The Flame's Daughter
2018
Search results
H. Jerry Qi. Professor. Location: MRDC Building, Room 4104. Email: qih@me.gatech.edu. Telephone: 404-385-2457. Research Area: Mechanics of Materials. Active Materials and Additive Manufacturing Lab. Education. Sc.D., Massachusetts Institute of Technology, 2003. Ph.D.,Tsinghua University, China, 1999. B.S., Tsinghua University, China, 1994.
Scene-centric joint parsing of cross-view videos. H Qi, Y Xu, T Yuan, T Wu, SC Zhu. Proceedings of the AAAI Conference on Artificial Intelligence 32 (1) , 2018. 22. 2018. A restricted visual turing test for deep scene and event understanding. H Qi, T Wu, MW Lee, SC Zhu. arXiv preprint arXiv:1512.01715.
Hang Qi. Software Engineer @ Google. © 2020 Hang Qi. Built with Jekylland Bootstrap. I am a Research Engineer at Google DeepMind. I received my PhD in Computer Sciencefrom UCLAin 2018, advised by Professor Song-Chun Zhu. Projects. Paleo: A Performance Model for Deep Neural Networks. Joint work with Evan R. Sparks and Ameet Talwalkar.
Institute for Materials. Parker H. Petit Institute for Bioengineering and Bioscience. Renewable Bioproducts Institute. Dr. H. Jerry Qi is a professor and the Woodruff Faculty Fellow in the George W. Woodruff School of Mechanical Engineering at Georgia Institute of Technology.
About. Dr. H. Jerry Qi is a professor and the Woodruff Faculty Fellow in the George W. Woodruff School of Mechanical Engineering at Georgia Institute of Technology. He received hisundergradaute...
- 27
- 55
- Georgia Institute of Technology
- Marietta, Georgia, United States
Actor: Perfect and Casual. Hang Qi was born on 17 June 1984 in Shandong, China. He is an actor, known for Perfect and Casual (2020), The Confidence (2020) and Winner (2015).
Dec 19, 2017 · Hang Qi and colleagues propose a novel method to improve ConvNet classifiers' low-shot learning performance by directly setting the final layer weights from novel training examples. The method is called weight imprinting and it uses a single imprinted weight vector for each novel category, instead of nearest-neighbor distances.
