Paper Notes
This repository contains my paper reading notes on deep learning and machine learning. It is inspired by Denny Britz, Daniel Takeshi and especially Patrick Langechuan Liu.
About Me
My name is Dat Vu, and I am currently leading the AI Team at PhenikaaX, a rapidly growing autonomous and industrial robot company where I serve as the Computer Vision Leader. I have a passion for seeking answers to complex questions and take great joy in exploring and deeply understanding mathematical concepts. You can see my publications here.
My ML/DL Notes
You can read my notes here.
2023-11
2023-10
2023-09
2023-08
2023-07
2023-06
2023-05
2023-04
2023-03
2023-02
- TPVFormer: Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction CVPR 2023 [Occupancy Network, Jiwen Lu]
- ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning ECCV 2022 [Hongyang Li]
- BEVFormer: Learning Bird’s-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers ECCV 2022 [BEVNet, Hongyang Li, Jifeng Dai]
- BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection [BEVNet]
- BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving [Jiwen Lu, BEVNet, perception + prediction]
- BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird’s-Eye View Representation [BEVNet, Han Song]
- PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark [BEVNet, lane line]
- VectorMapNet: End-to-end Vectorized HD Map Learning [BEVNet, LLD, Hang Zhao]
- PETR: Position Embedding Transformation for Multi-View 3D Object Detection ECCV 2022 [BEVNet]
- PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images [BEVNet, MegVii]
- M^2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation [BEVNet, nvidia]
- BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection [BEVNet, NuScenes SOTA, Megvii]
- CVT: Cross-view Transformers for real-time Map-view Semantic Segmentation CVPR 2022 oral [UTAustin, Philipp]
- Wayformer: Motion Forecasting via Simple & Efficient Attention Networks [Behavior prediction, Waymo]
- HDMapNet: An Online HD Map Construction and Evaluation Framework CVPR 2021 workshop [youtube video only, Li Auto]
- FIERY: Future Instance Prediction in Bird’s-Eye View from Surround Monocular Cameras ICCV 2021 [BEVNet, perception + prediction]