Yang Bin's Computer Vision Research | Generated by AI
Yang Bin (Bin Yang)
Yang Bin is a prominent researcher in computer vision, deep learning, and autonomous driving. He is a PhD candidate at the University of Toronto (advised by Raquel Urtasun) and has held roles at Uber ATG, Waabi, and MiniMax. His work focuses on advancing machine intelligence for physical world interactions, particularly 3D object detection, motion forecasting, and sensor fusion in self-driving systems. He has received awards like the Microsoft Research PhD Fellowship (2021) and NVIDIA Pioneer Award (2018). His Google Scholar profile shows over 14,000 citations and an h-index of around 30 (based on listed publications).
Here is a selection of his key academic publications (full list exceeds 30; prioritized by impact and relevance to his expertise):
| Title | Co-Authors | Year | Venue | Citations (approx.) |
|---|---|---|---|---|
| Learning to Reweight Examples for Robust Deep Learning | Mengye Ren, Wenyuan Zeng, Raquel Urtasun | 2018 | ICML (Oral) | 1,921 |
| PIXOR: Real-time 3D Object Detection From Point Clouds | Wenjie Luo, Raquel Urtasun | 2018 | CVPR | 1,564 |
| Deep Continuous Fusion for Multi-Sensor 3D Object Detection | Ming Liang, Shenlong Wang, Raquel Urtasun | 2018 | ECCV | 1,217 |
| Multi-Task Multi-Sensor Fusion for 3D Object Detection | Ming Liang, Yun Chen, Rui Hu, Raquel Urtasun | 2019 | CVPR | 909 |
| Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net | Wenjie Luo, Raquel Urtasun | 2018 | CVPR (Oral) | 872 |
| Learning Lane Graph Representations for Motion Forecasting | Ming Liang, Rui Hu, Yun Chen, Renjie Liao, Song Feng, Raquel Urtasun | 2020 | ECCV (Oral) | 852 |
| T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos | Kai Kang, Hongsheng Li, Junjie Yan, Xingyu Zeng, Tong Xiao, Cong Zhang, Zhe Wang, Ruohui Wang, Xiaogang Wang, Wanli Ouyang | 2018 | IEEE TCSVT | 705 |
| V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction | Tsun-Hsuan Wang, Siva Manivasagam, Ming Liang, Wenyuan Zeng, Raquel Urtasun | 2020 | ECCV (Oral) | 607 |
| End-to-End Interpretable Neural Motion Planner | Wenyuan Zeng, Wenjie Luo, Simon Suo, Abbas Sadat, Sergio Casas, Raquel Urtasun | 2019 | CVPR (Oral) | 563 |
| Aggregate Channel Features for Multi-view Face Detection | Junjie Yan, Zhen Lei, Stan Z. Li | 2014 | IJCB (Oral, Best Student Paper) | 442 |
For his complete publication list, see his University of Toronto page or Google Scholar profile.
Zhou Yucong (Yucong Zhou)
Zhou Yucong is a researcher specializing in deep learning optimization, activation functions, and computer vision. He previously worked as a Senior Researcher at SenseTime (2018–2019) and is now at Huawei Technologies. His contributions at SenseTime focused on video object detection and neural network efficiency. He has around 5 notable publications, with modest citation impact (total ~32 citations across works).
Here is a list of his known academic publications:
| Title | Co-Authors | Year | Venue | Citations (approx.) |
|---|---|---|---|---|
| PWLU: Learning Specialized Activation Functions With the Piecewise Linear Unit | (Not specified in sources) | 2023 | IEEE TPAMI | 12 |
| LR²VQ: Low-Rank Representation Vector Quantization | (Not specified in sources) | 2022 | (Conference/Journal not specified) | N/A |
| PWLU: Learning Specialized Activation Functions With the Piecewise Linear Unit (early version) | (Not specified in sources) | 2021 | arXiv/Preprint | N/A |
| FixNorm: Weight Decay Without the Learning Rate | (Not specified in sources) | 2021 | arXiv/Preprint | N/A |
| Fully Motion-Aware Network for Video Object Detection | Shiyao Wang, Junjie Yan, Zhidong Deng | 2018 | ECCV | ~200 (paper total; Zhou’s contribution not isolated) |
For more details, see his ResearchGate profile or Semantic Scholar profile. Note: Zhou’s publication record appears more industry-focused, with fewer public academic outputs compared to Yang.