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

Image/Video Storage, Retrieval

How should we evaluate supervised hashing?

Paper Details

Authors:
Matthijs Douze, Nicolas Usunier, Hervé Jégou
Submitted On:
2 March 2017 - 3:08pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster_landscape.pdf

(43 downloads)

Keywords

Subscribe

[1] Matthijs Douze, Nicolas Usunier, Hervé Jégou, "How should we evaluate supervised hashing?", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1595. Accessed: Jun. 29, 2017.
@article{1595-17,
url = {http://sigport.org/1595},
author = {Matthijs Douze; Nicolas Usunier; Hervé Jégou },
publisher = {IEEE SigPort},
title = {How should we evaluate supervised hashing?},
year = {2017} }
TY - EJOUR
T1 - How should we evaluate supervised hashing?
AU - Matthijs Douze; Nicolas Usunier; Hervé Jégou
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1595
ER -
Matthijs Douze, Nicolas Usunier, Hervé Jégou. (2017). How should we evaluate supervised hashing?. IEEE SigPort. http://sigport.org/1595
Matthijs Douze, Nicolas Usunier, Hervé Jégou, 2017. How should we evaluate supervised hashing?. Available at: http://sigport.org/1595.
Matthijs Douze, Nicolas Usunier, Hervé Jégou. (2017). "How should we evaluate supervised hashing?." Web.
1. Matthijs Douze, Nicolas Usunier, Hervé Jégou. How should we evaluate supervised hashing? [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1595

Summarization of Human Activity Videos Via Low-Rank Approximation


Summarization of videos depicting human activities is a timely problem with important applications, e.g., in the domains of surveillance or film/TV production, that steadily becomes more relevant. Research on video summarization has mainly relied on global clustering or local (frame-by-frame) saliency methods to provide automated algorithmic

Paper Details

Authors:
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas
Submitted On:
1 March 2017 - 6:25am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Summarization of Human Activity Videos Via Low-Rank Approximation

(146 downloads)

Keywords

Additional Categories

Subscribe

[1] Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas, "Summarization of Human Activity Videos Via Low-Rank Approximation", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1548. Accessed: Jun. 29, 2017.
@article{1548-17,
url = {http://sigport.org/1548},
author = {Anastasios Tefas; Nikos Nikolaidis; Ioannis Pitas },
publisher = {IEEE SigPort},
title = {Summarization of Human Activity Videos Via Low-Rank Approximation},
year = {2017} }
TY - EJOUR
T1 - Summarization of Human Activity Videos Via Low-Rank Approximation
AU - Anastasios Tefas; Nikos Nikolaidis; Ioannis Pitas
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1548
ER -
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. (2017). Summarization of Human Activity Videos Via Low-Rank Approximation. IEEE SigPort. http://sigport.org/1548
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas, 2017. Summarization of Human Activity Videos Via Low-Rank Approximation. Available at: http://sigport.org/1548.
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. (2017). "Summarization of Human Activity Videos Via Low-Rank Approximation." Web.
1. Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. Summarization of Human Activity Videos Via Low-Rank Approximation [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1548

Summarization of Human Activity Videos Via Low-Rank Approximation


Summarization of videos depicting human activities is a timely problem with important applications, e.g., in the domains of surveillance or film/TV production, that steadily becomes more relevant. Research on video summarization has mainly relied on global clustering or local (frame-by-frame) saliency methods to provide automated algorithmic

Paper Details

Authors:
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas
Submitted On:
1 March 2017 - 6:25am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Summarization of Human Activity Videos Via Low-Rank Approximation

(146 downloads)

Keywords

Additional Categories

Subscribe

[1] Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas, "Summarization of Human Activity Videos Via Low-Rank Approximation", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1547. Accessed: Jun. 29, 2017.
@article{1547-17,
url = {http://sigport.org/1547},
author = {Anastasios Tefas; Nikos Nikolaidis; Ioannis Pitas },
publisher = {IEEE SigPort},
title = {Summarization of Human Activity Videos Via Low-Rank Approximation},
year = {2017} }
TY - EJOUR
T1 - Summarization of Human Activity Videos Via Low-Rank Approximation
AU - Anastasios Tefas; Nikos Nikolaidis; Ioannis Pitas
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1547
ER -
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. (2017). Summarization of Human Activity Videos Via Low-Rank Approximation. IEEE SigPort. http://sigport.org/1547
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas, 2017. Summarization of Human Activity Videos Via Low-Rank Approximation. Available at: http://sigport.org/1547.
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. (2017). "Summarization of Human Activity Videos Via Low-Rank Approximation." Web.
1. Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. Summarization of Human Activity Videos Via Low-Rank Approximation [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1547

Summarization of Human Activity Videos Via Low-Rank Approximation


Summarization of videos depicting human activities is a timely problem with important applications, e.g., in the domains of surveillance or film/TV production, that steadily becomes more relevant. Research on video summarization has mainly relied on global clustering or local (frame-by-frame) saliency methods to provide automated algorithmic

Paper Details

Authors:
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas
Submitted On:
1 March 2017 - 6:25am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Summarization of Human Activity Videos Via Low-Rank Approximation

(146 downloads)

Keywords

Additional Categories

Subscribe

[1] Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas, "Summarization of Human Activity Videos Via Low-Rank Approximation", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1546. Accessed: Jun. 29, 2017.
@article{1546-17,
url = {http://sigport.org/1546},
author = {Anastasios Tefas; Nikos Nikolaidis; Ioannis Pitas },
publisher = {IEEE SigPort},
title = {Summarization of Human Activity Videos Via Low-Rank Approximation},
year = {2017} }
TY - EJOUR
T1 - Summarization of Human Activity Videos Via Low-Rank Approximation
AU - Anastasios Tefas; Nikos Nikolaidis; Ioannis Pitas
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1546
ER -
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. (2017). Summarization of Human Activity Videos Via Low-Rank Approximation. IEEE SigPort. http://sigport.org/1546
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas, 2017. Summarization of Human Activity Videos Via Low-Rank Approximation. Available at: http://sigport.org/1546.
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. (2017). "Summarization of Human Activity Videos Via Low-Rank Approximation." Web.
1. Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. Summarization of Human Activity Videos Via Low-Rank Approximation [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1546

Summarization of Human Activity Videos Via Low-Rank Approximation


Summarization of videos depicting human activities is a timely problem with important applications, e.g., in the domains of surveillance or film/TV production, that steadily becomes more relevant. Research on video summarization has mainly relied on global clustering or local (frame-by-frame) saliency methods to provide automated algorithmic

Paper Details

Authors:
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas
Submitted On:
1 March 2017 - 6:25am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Summarization of Human Activity Videos Via Low-Rank Approximation

(146 downloads)

Keywords

Additional Categories

Subscribe

[1] Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas, "Summarization of Human Activity Videos Via Low-Rank Approximation", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1545. Accessed: Jun. 29, 2017.
@article{1545-17,
url = {http://sigport.org/1545},
author = {Anastasios Tefas; Nikos Nikolaidis; Ioannis Pitas },
publisher = {IEEE SigPort},
title = {Summarization of Human Activity Videos Via Low-Rank Approximation},
year = {2017} }
TY - EJOUR
T1 - Summarization of Human Activity Videos Via Low-Rank Approximation
AU - Anastasios Tefas; Nikos Nikolaidis; Ioannis Pitas
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1545
ER -
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. (2017). Summarization of Human Activity Videos Via Low-Rank Approximation. IEEE SigPort. http://sigport.org/1545
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas, 2017. Summarization of Human Activity Videos Via Low-Rank Approximation. Available at: http://sigport.org/1545.
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. (2017). "Summarization of Human Activity Videos Via Low-Rank Approximation." Web.
1. Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. Summarization of Human Activity Videos Via Low-Rank Approximation [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1545

Summarization of Human Activity Videos Via Low-Rank Approximation


Summarization of videos depicting human activities is a timely problem with important applications, e.g., in the domains of surveillance or film/TV production, that steadily becomes more relevant. Research on video summarization has mainly relied on global clustering or local (frame-by-frame) saliency methods to provide automated algorithmic

Paper Details

Authors:
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas
Submitted On:
1 March 2017 - 6:25am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Summarization of Human Activity Videos Via Low-Rank Approximation

(146 downloads)

Keywords

Additional Categories

Subscribe

[1] Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas, "Summarization of Human Activity Videos Via Low-Rank Approximation", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1544. Accessed: Jun. 29, 2017.
@article{1544-17,
url = {http://sigport.org/1544},
author = {Anastasios Tefas; Nikos Nikolaidis; Ioannis Pitas },
publisher = {IEEE SigPort},
title = {Summarization of Human Activity Videos Via Low-Rank Approximation},
year = {2017} }
TY - EJOUR
T1 - Summarization of Human Activity Videos Via Low-Rank Approximation
AU - Anastasios Tefas; Nikos Nikolaidis; Ioannis Pitas
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1544
ER -
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. (2017). Summarization of Human Activity Videos Via Low-Rank Approximation. IEEE SigPort. http://sigport.org/1544
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas, 2017. Summarization of Human Activity Videos Via Low-Rank Approximation. Available at: http://sigport.org/1544.
Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. (2017). "Summarization of Human Activity Videos Via Low-Rank Approximation." Web.
1. Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas. Summarization of Human Activity Videos Via Low-Rank Approximation [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1544

EDITED FILM ALIGNMENT VIA SELECTIVE HOUGH TRANSFORM AND ACCURATE TEMPLATE MATCHING


Edited film alignment is the post-production process of finding small parts of unedited footage that temporally and spatially match an edited film. The huge amount of data to be processed makes significant downsampling of the videos essential in real-life applications. Simultaneously, professional users demand that the task be achieved with frame and pixel-level accuracy. We propose a novel selective Hough transform (SHT) and an accurate template matching method to address the difficult trade-off between accuracy and scalability.

1232.pdf

PDF icon 1232.pdf (34 downloads)

Paper Details

Authors:
Xiaomeng Wu, Takahito Kawanishi, Minoru Mori, Kaoru Hiramatsu, and Kunio Kashino
Submitted On:
28 February 2017 - 11:28pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

1232.pdf

(34 downloads)

Keywords

Subscribe

[1] Xiaomeng Wu, Takahito Kawanishi, Minoru Mori, Kaoru Hiramatsu, and Kunio Kashino, "EDITED FILM ALIGNMENT VIA SELECTIVE HOUGH TRANSFORM AND ACCURATE TEMPLATE MATCHING", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1528. Accessed: Jun. 29, 2017.
@article{1528-17,
url = {http://sigport.org/1528},
author = {Xiaomeng Wu; Takahito Kawanishi; Minoru Mori; Kaoru Hiramatsu; and Kunio Kashino },
publisher = {IEEE SigPort},
title = {EDITED FILM ALIGNMENT VIA SELECTIVE HOUGH TRANSFORM AND ACCURATE TEMPLATE MATCHING},
year = {2017} }
TY - EJOUR
T1 - EDITED FILM ALIGNMENT VIA SELECTIVE HOUGH TRANSFORM AND ACCURATE TEMPLATE MATCHING
AU - Xiaomeng Wu; Takahito Kawanishi; Minoru Mori; Kaoru Hiramatsu; and Kunio Kashino
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1528
ER -
Xiaomeng Wu, Takahito Kawanishi, Minoru Mori, Kaoru Hiramatsu, and Kunio Kashino. (2017). EDITED FILM ALIGNMENT VIA SELECTIVE HOUGH TRANSFORM AND ACCURATE TEMPLATE MATCHING. IEEE SigPort. http://sigport.org/1528
Xiaomeng Wu, Takahito Kawanishi, Minoru Mori, Kaoru Hiramatsu, and Kunio Kashino, 2017. EDITED FILM ALIGNMENT VIA SELECTIVE HOUGH TRANSFORM AND ACCURATE TEMPLATE MATCHING. Available at: http://sigport.org/1528.
Xiaomeng Wu, Takahito Kawanishi, Minoru Mori, Kaoru Hiramatsu, and Kunio Kashino. (2017). "EDITED FILM ALIGNMENT VIA SELECTIVE HOUGH TRANSFORM AND ACCURATE TEMPLATE MATCHING." Web.
1. Xiaomeng Wu, Takahito Kawanishi, Minoru Mori, Kaoru Hiramatsu, and Kunio Kashino. EDITED FILM ALIGNMENT VIA SELECTIVE HOUGH TRANSFORM AND ACCURATE TEMPLATE MATCHING [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1528

Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning

Paper Details

Authors:
Submitted On:
28 February 2017 - 9:31pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Image Retrieval

(59 downloads)

Keywords

Subscribe

[1] , "Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1520. Accessed: Jun. 29, 2017.
@article{1520-17,
url = {http://sigport.org/1520},
author = { },
publisher = {IEEE SigPort},
title = {Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning},
year = {2017} }
TY - EJOUR
T1 - Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1520
ER -
. (2017). Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning. IEEE SigPort. http://sigport.org/1520
, 2017. Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning. Available at: http://sigport.org/1520.
. (2017). "Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning." Web.
1. . Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1520

Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning

Paper Details

Authors:
Submitted On:
28 February 2017 - 9:17pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Image Retrieval

(59 downloads)

Keywords

Subscribe

[1] , "Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1519. Accessed: Jun. 29, 2017.
@article{1519-17,
url = {http://sigport.org/1519},
author = { },
publisher = {IEEE SigPort},
title = {Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning},
year = {2017} }
TY - EJOUR
T1 - Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1519
ER -
. (2017). Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning. IEEE SigPort. http://sigport.org/1519
, 2017. Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning. Available at: http://sigport.org/1519.
. (2017). "Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning." Web.
1. . Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1519

Enhanced Vote Count Circuit based on NOR Flash Memory for Fast Similarity Search

Paper Details

Authors:
Haiyan Shu, Wenyu Jiang, Xiaoming Bao, Huan Zhou, Rongshan Yu
Submitted On:
20 March 2016 - 6:59am
Short Link:
Type:

Document Files

EVC_ICASSP2016_v1a_printout.pdf

(157 downloads)

Keywords

Subscribe

[1] Haiyan Shu, Wenyu Jiang, Xiaoming Bao, Huan Zhou, Rongshan Yu, "Enhanced Vote Count Circuit based on NOR Flash Memory for Fast Similarity Search", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/868. Accessed: Jun. 29, 2017.
@article{868-16,
url = {http://sigport.org/868},
author = {Haiyan Shu; Wenyu Jiang; Xiaoming Bao; Huan Zhou; Rongshan Yu },
publisher = {IEEE SigPort},
title = {Enhanced Vote Count Circuit based on NOR Flash Memory for Fast Similarity Search},
year = {2016} }
TY - EJOUR
T1 - Enhanced Vote Count Circuit based on NOR Flash Memory for Fast Similarity Search
AU - Haiyan Shu; Wenyu Jiang; Xiaoming Bao; Huan Zhou; Rongshan Yu
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/868
ER -
Haiyan Shu, Wenyu Jiang, Xiaoming Bao, Huan Zhou, Rongshan Yu. (2016). Enhanced Vote Count Circuit based on NOR Flash Memory for Fast Similarity Search. IEEE SigPort. http://sigport.org/868
Haiyan Shu, Wenyu Jiang, Xiaoming Bao, Huan Zhou, Rongshan Yu, 2016. Enhanced Vote Count Circuit based on NOR Flash Memory for Fast Similarity Search. Available at: http://sigport.org/868.
Haiyan Shu, Wenyu Jiang, Xiaoming Bao, Huan Zhou, Rongshan Yu. (2016). "Enhanced Vote Count Circuit based on NOR Flash Memory for Fast Similarity Search." Web.
1. Haiyan Shu, Wenyu Jiang, Xiaoming Bao, Huan Zhou, Rongshan Yu. Enhanced Vote Count Circuit based on NOR Flash Memory for Fast Similarity Search [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/868

Pages