M
Ming Liang
Researcher at Uber
Publications - 44
Citations - 5525
Ming Liang is an academic researcher from Uber . The author has contributed to research in topics: Object detection & Convolutional neural network. The author has an hindex of 18, co-authored 44 publications receiving 3535 citations. Previous affiliations of Ming Liang include Tsinghua University.
Papers
More filters
Proceedings ArticleDOI
Recurrent convolutional neural network for object recognition
Ming Liang,Xiaolin Hu +1 more
TL;DR: With fewer trainable parameters, RCNN outperforms the state-of-the-art models on all of these datasets and demonstrates the advantage of the recurrent structure over purely feed-forward structure for object recognition.
Book ChapterDOI
Deep Continuous Fusion for Multi-Sensor 3D Object Detection
TL;DR: This paper proposes a novel 3D object detector that can exploit both LIDAR as well as cameras to perform very accurate localization and designs an end-to-end learnable architecture that exploits continuous convolutions to fuse image and LIDar feature maps at different levels of resolution.
Proceedings ArticleDOI
Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser
TL;DR: High-level representation guided denoiser (HGD) is proposed as a defense for image classification by using a loss function defined as the difference between the target model's outputs activated by the clean image and denoised image.
Proceedings ArticleDOI
Multi-Task Multi-Sensor Fusion for 3D Object Detection
TL;DR: An end-to-end learnable architecture that reasons about 2D and 3D object detection as well as ground estimation and depth completion is presented that leads the KITTI benchmark on 2D, 3D and bird's eye view object detection, while being real-time.
Journal ArticleDOI
Evaluate the Malignancy of Pulmonary Nodules Using the 3-D Deep Leaky Noisy-OR Network
TL;DR: A 3-D deep neural network for automatic diagnosing lung cancer from computed tomography scans that selects the top five nodules based on the detection confidence, evaluates their cancer probabilities, and combines them with a leaky noisy-OR gate to obtain the probability of lung cancer for the subject.