Talk given on 2020-06-15.
2:48 - Geometry-Aware Instance Segmentation with Disparity Maps by Cho-Ying Wu, USC
10:58 - Human-Centric Efficiency Improvements in Image Annotation for Autonomous Driving by Frédéric Ratle, Samasource
16:36 - FISHING Net: Future Inference of Semantic Heatmaps In Grids by Noureldin Hendy, Zoox
22:56 - BEV-Seg: Bird's Eye View Semantic Segmentation Using Geometry and Semantic Point Cloud, Mong Him Ng, UC Berkeley
28:48 - Efficient Black-box Assessment of Autonomous Vehicle Safety by Matthew O'Kelly, Trustworthy AI
35:51 - MOPT: Multi-Object Panoptic Tracking
40:45 - Keep it Simple: Image Statistics Matching for Domain Adaptation
41:47 - ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation
42:51 - Vehicle Re-ID for surround-view camera system
46:49 - AFDet: Anchor Free One Stage 3D Object Detection
47:50 - Single-Shot 3D Detection of Vehicles from Monocular RGB Images via Geometrically Constrained Keypoints in Real-Time
49:03 - Advisable Learning for Self-driving Vehicles by Internalizing Observation-to-Action Rules
Learning Depth-Guided Convolutions for Monocular 3D Object Detection
50:07 - Cityscapes 3D: Dataset and Benchmark for 9 DoF Vehicle Detection
53:14 - Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning
