Saliency, Recognition, Cosegmentation

In addition to estimating the geometric and dynamic properties of scenes imaged, we are also interested in discovering the semantic aspects for holistic scene understanding. We have worked on a few related problems such as fine-grained image categorization, saliency estimation, multiple foreground recognition and cosegmentation.

K. R. Jerripothula, J. Cai, J. Lu, and J. Yuan, “Object Co-skeletonization with Co-segmentation,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, Jul. 2017. [pdf]
Y. Zhang, L. Cheng, J. Wu, J. Cai, M. N. Do, and J. Lu, “Action Recognition in Still Images with Minimum Annotation Efforts,” IEEE Trans. on Image Processing (TIP), vol. 25, no. 11, pp. 5479-5490, Nov. 2016. [pdf]
Y. Zhang, X.-S. Wei, J. Wu, J. Cai, J. Lu, V. Nguyen, and M. N. Do, “Weakly Supervised Fine-Grained Categorization with Part-Based Image Representation,” IEEE Trans. on Image Processing (TIP), vol. 25, no. 4, pp. 1713-1725, Apr. 2016. [pdf]

H. Zhu, J. Lu, J. Cai, J. Zheng, S. Lu and N. Thalmann, “Multiple Human Identification and Cosegmentation: A Human-Oriented CRF Approach with Poselets,” IEEE Trans. on Multimedia (TMM), vol. 18, no. 8, pp. 1516-1530, Aug. 2016. [pdf][web]
H. Zhu, J. Lu, J. Cai, J. Zheng, and N. Thalmann, “Multiple Foreground Recognition and Cosegmentation: An Object-Oriented CRF Model with Robust Higher-Order Potentials,” IEEE Winter conference on Applications of Computer Vision (WACV), 2014. [pdf]

K. Wang, L. Lin, J. Lu, C. Li, and K. Shi, “PISA: Pixelwise Image Saliency by Aggregating Complimentary Appearance Contrast Measures with Edge-Preserving Coherence,” IEEE Trans. on Image Processing (TIP), vol. 24, no. 10, pp. 3019-3033, Oct. 2015. [pdf][web]
K. Shi, K. Wang, J. Lu, and L. Lin, “PISA: Pixelwise Image Saliency by Aggregating Complementary Appearance Contrast Measures with Spatial Priors,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Portland, Oregon, Jun. 2013. [pdf]