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

Image/Video Storage, Retrieval

REGION MATCHING AND SIMILARITY ENHANCING FOR IMAGE RETRIEVAL


Many image retrieval systems adopt the bag-of-words model and rely on matching of local descriptors. However, these descriptors of keypoints, such as SIFT, may lead to false matches, since they do not consider the contextual information of the keypoints. In this paper, we incorporate the cues of meaningful regions where local descriptors are extracted. We describe a matching region estimation (MRE) method to find appropriate matching regions for local descriptor matching pairs.

Paper Details

Authors:
Guixuan Zhang, Zhi Zeng, Shuwu Zhang, Hu Guan, Qinzhen Guo
Submitted On:
16 March 2016 - 2:31am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP16_poster.pdf

(413)

Subscribe

[1] Guixuan Zhang, Zhi Zeng, Shuwu Zhang, Hu Guan, Qinzhen Guo, "REGION MATCHING AND SIMILARITY ENHANCING FOR IMAGE RETRIEVAL", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/704. Accessed: Feb. 18, 2020.
@article{704-16,
url = {http://sigport.org/704},
author = {Guixuan Zhang; Zhi Zeng; Shuwu Zhang; Hu Guan; Qinzhen Guo },
publisher = {IEEE SigPort},
title = {REGION MATCHING AND SIMILARITY ENHANCING FOR IMAGE RETRIEVAL},
year = {2016} }
TY - EJOUR
T1 - REGION MATCHING AND SIMILARITY ENHANCING FOR IMAGE RETRIEVAL
AU - Guixuan Zhang; Zhi Zeng; Shuwu Zhang; Hu Guan; Qinzhen Guo
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/704
ER -
Guixuan Zhang, Zhi Zeng, Shuwu Zhang, Hu Guan, Qinzhen Guo. (2016). REGION MATCHING AND SIMILARITY ENHANCING FOR IMAGE RETRIEVAL. IEEE SigPort. http://sigport.org/704
Guixuan Zhang, Zhi Zeng, Shuwu Zhang, Hu Guan, Qinzhen Guo, 2016. REGION MATCHING AND SIMILARITY ENHANCING FOR IMAGE RETRIEVAL. Available at: http://sigport.org/704.
Guixuan Zhang, Zhi Zeng, Shuwu Zhang, Hu Guan, Qinzhen Guo. (2016). "REGION MATCHING AND SIMILARITY ENHANCING FOR IMAGE RETRIEVAL." Web.
1. Guixuan Zhang, Zhi Zeng, Shuwu Zhang, Hu Guan, Qinzhen Guo. REGION MATCHING AND SIMILARITY ENHANCING FOR IMAGE RETRIEVAL [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/704

Joint Instance and Feature Importance Re-weighting for Person Reidentification


Person re-identification refers to the task of recognizing the same person under different non-overlapping camera views and across different time and places.

Person reidentification refers to the task of recognizing the same person
under different non-overlapping camera views. Presently, person
reidentification based on metric learning is proved to be effective among
various techniques, which exploits the labeled data to learn
a subspace that maximizes the inter-person divergence while minimizes
the intra-person divergence. However, these methods fail to
take the different impacts of various instances and local features into
account. To address this issue, we propose to learn a projection matrix

Paper Details

Authors:
Qin Zhou, Shibao Zheng, Hua Yang, Yu Wang and Hang Su
Submitted On:
13 March 2016 - 8:54am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

icassp_zq.pdf

(396)

Subscribe

[1] Qin Zhou, Shibao Zheng, Hua Yang, Yu Wang and Hang Su, "Joint Instance and Feature Importance Re-weighting for Person Reidentification", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/651. Accessed: Feb. 18, 2020.
@article{651-16,
url = {http://sigport.org/651},
author = {Qin Zhou; Shibao Zheng; Hua Yang; Yu Wang and Hang Su },
publisher = {IEEE SigPort},
title = {Joint Instance and Feature Importance Re-weighting for Person Reidentification},
year = {2016} }
TY - EJOUR
T1 - Joint Instance and Feature Importance Re-weighting for Person Reidentification
AU - Qin Zhou; Shibao Zheng; Hua Yang; Yu Wang and Hang Su
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/651
ER -
Qin Zhou, Shibao Zheng, Hua Yang, Yu Wang and Hang Su. (2016). Joint Instance and Feature Importance Re-weighting for Person Reidentification. IEEE SigPort. http://sigport.org/651
Qin Zhou, Shibao Zheng, Hua Yang, Yu Wang and Hang Su, 2016. Joint Instance and Feature Importance Re-weighting for Person Reidentification. Available at: http://sigport.org/651.
Qin Zhou, Shibao Zheng, Hua Yang, Yu Wang and Hang Su. (2016). "Joint Instance and Feature Importance Re-weighting for Person Reidentification." Web.
1. Qin Zhou, Shibao Zheng, Hua Yang, Yu Wang and Hang Su. Joint Instance and Feature Importance Re-weighting for Person Reidentification [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/651

IMAGE SENTIMENT ANALYSIS USING LATENT CORRELATIONS AMONG VISUAL, TEXTUAL, AND SENTIMENT VIEWS


Multi-View Embedding for Image Sentiment Analysis

As Internet users increasingly post images to express their daily sentiment and emotions, the analysis of sentiments in user-generated images is of increasing importance for developing several applications. Most conventional methods of image sentiment analysis focus on the design of visual features, and the use of text associated to the images has not been sufficiently investigated. This paper proposes a novel approach that exploits latent correlations among multiple views: visual and textual views, and a sentiment view constructed using SentiWordNet.

Paper Details

Authors:
Marie Katsurai,Shin'ichi Satoh
Submitted On:
11 March 2016 - 9:18pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

icassp2016_katsurai.pdf

(631)

Subscribe

[1] Marie Katsurai,Shin'ichi Satoh, "IMAGE SENTIMENT ANALYSIS USING LATENT CORRELATIONS AMONG VISUAL, TEXTUAL, AND SENTIMENT VIEWS", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/619. Accessed: Feb. 18, 2020.
@article{619-16,
url = {http://sigport.org/619},
author = {Marie Katsurai;Shin'ichi Satoh },
publisher = {IEEE SigPort},
title = {IMAGE SENTIMENT ANALYSIS USING LATENT CORRELATIONS AMONG VISUAL, TEXTUAL, AND SENTIMENT VIEWS},
year = {2016} }
TY - EJOUR
T1 - IMAGE SENTIMENT ANALYSIS USING LATENT CORRELATIONS AMONG VISUAL, TEXTUAL, AND SENTIMENT VIEWS
AU - Marie Katsurai;Shin'ichi Satoh
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/619
ER -
Marie Katsurai,Shin'ichi Satoh. (2016). IMAGE SENTIMENT ANALYSIS USING LATENT CORRELATIONS AMONG VISUAL, TEXTUAL, AND SENTIMENT VIEWS. IEEE SigPort. http://sigport.org/619
Marie Katsurai,Shin'ichi Satoh, 2016. IMAGE SENTIMENT ANALYSIS USING LATENT CORRELATIONS AMONG VISUAL, TEXTUAL, AND SENTIMENT VIEWS. Available at: http://sigport.org/619.
Marie Katsurai,Shin'ichi Satoh. (2016). "IMAGE SENTIMENT ANALYSIS USING LATENT CORRELATIONS AMONG VISUAL, TEXTUAL, AND SENTIMENT VIEWS." Web.
1. Marie Katsurai,Shin'ichi Satoh. IMAGE SENTIMENT ANALYSIS USING LATENT CORRELATIONS AMONG VISUAL, TEXTUAL, AND SENTIMENT VIEWS [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/619

CRH: A Simple Benchmark Approach to Continuous Hashing

Paper Details

Authors:
Submitted On:
23 February 2016 - 1:43pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

gsip_mc.pdf

(638)

gsip_mc.pdf

(474)

Subscribe

[1] , "CRH: A Simple Benchmark Approach to Continuous Hashing", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/248. Accessed: Feb. 18, 2020.
@article{248-15,
url = {http://sigport.org/248},
author = { },
publisher = {IEEE SigPort},
title = {CRH: A Simple Benchmark Approach to Continuous Hashing},
year = {2015} }
TY - EJOUR
T1 - CRH: A Simple Benchmark Approach to Continuous Hashing
AU -
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/248
ER -
. (2015). CRH: A Simple Benchmark Approach to Continuous Hashing. IEEE SigPort. http://sigport.org/248
, 2015. CRH: A Simple Benchmark Approach to Continuous Hashing. Available at: http://sigport.org/248.
. (2015). "CRH: A Simple Benchmark Approach to Continuous Hashing." Web.
1. . CRH: A Simple Benchmark Approach to Continuous Hashing [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/248

Pages