Junyang Shen
University of Southern California
25 Papers
188 Citations
Junyang Shen is an academic researcher from University of Southern California. The author has contributed to research in topics: Cognitive radio & Computer science. The author has an hindex of 12, co-authored 22 publications. Previous affiliations of Junyang Shen include Beijing University of Posts and Telecommunications.
Chat about Author
Papers
Accurate Passive Location Estimation Using TOA Measurements
TL;DR: This paper considers the case where one transmitter and multiple, distributed, receivers are used to estimate the location of a passive (reflecting) object and proposes a novel, Two-Step estimation (TSE) algorithm for the localization of the object.
352
DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection
Yingwei Li,Adams Wei Yu,Tianjian Meng,Benjamin Caine,Jiquan Ngiam,Daiyi Peng,Junyang Shen,Bo-Xun Wu,Yifeng Lu,Denny Zhou,Quoc V. Le,Alan L. Yuille,Mingxing Tan +12 more
- 15 Mar 2022
TL;DR: This paper proposes two novel techniques: InverseAug that inverses geometric-related augmentations, e.g., rotation, to enable accurate geometric alignment between lidar points and image pixels, and LearnableAlign that leverages cross-attention to dynamically capture the correlations between image and lidar features during fusion.
Maximum channel throughput via cooperative spectrum sensing in cognitive radio networks
TL;DR: It is proved that the optimization problem in the second scenario can be converted into a convex-optimization problem, which can be solved efficiently and reliably.
141
Optimisation of cooperative spectrum sensing in cognitive radio network
TL;DR: The authors consider cooperative spectrum sensing (CSS) using a counting rule where several cognitive users sense whether primary users exist or not and send their decisions to the centre where the final decision is made.
74
Robust energy detection in cognitive radio
TL;DR: A novel two-stage Bayesian estimation-based energy detection algorithm is introduced here, showing a superior performance of 1 dB compared with previous methods and the consistency of the algorithm has been proved indicating that 100 correct primary user signal detection can be approached as the number of samples tends to infinity.
66