Fumin Shen
Fumin Shen

homepage
fumin.shenatgmail.com

  Affiliation history
Bibliometrics: publication history
Average citations per article2.49
Citation Count122
Publication count49
Publication years2012-2018
Available for download20
Average downloads per article210.85
Downloads (cumulative)4,217
Downloads (12 Months)2,342
Downloads (6 Weeks)315
Professional ACM Member
SEARCH
ROLE
Arrow RightAuthor only


AUTHOR'S COLLEAGUES
See all colleagues of this author

SUBJECT AREAS
See all subject areas




BOOKMARK & SHARE


48 results found Export Results: bibtexendnoteacmrefcsv

Result 1 – 20 of 48
Result page: 1 2 3

Sort by:

1
March 2018 Pattern Recognition: Volume 75 Issue C, March 2018
Publisher: Elsevier Science Inc.
Bibliometrics:
Citation Count: 0

We propose a novel supervised hashing scheme to generate high-quality hash codes and hash functions for facilitating large-scale multimedia applications.We devise an effective binary code modeling approach based on l2,p-norm, which can adaptively induce sample-wise sparsity, to perform automatic code selection as well as noisy samples identification.We preserve the discrete ...
Keywords: Discrete optimization., Robust modeling, Supervised hashing

2 published by ACM
November 2017 CIKM '17: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management
Publisher: ACM
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 17,   Downloads (12 Months): 53,   Downloads (Overall): 53

Full text available: PDFPDF
Recently, a new type of video understanding task called Movie-Fill-in-the-Blank (MovieFIB) has attracted many research attentions. Given a pair of movie clip and description with one blank word as input, MovieFIB aims to automatically predict the blank word. Because of the advantage in processing sequence data, Long-Short Term Memory (LSTM) ...
Keywords: description update, adaptive temporal attention, question answering

3 published by ACM
October 2017 MM '17: Proceedings of the 2017 ACM on Multimedia Conference
Publisher: ACM
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 14,   Downloads (12 Months): 76,   Downloads (Overall): 76

Full text available: PDFPDF
Recently, deep neural networks based hashing methods have greatly improved the multimedia retrieval performance by simultaneously learning feature representations and binary hash functions. Inspired by the latest advance in the asymmetric hashing scheme, in this work, we propose a novel Deep Asymmetric Pairwise Hashing approach (DAPH) for supervised hashing. The ...
Keywords: binary code, deep hashing, asymmetric hashing

4 published by ACM
October 2017 MM '17: Proceedings of the 2017 ACM on Multimedia Conference
Publisher: ACM
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 18,   Downloads (12 Months): 47,   Downloads (Overall): 47

Full text available: PDFPDF
Anomaly detection and localization in surveillance videos have attracted broad attention in both academic and industry for its importance to public safety, which however remain challenging. In this demonstration, we propose an anomaly detection algorithm called 2stream-VAE/GAN by embedding VAE/GAN in a two-stream architecture. By taking both spatial and temporal ...
Keywords: two-stream, anomaly detection, outlier detection

5 published by ACM
October 2017 MM '17: Proceedings of the 2017 ACM on Multimedia Conference
Publisher: ACM
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 7,   Downloads (12 Months): 38,   Downloads (Overall): 38

Full text available: PDFPDF
Subspace representations have been widely applied for videos in many tasks. In particular, the subspace-based query-by-image video retrieval (QBIVR), facing high challenges on similarity-preserving measurements and efficient retrieval schemes, urgently needs considerable research attention. In this paper, we propose a novel subspace-based QBIVR framework to enable efficient video search. We ...
Keywords: asymmetric hashing, query-by-image, geometry-preserving distance metric, video retrieval

6
August 2017 Neurocomputing: Volume 253 Issue C, August 2017
Publisher: Elsevier Science Publishers B. V.
Bibliometrics:
Citation Count: 0

Hashing techniques show significant advantage in dealing with enormous high-dimensional image and multimedia data. Specifically, learning based hashing methods attract a lot of attention from researchers thanks to its great performance in image retrieval. But discrete constraint problem of learning based hashing methods makes the optimization extremely difficult, which can ...
Keywords: Multimedia retrieval, Adaptive discrete optimization, Hashing

7 published by ACM
August 2017 SIGIR '17: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval
Publisher: ACM
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 17,   Downloads (12 Months): 105,   Downloads (Overall): 105

Full text available: PDFPDF
Travel route planning aims to mine user's attributes and recommend personalized routes. How to build interest model for users and understand their real intention brings great challenges. This paper presents an approach which mines the user interest model by multi-source social media (e.g., travelogues and check-in records), and understands the ...
Keywords: social media, route planning, topical package, user interest

8 published by ACM
August 2017 SIGIR '17: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval
Publisher: ACM
Bibliometrics:
Citation Count: 2
Downloads (6 Weeks): 59,   Downloads (12 Months): 315,   Downloads (Overall): 315

Full text available: PDFPDF
This paper proposes a generic formulation that significantly expedites the training and deployment of image classification models, particularly under the scenarios of many image categories and high feature dimensions. As the core idea, our method represents both the images and learned classifiers using binary hash codes, which are simultaneously learned ...
Keywords: hashing, classification, binary codes

9 published by ACM
August 2017 SIGIR '17: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval
Publisher: ACM
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 30,   Downloads (12 Months): 133,   Downloads (Overall): 133

Full text available: PDFPDF
Social media has become one of the most credible sources for delivering messages, breaking news, as well as events. Predicting the future dynamics of an event at a very early stage is significantly valuable, e.g, helping company anticipate marketing trends before the event becomes mature. However, this prediction is non-trivial ...
Keywords: social events, volume dynamics, early prediction, content information

10 published by ACM
June 2017 ICMR '17: Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval
Publisher: ACM
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 35,   Downloads (12 Months): 152,   Downloads (Overall): 152

Full text available: PDFPDF
Zero-shot learning (ZSL) aims to bridge the knowledge transfer via available semantic representations (e.g., attributes) between labeled source instances of seen classes and unlabelled target instances of unseen classes. Most existing ZSL approaches achieve this by learning a projection from the visual feature space to the semantic representation space based ...
Keywords: matrix factorization, zero-shot learning, manifold learning, transductive learning

11
June 2017 Pattern Recognition: Volume 66 Issue C, June 2017
Publisher: Elsevier Science Inc.
Bibliometrics:
Citation Count: 0

For robust face recognition tasks, we particularly focus on the ubiquitous scenarios where both training and testing images are corrupted due to occlusions. Previous low-rank based methods stacked each error image into a vector and then used L1 or L2 norm to measure the error matrix. However, in the stacking ...
Keywords: Face recognition, Low-rank matrix recovery, Nuclear norm

12 published by ACM
May 2017 ACM Transactions on Information Systems (TOIS): Volume 35 Issue 3, June 2017
Publisher: ACM
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 13,   Downloads (12 Months): 113,   Downloads (Overall): 113

Full text available: PDFPDF
Many real applications in real-time news stream advertising call for efficient processing of long queries against short text. In such applications, dynamic news feeds are regarded as queries to match against an advertisement (ad) database for retrieving the k most relevant ads. The existing approaches to keyword retrieval cannot work ...
Keywords: Long queries, top-k retrieval, inverted index, rank-aware partitioning, short text

13
May 2017 IEEE Transactions on Image Processing: Volume 26 Issue 5, May 2017
Publisher: IEEE Press
Bibliometrics:
Citation Count: 1

Hashing based methods have attracted considerable attention for efficient cross-modal retrieval on large-scale multimedia data. The core problem of cross-modal hashing is how to learn compact binary codes that construct the underlying correlations between heterogeneous features from different modalities. A majority of recent approaches aim at learning hash functions to ...

14
April 2017 Multimedia Tools and Applications: Volume 76 Issue 8, April 2017
Publisher: Kluwer Academic Publishers
Bibliometrics:
Citation Count: 0


15
April 2017 Multimedia Tools and Applications: Volume 76 Issue 8, April 2017
Publisher: Kluwer Academic Publishers
Bibliometrics:
Citation Count: 0

In our present society, Alzheimer's disease (AD) is the most common dementia form in elderly people and has been a big social health problem worldwide. In this paper, we propose a novel multi-view classification method based on l2,p -norm regularization for Alzheimer's Disease (AD) diagnosis. Unlike the previous l2,1 -norm ...
Keywords: l2,p-norm, Alzheimer's Disease (AD), Multi-view classification, l2,l-norm, Social health

16
March 2017 Neurocomputing: Volume 229 Issue C, March 2017
Publisher: Elsevier Science Publishers B. V.
Bibliometrics:
Citation Count: 0

In recent years, learning based hashing becomes an attractive technique in large-scale image retrieval due to its low storage and computation cost. Hashing methods map each high-dimensional vector onto a low-dimensional hamming space by projection operators. However, when processing high dimensional data retrieval, many existing methods including hashing cost a ...
Keywords: Image retrieval, Learning based hashing, Medical, Sparsity

17
March 2017 Pattern Recognition: Volume 63 Issue C, March 2017
Publisher: Elsevier Science Inc.
Bibliometrics:
Citation Count: 0

Morphological retrieval is an effective approach to explore large-scale neuronal databases, as the morphology is correlated with neuronal types, regions, functions, etc. In this paper, we focus on the neuron identification and analysis via morphological retrieval. In our proposed framework, multiple features are extracted to represent 3D neuron data. Because ...
Keywords: Neuron morphology, Large-scale retrieval, Binary coding

18
January 2017 IEEE Transactions on Image Processing: Volume 26 Issue 1, January 2017
Publisher: IEEE Press
Bibliometrics:
Citation Count: 1

With the dramatic development of the Internet, how to exploit large-scale retrieval techniques for multimodal web data has become one of the most popular but challenging problems in computer vision and multimedia. Recently, hashing methods are used for fast nearest neighbor search in large-scale data spaces, by embedding high-dimensional feature ...

19
December 2016 Neurocomputing: Volume 217 Issue C, December 2016
Publisher: Elsevier Science Publishers B. V.
Bibliometrics:
Citation Count: 1

In recent years, multimedia event detection has been attracting extensive research attention because of the exponential increase in volume of web video data. Traditional approaches usually utilize single visual representation, which may suffer from the problem of insufficient descriptive power. How to jointly employ multiple types of visual representation to ...
Keywords: Co-training, Multimedia event detection, Convolutional neural network

20
December 2016 IEEE Transactions on Image Processing: Volume 25 Issue 12, December 2016
Publisher: IEEE Press
Bibliometrics:
Citation Count: 6

Hashing or binary code learning has been recognized to accomplish efficient near neighbor search, and has thus attracted broad interests in recent retrieval, vision, and learning studies. One main challenge of learning to hash arises from the involvement of discrete variables in binary code optimization. While the widely used continuous ...



The ACM Digital Library is published by the Association for Computing Machinery. Copyright © 2018 ACM, Inc.
Terms of Usage   Privacy Policy   Code of Ethics   Contact Us