The page lists some source code/software/datasets from some of our research projects and papers. You are free to download them for your own research, provided that you cite the source paper explicitly in your work, do not make any redistribution and do not use them for commercial purposes.
This package is based on our following paper:
Y. Ding and B. Li, "VSEC-LDA: Boosting Topic Modeling with Embedded Vocabulary Selection", full manuscript available here https://arxiv.org/abs/2001.05578
This package is based on our following paper:
Y. Li, T. Yu, and B. Li, "Recognizing Video Events with Varying Rhythms", full manuscript available here https://arxiv.org/abs/2001.05060
(Note: In the current implementation, we used ResNet50 of the Keras library instead of AlexNet as reported in the paper. This is due to unavailability of AlexNet model in Keras. Consequently, we are able to achieve slightly better accuracy than reported in the paper.)
This package is based on our following publication:
V. Gattupalli, Y. Zhuo, B. Li, "Weakly Supervised Deep Image Hashing using Tag Embedding", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 10375-10384.
This package is based on our following publication:
Kan Chang, Xueyu Zhang, Pak Lun Kevin Ding, Baoxin Li, "Data-adaptive low-rank modeling and external gradient prior for single image super-resolution", Signal Processing 161: 36-49 (2019).
This package is based on our following publication:
Chang K, Ding P L K, Li B. "Single Image Super Resolution Using Joint Regularization", IEEE Signal Processing Letters, 2018, 25(4): 596-600.
This package is based on our following publication:
Chang K, Ding P L K, Li B. "Single image super-resolution using collaborative representation and non-local self-similarity", Signal Processing, 2018, 149:49-61.
This package is based on our following publication:
Kan Chang, Pak Lun Kevin Ding, and Baoxin Li, "Compressive Sensing Reconstruction of Correlated Images Using Joint Regularization", IEEE Signal Processing Letters (SPL), vol.23, no.4, pp.449-453, Apr. 2016.
This package is based on our following publication:
K. Chang and B. Li, "Joint modeling and reconstruction of a compressively-sensed set of correlated images", Journal of Visual Communication and Image Representation, Vol. 33, pp. 286-300. November, 2015.
This package is based on our following publication:
K. Chang, P.L.K. Ding and B. Li, "Joint modeling and recon
This package is based on our following publication:
L. Chen, Q. Zhang, and B. Li, "Predicting Multiple Attributes via Relative Multi-task Learning", IEEE International Conference on Computer Vision & Pattern Recognition (CVPR), June, 2014.
This package is based on our following publications: (The code corresponds to the journal paper, which is an improved version of the CVPR paper).
Q. Zhang and B. Li, "Relative Hidden Markov Models for Video-based Evaluation of Motion Skills in Surgical Training", IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2014.
andQiang Zhang & Baoxin Li, "Relative Hidden Markov Model for Skill Evaluation", IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June, 2013.
This package is based on our following publication:
Q. Zhang and B. Li, "Mining Discriminative Components with Low-Rank and Sparsity Constraints for Face Recognition", ACM Conf. on Knowledge Discover & Data Mining (SIG KDD) 2012.
This package is based on our following publication:
Naveen Kulkarni and Baoxin Li, "Discriminative Affine Sparse Codes for Image Classification", IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June, 2011.
This package is based on our following publication:
Qiang Zhang and Baoxin Li, "Discriminative K-SVD for Dictionary Learning in Face Recognition", IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June, 2010.
This package is based on our following publication:
Pradeep Nagesh and Baoxin Li, "A Compressive Sensing Approach for Expression-Invariant Face Recognition", IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June, 2009.
This dataset accompanies our following publication:
H. B. Maguluri, Q. Tian, B. Li, "Detecting Text in Floor Maps Using Histogram of Oriented Gradients", International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2013.
This dataset accompanies our following publication:
Zheshen Wang, Baoxin Li, "A Two-stage Approach to Saliency Detection", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2008.