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

Image/Video Processing

Deep Learning-based Image Compression with Trellis Coded Quantization

Paper Details

Authors:
Mohammad Akbari, Jie Liang, Yang Wang
Submitted On:
20 March 2020 - 2:28pm
Short Link:
Type:
Event:
Presenter's Name:
Session:
Document Year:
Cite

Document Files

DCC2020_present_v2.pdf

(15)

Subscribe

[1] Mohammad Akbari, Jie Liang, Yang Wang, "Deep Learning-based Image Compression with Trellis Coded Quantization", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5010. Accessed: Apr. 04, 2020.
@article{5010-20,
url = {http://sigport.org/5010},
author = {Mohammad Akbari; Jie Liang; Yang Wang },
publisher = {IEEE SigPort},
title = {Deep Learning-based Image Compression with Trellis Coded Quantization},
year = {2020} }
TY - EJOUR
T1 - Deep Learning-based Image Compression with Trellis Coded Quantization
AU - Mohammad Akbari; Jie Liang; Yang Wang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5010
ER -
Mohammad Akbari, Jie Liang, Yang Wang. (2020). Deep Learning-based Image Compression with Trellis Coded Quantization. IEEE SigPort. http://sigport.org/5010
Mohammad Akbari, Jie Liang, Yang Wang, 2020. Deep Learning-based Image Compression with Trellis Coded Quantization. Available at: http://sigport.org/5010.
Mohammad Akbari, Jie Liang, Yang Wang. (2020). "Deep Learning-based Image Compression with Trellis Coded Quantization." Web.
1. Mohammad Akbari, Jie Liang, Yang Wang. Deep Learning-based Image Compression with Trellis Coded Quantization [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5010

Wide and Deep Learning for Video Summarization via Attention Mechanism and Independently Recurrent Neural Network


Video summarization considers the problem of selecting a concise set of frames or shots to preserve the most essential contents of the original video. Most of the current approaches apply Recurrent Neural Network (RNN) to learn the interdependencies among the video frames without considering the distinct information of particular frames. Other methods leverage the attention mechanism to explore the characteristics of some certain frames, while ignoring the systematic knowledge across the video sequence.

Paper Details

Authors:
Lu Lu
Submitted On:
20 March 2020 - 12:12am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Session:
Document Year:
Cite

Document Files

Poster

(12)

Subscribe

[1] Lu Lu, "Wide and Deep Learning for Video Summarization via Attention Mechanism and Independently Recurrent Neural Network", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5007. Accessed: Apr. 04, 2020.
@article{5007-20,
url = {http://sigport.org/5007},
author = { Lu Lu },
publisher = {IEEE SigPort},
title = {Wide and Deep Learning for Video Summarization via Attention Mechanism and Independently Recurrent Neural Network},
year = {2020} }
TY - EJOUR
T1 - Wide and Deep Learning for Video Summarization via Attention Mechanism and Independently Recurrent Neural Network
AU - Lu Lu
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5007
ER -
Lu Lu. (2020). Wide and Deep Learning for Video Summarization via Attention Mechanism and Independently Recurrent Neural Network. IEEE SigPort. http://sigport.org/5007
Lu Lu, 2020. Wide and Deep Learning for Video Summarization via Attention Mechanism and Independently Recurrent Neural Network. Available at: http://sigport.org/5007.
Lu Lu. (2020). "Wide and Deep Learning for Video Summarization via Attention Mechanism and Independently Recurrent Neural Network." Web.
1. Lu Lu. Wide and Deep Learning for Video Summarization via Attention Mechanism and Independently Recurrent Neural Network [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5007

LEVERAGING ORDINAL REGRESSION WITH SOFT LABELS FOR 3D HEAD POSE ESTIMATION FROM POINT SETS


Head pose estimation from depth image is a challenging problem, considering its large pose variations, severer occlusions, and low quality of depth data. In contrast to existing approaches that take 2D depth image as input, we propose a novel deep regression architecture called Head PointNet, which consumes 3D point sets derived from a depth image describing the visible surface of a head. To cope with the non-stationary property of pose variation process, the network is facilitated with an ordinal regression module that incorporates metric penalties into ground truth label representation.

Paper Details

Authors:
Shihua Xiao, Nan Sang, Xupeng Wang, Xiangtian Ma
Submitted On:
12 February 2020 - 4:44am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

presentation_paperID5344.pptx

(27)

Subscribe

[1] Shihua Xiao, Nan Sang, Xupeng Wang, Xiangtian Ma, "LEVERAGING ORDINAL REGRESSION WITH SOFT LABELS FOR 3D HEAD POSE ESTIMATION FROM POINT SETS", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4981. Accessed: Apr. 04, 2020.
@article{4981-20,
url = {http://sigport.org/4981},
author = {Shihua Xiao; Nan Sang; Xupeng Wang; Xiangtian Ma },
publisher = {IEEE SigPort},
title = {LEVERAGING ORDINAL REGRESSION WITH SOFT LABELS FOR 3D HEAD POSE ESTIMATION FROM POINT SETS},
year = {2020} }
TY - EJOUR
T1 - LEVERAGING ORDINAL REGRESSION WITH SOFT LABELS FOR 3D HEAD POSE ESTIMATION FROM POINT SETS
AU - Shihua Xiao; Nan Sang; Xupeng Wang; Xiangtian Ma
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4981
ER -
Shihua Xiao, Nan Sang, Xupeng Wang, Xiangtian Ma. (2020). LEVERAGING ORDINAL REGRESSION WITH SOFT LABELS FOR 3D HEAD POSE ESTIMATION FROM POINT SETS. IEEE SigPort. http://sigport.org/4981
Shihua Xiao, Nan Sang, Xupeng Wang, Xiangtian Ma, 2020. LEVERAGING ORDINAL REGRESSION WITH SOFT LABELS FOR 3D HEAD POSE ESTIMATION FROM POINT SETS. Available at: http://sigport.org/4981.
Shihua Xiao, Nan Sang, Xupeng Wang, Xiangtian Ma. (2020). "LEVERAGING ORDINAL REGRESSION WITH SOFT LABELS FOR 3D HEAD POSE ESTIMATION FROM POINT SETS." Web.
1. Shihua Xiao, Nan Sang, Xupeng Wang, Xiangtian Ma. LEVERAGING ORDINAL REGRESSION WITH SOFT LABELS FOR 3D HEAD POSE ESTIMATION FROM POINT SETS [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4981

Scene Text Aware Image Retargeting


Extensive use of text labels and symbols available in the digital media for interpretation and communication of information has gained a lot of attention in the era of digital media. Access of the images with scene text in it through different display devices tend to deform the scene text region while resizing for better viewing experience. We propose an image retargeting operator, which is aware of the scene text present in the image. We perform the normal seam carving depending on the content of the image for the non-text region.

Paper Details

Authors:
Diptiben Patel, Shanmuganathan Raman
Submitted On:
14 November 2019 - 8:02am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster_Scene_Text_aware_Image_Retargeting.pdf

(98)

Subscribe

[1] Diptiben Patel, Shanmuganathan Raman, "Scene Text Aware Image Retargeting", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4957. Accessed: Apr. 04, 2020.
@article{4957-19,
url = {http://sigport.org/4957},
author = {Diptiben Patel; Shanmuganathan Raman },
publisher = {IEEE SigPort},
title = {Scene Text Aware Image Retargeting},
year = {2019} }
TY - EJOUR
T1 - Scene Text Aware Image Retargeting
AU - Diptiben Patel; Shanmuganathan Raman
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4957
ER -
Diptiben Patel, Shanmuganathan Raman. (2019). Scene Text Aware Image Retargeting. IEEE SigPort. http://sigport.org/4957
Diptiben Patel, Shanmuganathan Raman, 2019. Scene Text Aware Image Retargeting. Available at: http://sigport.org/4957.
Diptiben Patel, Shanmuganathan Raman. (2019). "Scene Text Aware Image Retargeting." Web.
1. Diptiben Patel, Shanmuganathan Raman. Scene Text Aware Image Retargeting [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4957

Super-Resolution for Imagery Enhancement Using Variational Quantum Eigensolver


Super-Resolution (SR) is a technique that has been exhaustively exploited and incorporates strategic aspects to image processing. As quantum computers gradually evolve and provide unconditional proof of computational advantage at solving intractable problems over their classical counterparts, quantum computing emerges with the compelling prospect to offer exponential speedup to process computationally expensive operations, such as the ones verified in SR imaging.

Paper Details

Authors:
Submitted On:
14 November 2019 - 4:13pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

GlobalSIP Presentation (Ystallonne Alves).pdf

(85)

Subscribe

[1] , "Super-Resolution for Imagery Enhancement Using Variational Quantum Eigensolver", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4956. Accessed: Apr. 04, 2020.
@article{4956-19,
url = {http://sigport.org/4956},
author = { },
publisher = {IEEE SigPort},
title = {Super-Resolution for Imagery Enhancement Using Variational Quantum Eigensolver},
year = {2019} }
TY - EJOUR
T1 - Super-Resolution for Imagery Enhancement Using Variational Quantum Eigensolver
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4956
ER -
. (2019). Super-Resolution for Imagery Enhancement Using Variational Quantum Eigensolver. IEEE SigPort. http://sigport.org/4956
, 2019. Super-Resolution for Imagery Enhancement Using Variational Quantum Eigensolver. Available at: http://sigport.org/4956.
. (2019). "Super-Resolution for Imagery Enhancement Using Variational Quantum Eigensolver." Web.
1. . Super-Resolution for Imagery Enhancement Using Variational Quantum Eigensolver [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4956

Using Multimodal Data for Automated Fidelity Evaluation in Pivotal Response Treatment Videos


Research has shown that caregivers implementing
pivotal response treatment (PRT) with their child with autism
spectrum disorder (ASD) helps the child develop social and
communication skills. Evaluation of caregiver fidelity to PRT in
training programs and research studies relies on the evaluation
of video probes depicting the caregiver interacting with his
or her child. These video probes are reviewed by behavior
analysts and are dependent on manual processing to extract
data metrics. Using multimodal data processing techniques and

Paper Details

Authors:
Corey Heath, Hemanth Venkateswara, Troy McDaniel, Sethuraman Panchanathan
Submitted On:
11 November 2019 - 8:34pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

GlobalSIP_Presentation.pptx

(40)

Subscribe

[1] Corey Heath, Hemanth Venkateswara, Troy McDaniel, Sethuraman Panchanathan, "Using Multimodal Data for Automated Fidelity Evaluation in Pivotal Response Treatment Videos", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4946. Accessed: Apr. 04, 2020.
@article{4946-19,
url = {http://sigport.org/4946},
author = {Corey Heath; Hemanth Venkateswara; Troy McDaniel; Sethuraman Panchanathan },
publisher = {IEEE SigPort},
title = {Using Multimodal Data for Automated Fidelity Evaluation in Pivotal Response Treatment Videos},
year = {2019} }
TY - EJOUR
T1 - Using Multimodal Data for Automated Fidelity Evaluation in Pivotal Response Treatment Videos
AU - Corey Heath; Hemanth Venkateswara; Troy McDaniel; Sethuraman Panchanathan
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4946
ER -
Corey Heath, Hemanth Venkateswara, Troy McDaniel, Sethuraman Panchanathan. (2019). Using Multimodal Data for Automated Fidelity Evaluation in Pivotal Response Treatment Videos. IEEE SigPort. http://sigport.org/4946
Corey Heath, Hemanth Venkateswara, Troy McDaniel, Sethuraman Panchanathan, 2019. Using Multimodal Data for Automated Fidelity Evaluation in Pivotal Response Treatment Videos. Available at: http://sigport.org/4946.
Corey Heath, Hemanth Venkateswara, Troy McDaniel, Sethuraman Panchanathan. (2019). "Using Multimodal Data for Automated Fidelity Evaluation in Pivotal Response Treatment Videos." Web.
1. Corey Heath, Hemanth Venkateswara, Troy McDaniel, Sethuraman Panchanathan. Using Multimodal Data for Automated Fidelity Evaluation in Pivotal Response Treatment Videos [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4946

FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network


High dynamic range (HDR) image generation from a single exposure low dynamic range (LDR) image has been made possible due to the recent advances in Deep Learning. Various feed-forward Convolutional Neural Networks (CNNs) have been proposed for learning LDR to HDR representations. To better utilize the power of CNNs, we exploit the idea of feedback, where the initial low level features are guided by the high level features using a hidden state of a Recurrent Neural Network.

Paper Details

Authors:
Zeeshan Khan, Mukul Khanna, Shanmuganathan Raman
Submitted On:
10 November 2019 - 4:07am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

FHDR Presentation.pdf

(83)

Subscribe

[1] Zeeshan Khan, Mukul Khanna, Shanmuganathan Raman, "FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4943. Accessed: Apr. 04, 2020.
@article{4943-19,
url = {http://sigport.org/4943},
author = {Zeeshan Khan; Mukul Khanna; Shanmuganathan Raman },
publisher = {IEEE SigPort},
title = {FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network},
year = {2019} }
TY - EJOUR
T1 - FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network
AU - Zeeshan Khan; Mukul Khanna; Shanmuganathan Raman
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4943
ER -
Zeeshan Khan, Mukul Khanna, Shanmuganathan Raman. (2019). FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network. IEEE SigPort. http://sigport.org/4943
Zeeshan Khan, Mukul Khanna, Shanmuganathan Raman, 2019. FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network. Available at: http://sigport.org/4943.
Zeeshan Khan, Mukul Khanna, Shanmuganathan Raman. (2019). "FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network." Web.
1. Zeeshan Khan, Mukul Khanna, Shanmuganathan Raman. FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4943

Image Alpha Matting via Residual Convolutional Grid Network


Alpha matting is an important topic in areas of computer vision. It has various applications, such as virtual reality, digital image and video editing, and image synthesis. Conventional approaches for alpha matting do not perform well when they encounter complicated background or when foreground and background color distributions overlap. It is also difficult to extract alpha matte accurately when the foreground objects are semi-transparent or hairy.

Paper Details

Authors:
Yang Zhou, Lei Chen, Jiying Zhao
Submitted On:
8 November 2019 - 1:26pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Image Alpha Matting via Residual Convolutional Grid Network_Poster.pdf

(54)

Subscribe

[1] Yang Zhou, Lei Chen, Jiying Zhao, "Image Alpha Matting via Residual Convolutional Grid Network", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4933. Accessed: Apr. 04, 2020.
@article{4933-19,
url = {http://sigport.org/4933},
author = {Yang Zhou; Lei Chen; Jiying Zhao },
publisher = {IEEE SigPort},
title = {Image Alpha Matting via Residual Convolutional Grid Network},
year = {2019} }
TY - EJOUR
T1 - Image Alpha Matting via Residual Convolutional Grid Network
AU - Yang Zhou; Lei Chen; Jiying Zhao
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4933
ER -
Yang Zhou, Lei Chen, Jiying Zhao. (2019). Image Alpha Matting via Residual Convolutional Grid Network. IEEE SigPort. http://sigport.org/4933
Yang Zhou, Lei Chen, Jiying Zhao, 2019. Image Alpha Matting via Residual Convolutional Grid Network. Available at: http://sigport.org/4933.
Yang Zhou, Lei Chen, Jiying Zhao. (2019). "Image Alpha Matting via Residual Convolutional Grid Network." Web.
1. Yang Zhou, Lei Chen, Jiying Zhao. Image Alpha Matting via Residual Convolutional Grid Network [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4933

Compressive Super-Pixel LiDAR for High-Framerate 3D Depth Imaging


We propose a new sampling and reconstruction framework for full frame depth imaging using synchronised, programmable laser diode and photon detector arrays. By adopting a measurement scheme that probes the environment with sparse, pseudo-random patterns, our method enables eyesafe LiDAR operation, while guaranteeing fast reconstruction of

Paper Details

Authors:
Brian Stewart, Joao F.C. Mota, Andrew M. Wallace
Submitted On:
8 November 2019 - 6:40am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

SuperPixel LiDAR GlobalSIP19 print.pdf

(85)

Subscribe

[1] Brian Stewart, Joao F.C. Mota, Andrew M. Wallace, "Compressive Super-Pixel LiDAR for High-Framerate 3D Depth Imaging", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4930. Accessed: Apr. 04, 2020.
@article{4930-19,
url = {http://sigport.org/4930},
author = {Brian Stewart; Joao F.C. Mota; Andrew M. Wallace },
publisher = {IEEE SigPort},
title = {Compressive Super-Pixel LiDAR for High-Framerate 3D Depth Imaging},
year = {2019} }
TY - EJOUR
T1 - Compressive Super-Pixel LiDAR for High-Framerate 3D Depth Imaging
AU - Brian Stewart; Joao F.C. Mota; Andrew M. Wallace
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4930
ER -
Brian Stewart, Joao F.C. Mota, Andrew M. Wallace. (2019). Compressive Super-Pixel LiDAR for High-Framerate 3D Depth Imaging. IEEE SigPort. http://sigport.org/4930
Brian Stewart, Joao F.C. Mota, Andrew M. Wallace, 2019. Compressive Super-Pixel LiDAR for High-Framerate 3D Depth Imaging. Available at: http://sigport.org/4930.
Brian Stewart, Joao F.C. Mota, Andrew M. Wallace. (2019). "Compressive Super-Pixel LiDAR for High-Framerate 3D Depth Imaging." Web.
1. Brian Stewart, Joao F.C. Mota, Andrew M. Wallace. Compressive Super-Pixel LiDAR for High-Framerate 3D Depth Imaging [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4930

A Novel Blurring based Method for Video Compression

Paper Details

Authors:
Submitted On:
4 November 2019 - 11:35pm
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

Video Compression Poster

(48)

Subscribe

[1] , "A Novel Blurring based Method for Video Compression ", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4912. Accessed: Apr. 04, 2020.
@article{4912-19,
url = {http://sigport.org/4912},
author = { },
publisher = {IEEE SigPort},
title = {A Novel Blurring based Method for Video Compression },
year = {2019} }
TY - EJOUR
T1 - A Novel Blurring based Method for Video Compression
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4912
ER -
. (2019). A Novel Blurring based Method for Video Compression . IEEE SigPort. http://sigport.org/4912
, 2019. A Novel Blurring based Method for Video Compression . Available at: http://sigport.org/4912.
. (2019). "A Novel Blurring based Method for Video Compression ." Web.
1. . A Novel Blurring based Method for Video Compression [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4912

Pages