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

Image, Video, and Multidimensional Signal Processing

COMPLEX PAIRWISE ACTIVITY ANALYSIS VIA INSTANCE LEVEL EVOLUTION REASONING


Video activity analysis systems are often trained on large datasets. Activities and events in the real-world do not occur in isolation, instead, they occur as interactions between related objects. This work introduces a novel method that jointly exploits relational information between pairs of objects and temporal dynamics of each object. The proposed method effectively leverages a new simple architecture that is flexible and easily trained to detect relational activities and events using small datasets (hundreds of samples).

Paper Details

Authors:
Sudipta Paul, Carlos Torres, Shivkumar Chandrasekaran, Amit K. Roy-Chowdhury
Submitted On:
13 May 2020 - 5:43pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

5348_complex_pairwise_activity_presentation.pdf

(31)

Subscribe

[1] Sudipta Paul, Carlos Torres, Shivkumar Chandrasekaran, Amit K. Roy-Chowdhury, "COMPLEX PAIRWISE ACTIVITY ANALYSIS VIA INSTANCE LEVEL EVOLUTION REASONING", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5157. Accessed: Sep. 23, 2020.
@article{5157-20,
url = {http://sigport.org/5157},
author = {Sudipta Paul; Carlos Torres; Shivkumar Chandrasekaran; Amit K. Roy-Chowdhury },
publisher = {IEEE SigPort},
title = {COMPLEX PAIRWISE ACTIVITY ANALYSIS VIA INSTANCE LEVEL EVOLUTION REASONING},
year = {2020} }
TY - EJOUR
T1 - COMPLEX PAIRWISE ACTIVITY ANALYSIS VIA INSTANCE LEVEL EVOLUTION REASONING
AU - Sudipta Paul; Carlos Torres; Shivkumar Chandrasekaran; Amit K. Roy-Chowdhury
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5157
ER -
Sudipta Paul, Carlos Torres, Shivkumar Chandrasekaran, Amit K. Roy-Chowdhury. (2020). COMPLEX PAIRWISE ACTIVITY ANALYSIS VIA INSTANCE LEVEL EVOLUTION REASONING. IEEE SigPort. http://sigport.org/5157
Sudipta Paul, Carlos Torres, Shivkumar Chandrasekaran, Amit K. Roy-Chowdhury, 2020. COMPLEX PAIRWISE ACTIVITY ANALYSIS VIA INSTANCE LEVEL EVOLUTION REASONING. Available at: http://sigport.org/5157.
Sudipta Paul, Carlos Torres, Shivkumar Chandrasekaran, Amit K. Roy-Chowdhury. (2020). "COMPLEX PAIRWISE ACTIVITY ANALYSIS VIA INSTANCE LEVEL EVOLUTION REASONING." Web.
1. Sudipta Paul, Carlos Torres, Shivkumar Chandrasekaran, Amit K. Roy-Chowdhury. COMPLEX PAIRWISE ACTIVITY ANALYSIS VIA INSTANCE LEVEL EVOLUTION REASONING [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5157

Key Action And Joint CTC-Attention Based Sign Language Recognition


Sign Language Recognition (SLR) translates sign language video into natural language. In practice, sign language video, owning a large number of redundant frames, is necessary to be selected the essential. However, unlike common video that describes actions, sign language video is characterized as continuous and dense action sequence, which is difficult to capture key actions corresponding to meaningful sentence. In this paper, we propose to hierarchically search key actions by a pyramid BiLSTM.

Paper Details

Authors:
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng
Submitted On:
16 April 2020 - 11:39am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster_video5717.pdf

(52)

Subscribe

[1] Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng, "Key Action And Joint CTC-Attention Based Sign Language Recognition", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5100. Accessed: Sep. 23, 2020.
@article{5100-20,
url = {http://sigport.org/5100},
author = {Haibo Li; Liqing Gao; Ruize Han; Liang Wan; Wei Feng },
publisher = {IEEE SigPort},
title = {Key Action And Joint CTC-Attention Based Sign Language Recognition},
year = {2020} }
TY - EJOUR
T1 - Key Action And Joint CTC-Attention Based Sign Language Recognition
AU - Haibo Li; Liqing Gao; Ruize Han; Liang Wan; Wei Feng
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5100
ER -
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng. (2020). Key Action And Joint CTC-Attention Based Sign Language Recognition. IEEE SigPort. http://sigport.org/5100
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng, 2020. Key Action And Joint CTC-Attention Based Sign Language Recognition. Available at: http://sigport.org/5100.
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng. (2020). "Key Action And Joint CTC-Attention Based Sign Language Recognition." Web.
1. Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng. Key Action And Joint CTC-Attention Based Sign Language Recognition [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5100

Key Action And Joint CTC-Attention Based Sign Language Recognition


Sign Language Recognition (SLR) translates sign language video into natural language. In practice, sign language video, owning a large number of redundant frames, is necessary to be selected the essential. However, unlike common video that describes actions, sign language video is characterized as continuous and dense action sequence, which is difficult to capture key actions corresponding to meaningful sentence. In this paper, we propose to hierarchically search key actions by a pyramid BiLSTM.

Paper Details

Authors:
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng
Submitted On:
16 April 2020 - 11:38am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

poster_video5717.pdf

(70)

Subscribe

[1] Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng, "Key Action And Joint CTC-Attention Based Sign Language Recognition", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5099. Accessed: Sep. 23, 2020.
@article{5099-20,
url = {http://sigport.org/5099},
author = {Haibo Li; Liqing Gao; Ruize Han; Liang Wan; Wei Feng },
publisher = {IEEE SigPort},
title = {Key Action And Joint CTC-Attention Based Sign Language Recognition},
year = {2020} }
TY - EJOUR
T1 - Key Action And Joint CTC-Attention Based Sign Language Recognition
AU - Haibo Li; Liqing Gao; Ruize Han; Liang Wan; Wei Feng
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5099
ER -
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng. (2020). Key Action And Joint CTC-Attention Based Sign Language Recognition. IEEE SigPort. http://sigport.org/5099
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng, 2020. Key Action And Joint CTC-Attention Based Sign Language Recognition. Available at: http://sigport.org/5099.
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng. (2020). "Key Action And Joint CTC-Attention Based Sign Language Recognition." Web.
1. Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng. Key Action And Joint CTC-Attention Based Sign Language Recognition [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5099

Efficient Storage of Images onto DNA Using Vector Quantization


The archiving of digital data is becoming very challenging as conventional electronic devices wear out in time leaving at stake any data that has been stored in them. Therefore, data migration is necessary every 5-10 years. A great percentage of this stored data is "cold", which means that it is very rarely accessed but needs to be safely stored into back-up drives for security and compliance reasons. Unfortunately, the maintenance and replacement of back-up tape drives in big data centers is very expensive both in terms of money and energy.

Paper Details

Authors:
Melpomeni Dimopoulou, Marc Antonini
Submitted On:
2 April 2020 - 5:05am
Short Link:
Type:
Event:
Session:
Document Year:
Cite

Document Files

Dimopoulou_DCC_poster.pdf

(80)

Subscribe

[1] Melpomeni Dimopoulou, Marc Antonini, "Efficient Storage of Images onto DNA Using Vector Quantization", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5085. Accessed: Sep. 23, 2020.
@article{5085-20,
url = {http://sigport.org/5085},
author = {Melpomeni Dimopoulou; Marc Antonini },
publisher = {IEEE SigPort},
title = {Efficient Storage of Images onto DNA Using Vector Quantization},
year = {2020} }
TY - EJOUR
T1 - Efficient Storage of Images onto DNA Using Vector Quantization
AU - Melpomeni Dimopoulou; Marc Antonini
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5085
ER -
Melpomeni Dimopoulou, Marc Antonini. (2020). Efficient Storage of Images onto DNA Using Vector Quantization. IEEE SigPort. http://sigport.org/5085
Melpomeni Dimopoulou, Marc Antonini, 2020. Efficient Storage of Images onto DNA Using Vector Quantization. Available at: http://sigport.org/5085.
Melpomeni Dimopoulou, Marc Antonini. (2020). "Efficient Storage of Images onto DNA Using Vector Quantization." Web.
1. Melpomeni Dimopoulou, Marc Antonini. Efficient Storage of Images onto DNA Using Vector Quantization [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5085

MODEL-INDEPENDENT RATE CONTROL FOR INTRA-CODING BASED ON PIECEWISE LINEAR APPROXIMATIONS

Paper Details

Authors:
Submitted On:
31 March 2020 - 7:58am
Short Link:
Type:
Event:
Presenter's Name:
Session:
Document Year:
Cite

Document Files

DCC2020_POSTER_SANCHEZ.pdf

(58)

Subscribe

[1] , "MODEL-INDEPENDENT RATE CONTROL FOR INTRA-CODING BASED ON PIECEWISE LINEAR APPROXIMATIONS", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5080. Accessed: Sep. 23, 2020.
@article{5080-20,
url = {http://sigport.org/5080},
author = { },
publisher = {IEEE SigPort},
title = {MODEL-INDEPENDENT RATE CONTROL FOR INTRA-CODING BASED ON PIECEWISE LINEAR APPROXIMATIONS},
year = {2020} }
TY - EJOUR
T1 - MODEL-INDEPENDENT RATE CONTROL FOR INTRA-CODING BASED ON PIECEWISE LINEAR APPROXIMATIONS
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5080
ER -
. (2020). MODEL-INDEPENDENT RATE CONTROL FOR INTRA-CODING BASED ON PIECEWISE LINEAR APPROXIMATIONS. IEEE SigPort. http://sigport.org/5080
, 2020. MODEL-INDEPENDENT RATE CONTROL FOR INTRA-CODING BASED ON PIECEWISE LINEAR APPROXIMATIONS. Available at: http://sigport.org/5080.
. (2020). "MODEL-INDEPENDENT RATE CONTROL FOR INTRA-CODING BASED ON PIECEWISE LINEAR APPROXIMATIONS." Web.
1. . MODEL-INDEPENDENT RATE CONTROL FOR INTRA-CODING BASED ON PIECEWISE LINEAR APPROXIMATIONS [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5080

Implicit Geometry Partition for Point Cloud Compression

Paper Details

Authors:
Xiang Zhang, Wen Gao, Shan Liu
Submitted On:
31 March 2020 - 1:01am
Short Link:
Type:
Event:
Presenter's Name:
Session:
Document Year:
Cite

Document Files

DCC2020-179-Implicit Geometry Partition for Point Cloud Compression.pdf

(53)

Subscribe

[1] Xiang Zhang, Wen Gao, Shan Liu, "Implicit Geometry Partition for Point Cloud Compression", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5065. Accessed: Sep. 23, 2020.
@article{5065-20,
url = {http://sigport.org/5065},
author = {Xiang Zhang; Wen Gao; Shan Liu },
publisher = {IEEE SigPort},
title = {Implicit Geometry Partition for Point Cloud Compression},
year = {2020} }
TY - EJOUR
T1 - Implicit Geometry Partition for Point Cloud Compression
AU - Xiang Zhang; Wen Gao; Shan Liu
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5065
ER -
Xiang Zhang, Wen Gao, Shan Liu. (2020). Implicit Geometry Partition for Point Cloud Compression. IEEE SigPort. http://sigport.org/5065
Xiang Zhang, Wen Gao, Shan Liu, 2020. Implicit Geometry Partition for Point Cloud Compression. Available at: http://sigport.org/5065.
Xiang Zhang, Wen Gao, Shan Liu. (2020). "Implicit Geometry Partition for Point Cloud Compression." Web.
1. Xiang Zhang, Wen Gao, Shan Liu. Implicit Geometry Partition for Point Cloud Compression [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5065

Linear Model based Geometry Coding for Lidar Acquired Point Clouds

Paper Details

Authors:
Xiang Zhang, Wen Gao, Shan Liu
Submitted On:
30 March 2020 - 11:51am
Short Link:
Type:
Event:
Presenter's Name:
Session:
Document Year:
Cite

Document Files

DCC2020_180_Linear_Model_for_PCC__poster_.pdf

(51)

Subscribe

[1] Xiang Zhang, Wen Gao, Shan Liu, "Linear Model based Geometry Coding for Lidar Acquired Point Clouds", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5064. Accessed: Sep. 23, 2020.
@article{5064-20,
url = {http://sigport.org/5064},
author = {Xiang Zhang; Wen Gao; Shan Liu },
publisher = {IEEE SigPort},
title = {Linear Model based Geometry Coding for Lidar Acquired Point Clouds},
year = {2020} }
TY - EJOUR
T1 - Linear Model based Geometry Coding for Lidar Acquired Point Clouds
AU - Xiang Zhang; Wen Gao; Shan Liu
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5064
ER -
Xiang Zhang, Wen Gao, Shan Liu. (2020). Linear Model based Geometry Coding for Lidar Acquired Point Clouds. IEEE SigPort. http://sigport.org/5064
Xiang Zhang, Wen Gao, Shan Liu, 2020. Linear Model based Geometry Coding for Lidar Acquired Point Clouds. Available at: http://sigport.org/5064.
Xiang Zhang, Wen Gao, Shan Liu. (2020). "Linear Model based Geometry Coding for Lidar Acquired Point Clouds." Web.
1. Xiang Zhang, Wen Gao, Shan Liu. Linear Model based Geometry Coding for Lidar Acquired Point Clouds [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5064

Spectral Video Compression Using Convolutional Sparse Coding

Paper Details

Authors:
Crisostomo Barajas-Solano, Juan-Pablo Ramirez, Henry Arguello
Submitted On:
26 March 2020 - 11:38am
Short Link:
Type:
Event:
Presenter's Name:
Session:

Document Files

DCCcbarajas2020v2.pdf

(50)

Subscribe

[1] Crisostomo Barajas-Solano, Juan-Pablo Ramirez, Henry Arguello, "Spectral Video Compression Using Convolutional Sparse Coding", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5034. Accessed: Sep. 23, 2020.
@article{5034-20,
url = {http://sigport.org/5034},
author = {Crisostomo Barajas-Solano; Juan-Pablo Ramirez; Henry Arguello },
publisher = {IEEE SigPort},
title = {Spectral Video Compression Using Convolutional Sparse Coding},
year = {2020} }
TY - EJOUR
T1 - Spectral Video Compression Using Convolutional Sparse Coding
AU - Crisostomo Barajas-Solano; Juan-Pablo Ramirez; Henry Arguello
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5034
ER -
Crisostomo Barajas-Solano, Juan-Pablo Ramirez, Henry Arguello. (2020). Spectral Video Compression Using Convolutional Sparse Coding. IEEE SigPort. http://sigport.org/5034
Crisostomo Barajas-Solano, Juan-Pablo Ramirez, Henry Arguello, 2020. Spectral Video Compression Using Convolutional Sparse Coding. Available at: http://sigport.org/5034.
Crisostomo Barajas-Solano, Juan-Pablo Ramirez, Henry Arguello. (2020). "Spectral Video Compression Using Convolutional Sparse Coding." Web.
1. Crisostomo Barajas-Solano, Juan-Pablo Ramirez, Henry Arguello. Spectral Video Compression Using Convolutional Sparse Coding [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5034

Luma Mapping with Chroma Scaling in Versatile Video Coding


This paper describes a new video coding tool in the Versatile Video Coding standard (VVC) named as luma mapping with chroma scaling (LMCS). Experimental compression performance results for LMCS and non-normative examples for deriving LMCS parameter values are also provided. LMCS has two main components: 1) a process for mapping input luma code values to a new set of code values for use inside the coding loop; and 2) a luma-dependent process for scaling chroma residue values.

Paper Details

Authors:
Taoran Lu, Peng Yin, Sean McCarthy, Walt Husak, Tao Chen, Edouard Francois, Christophe Chevance, Franck Hiron, Jie Chen, Ru-Ling Liao, Yan Ye, Jiancong Luo
Submitted On:
23 March 2020 - 11:59pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Session:
Document Year:
Cite

Document Files

DCC2020_ID189_LMCS_present.pdf

(159)

Subscribe

[1] Taoran Lu, Peng Yin, Sean McCarthy, Walt Husak, Tao Chen, Edouard Francois, Christophe Chevance, Franck Hiron, Jie Chen, Ru-Ling Liao, Yan Ye, Jiancong Luo, "Luma Mapping with Chroma Scaling in Versatile Video Coding", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5026. Accessed: Sep. 23, 2020.
@article{5026-20,
url = {http://sigport.org/5026},
author = {Taoran Lu; Peng Yin; Sean McCarthy; Walt Husak; Tao Chen; Edouard Francois; Christophe Chevance; Franck Hiron; Jie Chen; Ru-Ling Liao; Yan Ye; Jiancong Luo },
publisher = {IEEE SigPort},
title = {Luma Mapping with Chroma Scaling in Versatile Video Coding},
year = {2020} }
TY - EJOUR
T1 - Luma Mapping with Chroma Scaling in Versatile Video Coding
AU - Taoran Lu; Peng Yin; Sean McCarthy; Walt Husak; Tao Chen; Edouard Francois; Christophe Chevance; Franck Hiron; Jie Chen; Ru-Ling Liao; Yan Ye; Jiancong Luo
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5026
ER -
Taoran Lu, Peng Yin, Sean McCarthy, Walt Husak, Tao Chen, Edouard Francois, Christophe Chevance, Franck Hiron, Jie Chen, Ru-Ling Liao, Yan Ye, Jiancong Luo. (2020). Luma Mapping with Chroma Scaling in Versatile Video Coding. IEEE SigPort. http://sigport.org/5026
Taoran Lu, Peng Yin, Sean McCarthy, Walt Husak, Tao Chen, Edouard Francois, Christophe Chevance, Franck Hiron, Jie Chen, Ru-Ling Liao, Yan Ye, Jiancong Luo, 2020. Luma Mapping with Chroma Scaling in Versatile Video Coding. Available at: http://sigport.org/5026.
Taoran Lu, Peng Yin, Sean McCarthy, Walt Husak, Tao Chen, Edouard Francois, Christophe Chevance, Franck Hiron, Jie Chen, Ru-Ling Liao, Yan Ye, Jiancong Luo. (2020). "Luma Mapping with Chroma Scaling in Versatile Video Coding." Web.
1. Taoran Lu, Peng Yin, Sean McCarthy, Walt Husak, Tao Chen, Edouard Francois, Christophe Chevance, Franck Hiron, Jie Chen, Ru-Ling Liao, Yan Ye, Jiancong Luo. Luma Mapping with Chroma Scaling in Versatile Video Coding [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5026

Segmentation of Text-Lines and Words from JPEG Compressed Printed Text Documents Using DCT Coefficients


Segmenting a document image into text-lines and words finds applications in many research areas of DIA(Document Image Analysis) such as OCR, Word Spotting, and document retrieval. However, carrying out segmentation operation directly in the compressed document images is still an unexplored and challenging research area. Since JPEG is most widely accepted compression algorithm, this research paper attempts to segment a JPEG compressed printed text document image into text-lines and words, without fully decompressing the image.

Paper Details

Authors:
Mohammed Javed, P Nagabhushan, Watanabe Osamu
Submitted On:
7 April 2020 - 5:04am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Session:
Document Year:
Cite

Document Files

DCC2020 Paper ID 181

(77)

Subscribe

[1] Mohammed Javed, P Nagabhushan, Watanabe Osamu, "Segmentation of Text-Lines and Words from JPEG Compressed Printed Text Documents Using DCT Coefficients", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5001. Accessed: Sep. 23, 2020.
@article{5001-20,
url = {http://sigport.org/5001},
author = {Mohammed Javed; P Nagabhushan; Watanabe Osamu },
publisher = {IEEE SigPort},
title = {Segmentation of Text-Lines and Words from JPEG Compressed Printed Text Documents Using DCT Coefficients},
year = {2020} }
TY - EJOUR
T1 - Segmentation of Text-Lines and Words from JPEG Compressed Printed Text Documents Using DCT Coefficients
AU - Mohammed Javed; P Nagabhushan; Watanabe Osamu
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5001
ER -
Mohammed Javed, P Nagabhushan, Watanabe Osamu. (2020). Segmentation of Text-Lines and Words from JPEG Compressed Printed Text Documents Using DCT Coefficients. IEEE SigPort. http://sigport.org/5001
Mohammed Javed, P Nagabhushan, Watanabe Osamu, 2020. Segmentation of Text-Lines and Words from JPEG Compressed Printed Text Documents Using DCT Coefficients. Available at: http://sigport.org/5001.
Mohammed Javed, P Nagabhushan, Watanabe Osamu. (2020). "Segmentation of Text-Lines and Words from JPEG Compressed Printed Text Documents Using DCT Coefficients." Web.
1. Mohammed Javed, P Nagabhushan, Watanabe Osamu. Segmentation of Text-Lines and Words from JPEG Compressed Printed Text Documents Using DCT Coefficients [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5001

Pages