Shiyi Lan

papers

948

total citations

papers (13)

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence From Box Supervision

ICCV 2021arXiv

citations

OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning

CVPR 2025arXiv

citations

InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling

ECCV 2020arXiv

citations

BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection

CVPR 2024arXiv

citations

SaccadeNet: A Fast and Accurate Object Detector

CVPR 2020arXiv

citations

Vision Transformers Are Good Mask Auto-Labelers

CVPR 2023arXiv

citations

Hydra-NeXt: Robust Closed-Loop Driving with Open-Loop Training

ICCV 2025arXiv

citations

Fully Attentional Networks with Self-emerging Token Labeling

ICCV 2023arXiv

citations

MDP: Multidimensional Vision Model Pruning with Latency Constraint

CVPR 2025arXiv

citations

Synthesize Diagnose and Optimize: Towards Fine-Grained Vision-Language Understanding

CVPR 2024

citations

Shiyi Lan

papers (13)

AdaViT: Adaptive Vision Transformers for Efficient Image Recognition

Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?

FocalFormer3D: Focusing on Hard Instance for 3D Object Detection

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence From Box Supervision

OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning

InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling

BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection

SaccadeNet: A Fast and Accurate Object Detector

Vision Transformers Are Good Mask Auto-Labelers

Hydra-NeXt: Robust Closed-Loop Driving with Open-Loop Training

Fully Attentional Networks with Self-emerging Token Labeling

MDP: Multidimensional Vision Model Pruning with Latency Constraint

Synthesize Diagnose and Optimize: Towards Fine-Grained Vision-Language Understanding

papers (13)

AdaViT: Adaptive Vision Transformers for Efficient Image Recognition

Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?

FocalFormer3D: Focusing on Hard Instance for 3D Object Detection

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence From Box Supervision

OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning

InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling

BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection

SaccadeNet: A Fast and Accurate Object Detector

Vision Transformers Are Good Mask Auto-Labelers

Hydra-NeXt: Robust Closed-Loop Driving with Open-Loop Training

Fully Attentional Networks with Self-emerging Token Labeling

MDP: Multidimensional Vision Model Pruning with Latency Constraint

Synthesize Diagnose and Optimize: Towards Fine-Grained Vision-Language Understanding