His research interests include multimedia analysis and machine learning. Specifically, he focuses on research of image and video content understanding and its applications.
concept detectors, features and detection scores on
We are pleased to release 81 semantic concept detectors
trained on the NUS-WIDE training dataset, and their
detection scores on NUS-WIDE testing dataset. Global and
local features (BoW) are also available.
Deep Multimodal Learning for Affective Analysis and Retrieval
L. Pang, S. A. Zhu and C. W. Ngo, IEEE Trans. on Multimedia, accepted, 2015.
On the Learning of Image Social Relevance from Heterogeneous Social Network S. A. Zhu, S. Aloufi, J. Yang and A. El Saddik, Neurocomputing, accepted, 2015.
Collaborative Error Reduction for Hierarchical Classification S. A. Zhu, X. Y. Wei and C. W. Ngo, Computer Vision and Image Understanding, 2014.
Sampling and Ontologically Pooling Web Images for Visual Concept Learning S. A. Zhu, C. W. Ngo and Y. G. Jiang, IEEE Trans. on Multimedia, vol. 14, no. 4, pp. 1068-1078, 2012.
Sentiment Analysis on Multi-view Social Data
T. Niu, S. A. Zhu, L. Pang and A. El Saddik, International Conference on Multimedia Modelling (MMM), Miami, USA, January, 2016.
Point-of-Interest Recommender Systems: A Separate-Space Perspective
H. Y. Li, R. C. Hong, S. A. Zhu and Y. Ge, IEEE International Conference on Data Mining (ICDM), Atlantic City, New Jersey, USA, November, 2015.
Utilizing Image Social Clues for Automated Image Tagging S. A. Zhu, S. Aloufi and A. El Saddik, IEEE International Conference on Multimedia and Expo (ICME), Torino, Italy, July 2015.
Boosting Prediction of Geo-location for Web Images Through Integrating Multiple Knowledge Sources
H. Kuang, S. A. Zhu and A. El Saddik, ACM International Conference on Multimedia Retrieval (ICMR), Shanghai, China, June 2015.
Error Recovered Hierarchical Classication S. A. Zhu, X. Y. Wei and C. W. Ngo, ACM Multimedia (ACM MM), Barcelona, Catalunya, Spain, October 2013.
Video Concept Detection by Learning from Web Images: A Case Study on Cross Domain Learning S. A. Zhu, T. Yao and C. W. Ngo, ICME Workshop on Media Fragment Creation and reMIXing (MMIX'13), San Jose, California, USA, July 2013.
VIREO/ECNU @ TRECVID 2013: A Video Dance of Detection, Recounting and Search with Motion Relativity and Concept Learning from Wild
C.-W. Ngo, F. Wang, W. Zhang, C.-C. Tan, Z. H. Sun, S. A. Zhu and T. Yao, NIST TRECVID Workshop (TRECVID'13), Gaithersburg, USA, 2013.
Predicting Domain Adaptivity: Redo or Recycle?
T. Yao, C. W. Ngo and S. A. Zhu, ACM Multimedia (ACM MM), Nara, Japan, October 2012.
VIREO@TRECVID 2012: Searching with Topology, Recounting will Small Concepts, Learning with Free Examples
W. Zhang, C. C. Tan, S. A. Zhu, T. Yao, L. Pang, C. W. Ngo, NIST TRECVID Workshop (TRECVID'12), Gaithersburg, USA, 2012.
On the Pooling of Positive Examples with Ontology for
Visual Concept Learning S. A. Zhu, C. W. Ngo and Y. G. Jiang, ACM Multimedia (ACM MM), Arizona, USA, November 2011.
VIREO @ TRECVID 2011: Instance Search, Semantic
Indexing, Multimedia Event Detection and Known-Item
C. W. Ngo, S. A. Zhu, W. Zhang, C. C. Tan, T. Yao, L. Pang
and H. K. Tan, NIST TRECVID Workshop (TRECVID'11),
Gaithersburg, USA, December 2011.
On the Sampling of Web Images for Learning Visual
Concept Classifiers S. A. Zhu, G. Wang, C. W. Ngo, Y. G. Jiang, International
Conference on Image and Video Retrieval (CIVR, merged with MIR under the ICMR), Xi'an,
China, July 2010. (Oral)
VIREO at TRECVID 2010: Semantic Indexing, Known-Item
Search, and Content-Based Copy Detection
C. W. Ngo, S. A. Zhu, H. K. Tan, W. L. Zhao, X. Y. Wei,
NIST TRECVID Workshop (TRECVID'10), Gaithersburg, USA, Nov.
VIREO/DVMM at TRECVID 2009: High-Level Feature
Extraction, Automatic Video Search, and Content-Based Copy
C. W. Ngo, Y. G. Jiang, X. Y. Wei, W. L. Zhao, Y. Liu, J.
Wang, S. A. Zhu and S. F. Chang, NIST TRECVID Workshop
(TRECVID'09), Gaithersburg, MD, USA, Nov. 16-17, 2009.