided by traditional light microscopy. Such technology is enabling the exploration of structure and function in living tissues such as bacterial biofilms that have mysterious interconnections and organization. Unfortunately, the standard tools used in the image analysis community to perform segmentation and other higher-level analyses cannot be applied naively to these data.

Paper Details

Authors:
R. Sarkar, A. Aziz, A. Vaccari, A. Gahlmann and S. T. Acton
Submitted On:
16 September 2017 - 9:24pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP 2017 BACT-3D

(27 downloads)

Keywords

Subscribe

[1] R. Sarkar, A. Aziz, A. Vaccari, A. Gahlmann and S. T. Acton, "BACT-3D: A LEVEL SET SEGMENTATION APPROACH FOR DENSE MULTI-LAYERED 3D BACTERIAL BIOFILMS", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2202. Accessed: Dec. 15, 2017.
@article{2202-17,
url = {http://sigport.org/2202},
author = {R. Sarkar; A. Aziz; A. Vaccari; A. Gahlmann and S. T. Acton },
publisher = {IEEE SigPort},
title = {BACT-3D: A LEVEL SET SEGMENTATION APPROACH FOR DENSE MULTI-LAYERED 3D BACTERIAL BIOFILMS},
year = {2017} }
TY - EJOUR
T1 - BACT-3D: A LEVEL SET SEGMENTATION APPROACH FOR DENSE MULTI-LAYERED 3D BACTERIAL BIOFILMS
AU - R. Sarkar; A. Aziz; A. Vaccari; A. Gahlmann and S. T. Acton
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2202
ER -
R. Sarkar, A. Aziz, A. Vaccari, A. Gahlmann and S. T. Acton. (2017). BACT-3D: A LEVEL SET SEGMENTATION APPROACH FOR DENSE MULTI-LAYERED 3D BACTERIAL BIOFILMS. IEEE SigPort. http://sigport.org/2202
R. Sarkar, A. Aziz, A. Vaccari, A. Gahlmann and S. T. Acton, 2017. BACT-3D: A LEVEL SET SEGMENTATION APPROACH FOR DENSE MULTI-LAYERED 3D BACTERIAL BIOFILMS. Available at: http://sigport.org/2202.
R. Sarkar, A. Aziz, A. Vaccari, A. Gahlmann and S. T. Acton. (2017). "BACT-3D: A LEVEL SET SEGMENTATION APPROACH FOR DENSE MULTI-LAYERED 3D BACTERIAL BIOFILMS." Web.
1. R. Sarkar, A. Aziz, A. Vaccari, A. Gahlmann and S. T. Acton. BACT-3D: A LEVEL SET SEGMENTATION APPROACH FOR DENSE MULTI-LAYERED 3D BACTERIAL BIOFILMS [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2202

DEMONSTRATION OF AN HMM-BASED PHOTOREALISTIC EXPRESSIVE AUDIO-VISUAL SPEECH SYNTHESIS SYSTEM

Paper Details

Authors:
Athanasios Katsamanis, Petros Maragos
Submitted On:
16 September 2017 - 1:06pm
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

multimedia.zip

(24 downloads)

Keywords

Subscribe

[1] Athanasios Katsamanis, Petros Maragos, "DEMONSTRATION OF AN HMM-BASED PHOTOREALISTIC EXPRESSIVE AUDIO-VISUAL SPEECH SYNTHESIS SYSTEM", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2201. Accessed: Dec. 15, 2017.
@article{2201-17,
url = {http://sigport.org/2201},
author = {Athanasios Katsamanis; Petros Maragos },
publisher = {IEEE SigPort},
title = {DEMONSTRATION OF AN HMM-BASED PHOTOREALISTIC EXPRESSIVE AUDIO-VISUAL SPEECH SYNTHESIS SYSTEM},
year = {2017} }
TY - EJOUR
T1 - DEMONSTRATION OF AN HMM-BASED PHOTOREALISTIC EXPRESSIVE AUDIO-VISUAL SPEECH SYNTHESIS SYSTEM
AU - Athanasios Katsamanis; Petros Maragos
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2201
ER -
Athanasios Katsamanis, Petros Maragos. (2017). DEMONSTRATION OF AN HMM-BASED PHOTOREALISTIC EXPRESSIVE AUDIO-VISUAL SPEECH SYNTHESIS SYSTEM. IEEE SigPort. http://sigport.org/2201
Athanasios Katsamanis, Petros Maragos, 2017. DEMONSTRATION OF AN HMM-BASED PHOTOREALISTIC EXPRESSIVE AUDIO-VISUAL SPEECH SYNTHESIS SYSTEM. Available at: http://sigport.org/2201.
Athanasios Katsamanis, Petros Maragos. (2017). "DEMONSTRATION OF AN HMM-BASED PHOTOREALISTIC EXPRESSIVE AUDIO-VISUAL SPEECH SYNTHESIS SYSTEM." Web.
1. Athanasios Katsamanis, Petros Maragos. DEMONSTRATION OF AN HMM-BASED PHOTOREALISTIC EXPRESSIVE AUDIO-VISUAL SPEECH SYNTHESIS SYSTEM [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2201

PHOTOREALISTIC ADAPTATION AND INTERPOLATION OF FACIAL EXPRESSIONS USING HMMS AND AAMS FOR AUDIO-VISUAL SPEECH SYNTHESIS


In this paper, motivated by the continuously increasing presence of intelligent agents in everyday life, we address the problem of expres-sive photorealistic audio-visual speech synthesis, with a strong focus on the visual modality. Emotion constitutes one of the main driving factors of social life and it is expressed mainly through facial expres-sions. Synthesis of a talking head capable of expressive audio-visual speech is challenging due to the data overhead that arises when con-sidering the vast number of emotions we would like the talking head to express.

Paper Details

Authors:
Athanasios Katsamanis, Petros Maragos
Submitted On:
16 September 2017 - 12:51pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

pf_poster_icip-2017.pdf

(21 downloads)

Keywords

Subscribe

[1] Athanasios Katsamanis, Petros Maragos, "PHOTOREALISTIC ADAPTATION AND INTERPOLATION OF FACIAL EXPRESSIONS USING HMMS AND AAMS FOR AUDIO-VISUAL SPEECH SYNTHESIS ", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2200. Accessed: Dec. 15, 2017.
@article{2200-17,
url = {http://sigport.org/2200},
author = {Athanasios Katsamanis; Petros Maragos },
publisher = {IEEE SigPort},
title = {PHOTOREALISTIC ADAPTATION AND INTERPOLATION OF FACIAL EXPRESSIONS USING HMMS AND AAMS FOR AUDIO-VISUAL SPEECH SYNTHESIS },
year = {2017} }
TY - EJOUR
T1 - PHOTOREALISTIC ADAPTATION AND INTERPOLATION OF FACIAL EXPRESSIONS USING HMMS AND AAMS FOR AUDIO-VISUAL SPEECH SYNTHESIS
AU - Athanasios Katsamanis; Petros Maragos
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2200
ER -
Athanasios Katsamanis, Petros Maragos. (2017). PHOTOREALISTIC ADAPTATION AND INTERPOLATION OF FACIAL EXPRESSIONS USING HMMS AND AAMS FOR AUDIO-VISUAL SPEECH SYNTHESIS . IEEE SigPort. http://sigport.org/2200
Athanasios Katsamanis, Petros Maragos, 2017. PHOTOREALISTIC ADAPTATION AND INTERPOLATION OF FACIAL EXPRESSIONS USING HMMS AND AAMS FOR AUDIO-VISUAL SPEECH SYNTHESIS . Available at: http://sigport.org/2200.
Athanasios Katsamanis, Petros Maragos. (2017). "PHOTOREALISTIC ADAPTATION AND INTERPOLATION OF FACIAL EXPRESSIONS USING HMMS AND AAMS FOR AUDIO-VISUAL SPEECH SYNTHESIS ." Web.
1. Athanasios Katsamanis, Petros Maragos. PHOTOREALISTIC ADAPTATION AND INTERPOLATION OF FACIAL EXPRESSIONS USING HMMS AND AAMS FOR AUDIO-VISUAL SPEECH SYNTHESIS [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2200

MOTION FEATURE AUGMENTED RECURRENT NEURAL NETWORK FOR SKELETON-BASED DYNAMIC HAND GESTURE RECOGNITION


Dynamic hand gesture recognition has attracted increasing interests because of its importance for human computer interaction. In this paper, we propose a new motion feature augmented recurrent neural network for skeleton-based dynamic hand gesture recognition. Finger motion features are extracted to describe finger movements and global motion features are utilized to represent the global movement of hand skeleton.

Paper Details

Authors:
Xinghao Chen, Hengkai Guo, Guijin Wang, Li Zhang
Submitted On:
16 September 2017 - 11:39am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2017-Poster-Chen.pdf

(27 downloads)

Keywords

Subscribe

[1] Xinghao Chen, Hengkai Guo, Guijin Wang, Li Zhang, "MOTION FEATURE AUGMENTED RECURRENT NEURAL NETWORK FOR SKELETON-BASED DYNAMIC HAND GESTURE RECOGNITION", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2198. Accessed: Dec. 15, 2017.
@article{2198-17,
url = {http://sigport.org/2198},
author = {Xinghao Chen; Hengkai Guo; Guijin Wang; Li Zhang },
publisher = {IEEE SigPort},
title = {MOTION FEATURE AUGMENTED RECURRENT NEURAL NETWORK FOR SKELETON-BASED DYNAMIC HAND GESTURE RECOGNITION},
year = {2017} }
TY - EJOUR
T1 - MOTION FEATURE AUGMENTED RECURRENT NEURAL NETWORK FOR SKELETON-BASED DYNAMIC HAND GESTURE RECOGNITION
AU - Xinghao Chen; Hengkai Guo; Guijin Wang; Li Zhang
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2198
ER -
Xinghao Chen, Hengkai Guo, Guijin Wang, Li Zhang. (2017). MOTION FEATURE AUGMENTED RECURRENT NEURAL NETWORK FOR SKELETON-BASED DYNAMIC HAND GESTURE RECOGNITION. IEEE SigPort. http://sigport.org/2198
Xinghao Chen, Hengkai Guo, Guijin Wang, Li Zhang, 2017. MOTION FEATURE AUGMENTED RECURRENT NEURAL NETWORK FOR SKELETON-BASED DYNAMIC HAND GESTURE RECOGNITION. Available at: http://sigport.org/2198.
Xinghao Chen, Hengkai Guo, Guijin Wang, Li Zhang. (2017). "MOTION FEATURE AUGMENTED RECURRENT NEURAL NETWORK FOR SKELETON-BASED DYNAMIC HAND GESTURE RECOGNITION." Web.
1. Xinghao Chen, Hengkai Guo, Guijin Wang, Li Zhang. MOTION FEATURE AUGMENTED RECURRENT NEURAL NETWORK FOR SKELETON-BASED DYNAMIC HAND GESTURE RECOGNITION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2198

Visual Tracking via Structural Patch-based Dictionary Pair Learning

Paper Details

Authors:
Submitted On:
16 September 2017 - 11:27am
Short Link:
Type:
Event:

Document Files

TaoZhou_ICIP_2017.pdf

(38 downloads)

Keywords

Subscribe

[1] , "Visual Tracking via Structural Patch-based Dictionary Pair Learning", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2197. Accessed: Dec. 15, 2017.
@article{2197-17,
url = {http://sigport.org/2197},
author = { },
publisher = {IEEE SigPort},
title = {Visual Tracking via Structural Patch-based Dictionary Pair Learning},
year = {2017} }
TY - EJOUR
T1 - Visual Tracking via Structural Patch-based Dictionary Pair Learning
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2197
ER -
. (2017). Visual Tracking via Structural Patch-based Dictionary Pair Learning. IEEE SigPort. http://sigport.org/2197
, 2017. Visual Tracking via Structural Patch-based Dictionary Pair Learning. Available at: http://sigport.org/2197.
. (2017). "Visual Tracking via Structural Patch-based Dictionary Pair Learning." Web.
1. . Visual Tracking via Structural Patch-based Dictionary Pair Learning [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2197

MULTIPLE PATH SEARCH FOR ACTION TUBE DETECTION IN VIDEOS


This paper presents an efficient convolutional neural net- work (CNN)-based multiple path search (MPS) algorithm to detect multiple spatial-temporal action tubes in videos. With the pass information and the accumulated scores generated by forward message passing, the new algorithm reuses these information to simultaneously find multiple paths in back- ward path tracing without repeating the search process. More- over, to rectify the potentially inaccurate bounding boxes, we also propose a video localization refinement scheme to further boost the detection accuracy.

Paper Details

Authors:
Erick Hendra Putra Alwand Wen-Hsien Fang
Submitted On:
16 September 2017 - 11:23am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

MULTIPLE PATH SEARCH FOR ACTION TUBE DETECTION IN VIDEOS

(89 downloads)

Keywords

Subscribe

[1] Erick Hendra Putra Alwand Wen-Hsien Fang, "MULTIPLE PATH SEARCH FOR ACTION TUBE DETECTION IN VIDEOS", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2196. Accessed: Dec. 15, 2017.
@article{2196-17,
url = {http://sigport.org/2196},
author = {Erick Hendra Putra Alwand Wen-Hsien Fang },
publisher = {IEEE SigPort},
title = {MULTIPLE PATH SEARCH FOR ACTION TUBE DETECTION IN VIDEOS},
year = {2017} }
TY - EJOUR
T1 - MULTIPLE PATH SEARCH FOR ACTION TUBE DETECTION IN VIDEOS
AU - Erick Hendra Putra Alwand Wen-Hsien Fang
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2196
ER -
Erick Hendra Putra Alwand Wen-Hsien Fang. (2017). MULTIPLE PATH SEARCH FOR ACTION TUBE DETECTION IN VIDEOS. IEEE SigPort. http://sigport.org/2196
Erick Hendra Putra Alwand Wen-Hsien Fang, 2017. MULTIPLE PATH SEARCH FOR ACTION TUBE DETECTION IN VIDEOS. Available at: http://sigport.org/2196.
Erick Hendra Putra Alwand Wen-Hsien Fang. (2017). "MULTIPLE PATH SEARCH FOR ACTION TUBE DETECTION IN VIDEOS." Web.
1. Erick Hendra Putra Alwand Wen-Hsien Fang. MULTIPLE PATH SEARCH FOR ACTION TUBE DETECTION IN VIDEOS [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2196

Pages