CarFormer: Self-driving with Learned Object-Centric Representations
- 30 October 2024
- book chapter
- Published by Springer Nature
- p. 177-193
Abstract
No abstract availableKeywords
All Related Versions
This publication has 30 references indexed in Scilit:
- BEVFormer: Learning Bird’s-Eye-View Representation from Multi-camera Images via Spatiotemporal Transformers2022
- KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients2022
- Taming Transformers for High-Resolution Image Synthesis2021
- Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D2020
- Argoverse: 3D Tracking and Forecasting With Rich Maps2019
- YouTube-VOS: Sequence-to-Sequence Video Object Segmentation2018
- CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning2017
- A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation2016
- Microsoft COCO: Common Objects in Context2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009