Xiao Lin

Position e-mail
PhD Candidate xiao.lin@upc.edu
Office Phone
D5-119 +34 934 011 066

Biography

Xiao received the degree in Software Engineering in 2010 and the M.Sc. in Research on Computer Vision in 2013, both from the South West Unviersity in China. He is currently doing his Ph.D. under the advisement of Josep Ramon Casas and Montse Pardas in the Image and Video Processing Group at UPC. He holds a scholarship from China Scholarship Council (CSC). His main research field is focused on 3D segmentation and human-object interaction analysis based on depth sensor.

Journal Articles top

2018
X. Lin, Casas, J., and Pardàs, M., Temporally Coherent 3D Point Cloud Video Segmentation in Generic Scenes, IEEE Transactions on Image Processing, vol. 27, no. 6, pp. 3087 - 3099, 2018. (24.37 MB)
2017
P. A. Martínez, Lin, X., Castelán, M., Casas, J., and Arechavaleta, G., A closed-loop approach for tracking a humanoid robot using particle filtering and depth data, Intelligent Service Robotics, vol. 10, no. 4, pp. 297–312, 2017. (88.92 KB)

Conference Papers top

In Press
D. Sanchez-Escobedo, Lin, X., Casas, J., and Pardàs, M., HybridNet for Depth Estimation and Semantic Segmentation, in ICASSP 2018, Calgary, Alberta, Canada, In Press.
2017
X. Lin, Casas, J., and Pardàs, M., 3D Point Cloud Segmentation Using a Fully Connected Conditional Random Field, in The 25th European Signal Processing Conference (EUSIPCO 2017), Kos island, Greece, 2017. (2.34 MB)
2016
X. Lin, Casas, J., and Pardàs, M., Graph based Dynamic Segmentation of Generic Objects in 3D, in CVPR SUNw: Scene Understanding Workshop, Las Vegas, US, 2016. (956.15 KB)
X. Lin, Casas, J., and Pardàs, M., 3D Point Cloud Segmentation Oriented to The Analysis of Interactions, in The 24th European Signal Processing Conference (EUSIPCO 2016), Budapest, Hungary, 2016. (10.54 MB)
X. Lin, Casas, J., and Pardàs, M., 3D Point Cloud Video Segmentation Based on Interaction Analysis, in ECCV 2016: Computer Vision – ECCV 2016 Workshops, Amsterdam, 2016, vol. III, 9915 vol., pp. 821 - 835. (10 MB)