I am currently a researcher at Qualcomm AI Research, working on neural image and video compression. At Qualcomm, we have built the world first neural video decoder running on mobile devices.
hoangle at hoangle.net
Experience and Education
Researcher at Qualcomm AI Research, 2020 - present
PhD in Computer Science, 2020
Portland State University
MS in Computer Science, 2012
Washington State University
BSc in Computer Science, 2012
Portland State University
Selected Publications
Pourreza, R., Le, H., Said, A., Sautiere, G., & Wiggers, A. (2023). Boosting neural video codecs by exploiting hierarchical redundancy. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 5355–5364.
Le, H., Pourreza, R., Said, A., Sautiere, G., & Wiggers, A. (2022). GameCodec: Neural Cloud Gaming Video Codec. 33rd British Machine Vision Conference 2022, BMVC 2022, London, UK, November 21-24, 2022. https://bmvc2022.mpi-inf.mpg.de/0204.pdf
Said, A., Pourreza, R., & Le, H. (2022). Optimized Learned Entropy Coding Parameters for Practical Neural-Based Image and Video Compression. 2022 IEEE International Conference on Image Processing (ICIP), 661–665.
Le, H., Zhang, L., Said, A., Sautiere, G., Yang, Y., Shrestha, P., Yin, F., Pourreza, R., & Wiggers, A. (2022). MobileCodec: neural inter-frame video compression on mobile devices. Proceedings of the 13th ACM Multimedia Systems Conference, 324–330.
Le, H., Liu, F., Zhang, S., & Agarwala, A. (2020). Deep homography estimation for dynamic scenes. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 7652–7661.
Le, H., & Liu, F. (2019). Appearance flow completion for novel view synthesis. Computer Graphics Forum: Journal of the European Association for Computer Graphics, 38(7), 555–565.
Le, H., Mai, L., Price, B., Cohen, S., Jin, H., & Liu, F. (2018). Interactive boundary prediction for object selection. In Computer Vision – ECCV 2018 (pp. 20–36). Springer International Publishing.
Le, H., Doan, T., Marshall, C. S., Panneer, S., & Liu, F. (2017). Detecting Good Surface for Improvisatory Visual Projection. 2017 IEEE International Symposium on Multimedia (ISM), 114–121.
H. Le, C. Marshall, T. Doan, L. Mai and F. Liu, "Visual Quality Assessment for Projected Content," 2017 14th Conference on Computer and Robot Vision (CRV), Edmonton, AB, Canada, 2017, pp. 225-231, doi: 10.1109/CRV.2017.47.
Mai, L., Le, H., & Liu, F. (2017). Content and Surface Aware Projection. Graphics Interface, 24–32.
Le, H., Dang, T., & Liu, F. (2013). Eye Blink Detection for Smart Glasses. 2013 IEEE International Symposium on Multimedia, 305–308.
Le, H., Dang, T., & Liu, F. (2013). Towards long-term large-scale visual health monitoring using Cyber Glasses. 2013 7th International Conference on Pervasive Computing Technologies for Healthcare and Workshops, 200–207.
Mai, L., Le, H., Niu, Y., Lai, Y.-C., & Liu, F. (2012). Detecting rule of simplicity from photos. Proceedings of the 20th ACM International Conference on Multimedia, 1149–1152.
Mai, L., Le, H., Niu, Y., & Liu, F. (2011). Rule of Thirds Detection from Photograph. 2011 IEEE International Symposium on Multimedia, 91–96.