C
Cheng Li
Researcher at University of Illinois at Urbana–Champaign
Publications - 69
Citations - 7327
Cheng Li is an academic researcher from University of Illinois at Urbana–Champaign. The author has contributed to research in topics: Deep learning & Benchmarking. The author has an hindex of 23, co-authored 61 publications receiving 5346 citations. Previous affiliations of Cheng Li include SenseTime & Tsinghua University.
Papers
More filters
Proceedings ArticleDOI
Residual Attention Network for Image Classification
Fei Wang,Mengqing Jiang,Chen Qian,Shuo Yang,Cheng Li,Honggang Zhang,Xiaogang Wang,Xiaoou Tang +7 more
TL;DR: Residual Attention Network as mentioned in this paper is a convolutional neural network using attention mechanism which can incorporate with state-of-the-art feed forward network architecture in an end-to-end training fashion.
Posted Content
Residual Attention Network for Image Classification
Fei Wang,Mengqing Jiang,Chen Qian,Shuo Yang,Cheng Li,Honggang Zhang,Xiaogang Wang,Xiaoou Tang +7 more
TL;DR: Residual Attention Network as discussed by the authors is a convolutional neural network using attention mechanism which can incorporate with state-of-the-art feed forward network architecture in an end-to-end training fashion.
Proceedings ArticleDOI
Face alignment by coarse-to-fine shape searching
TL;DR: A novel face alignment framework based on coarse-to-fine shape searching that prevents the final solution from being trapped in local optima due to poor initialisation, and improves the robustness in coping with large pose variations.
Proceedings ArticleDOI
Pixel-Level Hand Detection in Ego-centric Videos
Cheng Li,Kris M. Kitani +1 more
TL;DR: This work presents a fully labeled indoor/outdoor ego-centric hand detection benchmark dataset containing over 200 million labeled pixels, which contains hand images taken under various illumination conditions and highlights the effectiveness of sparse features and the importance of modeling global illumination.
Proceedings ArticleDOI
Sirius: An Open End-to-End Voice and Vision Personal Assistant and Its Implications for Future Warehouse Scale Computers
Johann Hauswald,Michael A. Laurenzano,Yunqi Zhang,Cheng Li,Austin Rovinski,Arjun Khurana,Ronald G. Dreslinski,Trevor Mudge,Vinicius Petrucci,Lingjia Tang,Jason Mars +10 more
TL;DR: The design of Sirius is presented, an open end-to-end IPA web-service application that accepts queries in the form of voice and images, and responds with natural language, and finds that accelerators are critical for the future scalability of IPA services.