Posters
Keep it Simple: Image Statistics Matching for Domain Adaptation
Alexey Abramov (Continental Teves AG & Co. oHG)*; Claudio Heller (Continental Teves AG & Co. ohG); Christopher Bayer (Continental Teves AG & Co. oHG)
Learning Depth-Guided Convolutions for Monocular 3D Object Detection
Mingyu Ding (The University of Hong Kong)*; Yuqi Huo (Renmin University of China); Hongwei Yi (Peking University); Zhe Wang (SenseTime Group Limited); Jianping Shi (Sensetime Group Limited); Zhiwu Lu (Renmin University of China); Ping Luo (The University of Hong Kong)
ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation
Antoine Saporta (Sorbonne University)*; Tuan-Hung VU (Valeo.ai); Matthieu Cord (Sorbonne University); Patrick Pérez (Valeo.ai)
Vehicle Re-ID for surround-view camera system
zizhang wu (zongmu tech.com)*; man wang (zongmu tech.com); lingxiao yin (zongmutech); Weiwei Sun (University of Victoria); jason wang (zongmutech); huangbin wu (Xiamen University)
AFDet: Anchor Free One Stage 3D Object Detection
Runzhou Ge (Horizon Robotics Inc.); Zhuangzhuang Ding (Horizon); Yihan Hu (Horizon Robotics); Yu Wang (Horizon Robotics)*; Sijia Chen (Horizon Robotics); Li Huang (Horizon Robotics Inc); Yuan Li (Horizon Ai)
Geometry-Aware Instance Segmentation with Disparity Maps
Cho-Ying Wu (University of Southern California)*; Xiaoyan Hu (Argo AI); Michael Happold (Argo AI, LLC); qiangeng xu (University of Southern California); Ulrich Neumann (USC)
Nils Gählert (Mercedes-Benz AG, R&D)*; Jun-Jun Wan (KIT); Nicolas Jourdan (TU Darmstadt); Jan Finkbeiner (Mercedes-Benz AG, R&D); Uwe Franke (Daimler R&D, Germany); Joachim Denzler (Computer Vision Group, Friedrich Schiller University Jena, Germany)
Cityscapes 3D: Dataset and Benchmark for 9 DoF Vehicle Detection
Nils Gählert (Mercedes-Benz AG, R&D)*; Nicolas Jourdan (TU Darmstadt); Marius Cordts (Daimler); Uwe Franke (Daimler R&D, Germany); Joachim Denzler (Computer Vision Group, Friedrich Schiller University Jena, Germany)
Efficient Black-box Assessment of Autonomous Vehicle Safety
Aman Sinha (Trustworthy AI); Matthew E OKelly (Trustworthy AI); Justin Norden (Trustworthy AI)
Advisable Learning for Self-driving Vehicles by Internalizing Observation-to-Action Rules
Jinkyu Kim (UC Berkeley)*; Suhong Moon (UC Berkeley); Anna Rohrbach (UC Berkeley); Trevor Darrell (UC Berkeley); John F Canny (UC Berkeley)
MOPT: Multi-Object Panoptic Tracking
Juana Valeria Hurtado (UNIVERSTY OF FREIBURG)*; Rohit Mohan (UNIVERSTY OF FREIBURG); Wolfram Burgard (University of Freiburg); Abhinav Valada (Uni Freiburg)
Human-Centric Efficiency Improvements in Image Annotation for Autonomous Driving
Frédéric Ratle (Samasource)*; Martine Bertrand (Samasource)
FISHING Net: Future Inference of Semantic Heatmaps In Grids
Noureldin Hendy (Zoox)*; Cooper Sloan (Zoox); Feng Tian (Zoox); Pengfei Duan (Zoox); Nick Charchut (Zoox); Yuesong Xie (Zoox); Chuang Wang (Zoox); James Philbin (Zoox)
Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning
Jianyu Chen (UC Berkeley)*; Shengbo Li (Tsinghua University); Masayoshi TOMIZUKA (MSC Lab)
BEV-Seg: Bird's Eye View Semantic Segmentation Using Geometry and Semantic Point Cloud
Mong Him Ng (UC Berkeley)*; Kaahan Radia (University Of California, Berkeley)*; Jianfei Chen (University of California, Berkeley); Dequan Wang (UC Berkeley); ionel Gog (University of California, Berkeley); Joey Gonzalez (University of California, Berkeley)
Call for papers
We invite paper submissions in two formats: Full papers: Original research work that has not been published or accepted recently (4-8 pages excluding references). Extended abstract: A significant work that has been published or accepted recently. 2 pages excluding references.
Accepted papers will be published on this website but they will not be part of the conference proceedings.
The topics include but are not limited to:
- Generalization and scaling-up in detection / tracking / scene understanding
- Handling of long-tail events / Performance and safety evaluation
- Self-supervised / semi-supervised learning / domain adaptation / transfer learning / multi-task learning for autonomous driving
- Efficient large-scale data labeling
- Learning in simulated environments
- Autonomous driving datasets
- Model architectures / deep learning
- Multi-modality sensor fusion for autonomous driving
Important dates
Submission Open: Feb. 28, 2020
Submission Deadline: April 1, 2020 April 8, 2020 April 15, 2020 (11:59pm PST)
Acceptance Decision: April 22, 2020 May 6, 2020
Camera-Ready Version: June 7, 2020 (11:59 pm PST)
Submission guidelines
Submitted manuscripts should follow the CVPR 2020 paper template. Submissions will be peer reviewed under the double-blind policy, and need to be submitted through the CMT system: https://cmt3.research.microsoft.com/WSAD2020
Presentation guidelines
Accepted submissions will be invited for poster presentations at the workshop. Details to follow at least two weeks before the workshop.