S. Zheng, A. Arnab, B. Romera-Paredes. Holistic Image Understanding with Deep Learning and Dense Random Fields, European Conference on Computer Vision (ECCV), Amsterdam, Netherlands, 2016. (Guest tutorial)
B.A. Plummer, M. H. Kiapour, S. Zheng, R. Piramuthu. Give me a hint! Navigating Image Databases using Human-in-the-loop Feedback. WACV 2019. (accepted, arXiv:1809.08714)
S. Zheng, F. Yang, K. Kaipour, R. Piramuthu. ModaNet: A Large-Scale Street Fashion Dataset with Polygon Annotations. ACM Multimedia, Seoul, South Korea, 2018.(Full Paper, Oral Presentation) [data][leaderboard][Slides PDF 48.44MB]
- A. Arnab*, S. Zheng*, S. Jayasumana, B. Romera-Paredes, M. Larsson, A. Kirillov, B. Savchynskyy, C. Rother, F. Kahl, and P. H. S. Torr. Conditional Random Fields meet Deep Neural Networks for Semantic Segmentation: combing probabilistic graphical models with deep learning for structured prediction. IEEE Signal Processing Magazine Special Issue in Deep Learning for Visual Understanding White Paper. vol 3, issue 1, pp. 37-52, 2018. (* joint author)
M. Larsson, A. Arnab, F. Kahl, S. Zheng, and P. H. S. Torr. Learning Arbitrary Potentials in CRFs with Gradient Descent. International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), 2017.
- H. Wu, S. Zheng, J. Zhang, and K. Huang. GP-GAN: Towards Realistic High-Resolution Image Blending. technical report, 2017. ( arXiv:1703.07195)
S. Zheng. Holistic image understanding with deep learning and dense random fields. DPhil thesis, University of Oxford, 2016.
A. Arnab, S. Jayasumana, S. Zheng, P. H. S. Torr. Higher Order Conditional Random Fields in Deep Neural Networks. European Conference on Computer Vision (ECCV), Amsterdam, Netherlands, 2016. (Technical report appears on arXiv:1511.08119. 2015)
J.Thewlis, S. Zheng, P. H. S. Torr, A. Vedaldi. Fully-trainable deep matching. British Machine Vision Conference (BMVC), York, United Kingdom, 2016. (oral)
- A. Kirillov, D. Schlesinger, S. Zheng, Efficient Likelihood Learning of a Generic CNN-CRF Model for Semantic Segmentation. Asian Conference on Computer Vision (ACCV), 2016. (Technical report appears on https://arxiv.org/abs/1511.05067) , P. H. S. Torr, C. Rother.
- S. Zheng*, S. Jayasumana*, B. Romera-Paredes, V. Vineet, Z. Su, D. Du, C. Huang, P. H. S. Torr. Conditional Random Fields as Recurrent Neural Networks. International Conference on Computer Vision (IEEE ICCV), Santiago, Chile, 2015.[project][live_demo][code][bib] (* shared equal contribution)
- M. Cheng, V. Prisacariu, S. Zheng, P. Torr, C Rother. “DenseCut: Densely Connected CRFs for Realtime GrabCut” , Computer Graphics Forum (CGF), special issue of Pacific Graphics, Beijing, China, 2015. (oral & journal) [Project][pdf][bib][code]
- S. Zheng, V. Prisacariu, M Averkiou, M. Cheng, N. Mitra, J. Shotton, P. Torr, C. Rother. “Object Proposal Estimation in Depth Images using Compact 3D Shape Manifolds”, German Conference on Pattern Recognition (GCPR), Aachen, Germany, 2015. (oral)[pdf][bib]
- S. Zheng, M. Cheng, J. Warrell, P. Sturgess, V. Vineet, C Rother, P. H. S. Torr. “Dense Semantic Image Segmentation with Objects and Attributes” , IEEE International Conference on Computer Vision and Pattern Recognition (IEEE CVPR), Columbus, Ohio, U.S.A., 2014. [pdf][bib][Project][code]
- M.M. Cheng*, S. Zheng*, W. Lin, V. Vineet, P. Sturgess, N. Crook, N. Mitra, and P. H. S. Torr. “ImageSpirit: Verbal Guided Image Parsing” , ACM Transactions on Graphics (ACM TOG), Los Angeles, California, U.S.A., 2014. [pdf][bib][code] (* shared equal contribution)
- S. Zheng, P. Sturgess, and P. H. S. Torr, “Approximate Structured Output Learning for Constrained Local Models with Application to Real-time Facial Feature Detection and Tracking on Low-power Devices“, IEEE International Conference on Automatic Face and Gesture Recognition (IEEE FG), Shanghai, China, 2013.(spotlight) [pdf][bib]
- M. Cheng, J.Warrell, W. Lin, S. Zheng, V. Vineet, and N. Crook, “Efficient Salient Region Detection with Soft Image Abstraction,” in International Conference on Computer Vision (IEEE ICCV), Sydney, Australia, 2013. [pdf][exe][bib]
- W. Lin, M. Cheng, S. Zheng, J. Lu, and N. Crook. “Robust Non-parametric Data Fitting for Correspondence Modeling“, in International Conference on Computer Vision (IEEE ICCV),Sydney, Australia, 2013. [pdf][bib][[MATLABCode]
- S. Zheng, K. Huang, T. Tan and D. Tao, ” A Cascade Fusion Scheme for Gait and Cumulative Foot Pressure Image Recognition“,45 (10), Pattern Recognition, pp.3603-3610, 2012.[CASIAGaitPartD][bib]
- S. Zheng, J. Zhang, K. Huang, R. He, and T. Tan, “Robust View Transformation Model for Gait Recognition,” in International Conference on Image Processing, Brussels, Belgium, 2011.[GEI_CASIAGaitPartB][code_rar][pwd4code][bib]
- S. Zheng, K. Huang, and T. Tan., “Evaluation framework on translation-invariant representation for cumulative foot pressure image,” in International Conference on Image Processing, Brussels, Belgium, 2011.[dataset][bib]
- S. Zheng, B. Xie, D. Tao, and K. Huang, “Multi-View Pedestrian Recognition using Shared Dictionary Learning with Group Sparsity,” in International Conference on Neural Information Processing, Shanghai, China, 2011.(oral) [slides][dataset][code][bib]
- J. Zhang, Y. Yu, S. Zheng, and K. Huang, “An Empirical Study of Visual Features for Part-Based Model,” in Asian Conference on Pattern Recognition, Beijing, China, 2011. (poster) [bib] -How we win PASCAL VOC Challenge with improved Part Based Model?
- Y. Huang, S. Zheng, W. Ren, Y. Yu, J. Zhang, K. Huang, and T. Tan, “SVM classifier and saliency coding for Image classification,” in PASCAL Visual Object Challenge Workshop, European Conference on Computer Vision (ECCVW), Crete, Greece, 2010.
- Y. Yu, J. Zhang, Y. Huang, S. Zheng, W. Ren, K. Huang, and T. Tan, “Object Detection by Context and Boosted HOG-LBP“, in PASCAL Visual Object Challenge Workshop, European Conference on Computer Vision (ECCVW), Crete, Greece, 2010. [bib][code]
Notes: IEEE TPAMI is the #1 IEEE publication. ACM TOG is the most-cited ACM Transaction. IEEE TPAMI, ACM TOG, and IEEE TVCG are CCF Tier-A Journals. SIGGRAPH, CVPR, and ICCV are CCF Tier-A Conferences and they have CiteSeer impact factor ranking top 0.7%, top 5%, and top 5% of all computer science journals and conferences respectively.
- S. Zheng, et.al, “Camera Platform and Object Inventory Control”, IP-P3342PRV.
- S. Zheng, et.al., “Intelligent online personal assistant with image text localization”, IP-P3301WO1.
To achieve great things, two things are needed; a plan, and not quite enough time. -Leonard Bernstein