Picture for Yifeng Shi

Yifeng Shi

ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions

Add code
Mar 15, 2024
Figure 1 for ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions
Figure 2 for ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions
Figure 3 for ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions
Figure 4 for ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions
Viaarxiv icon

MonoLSS: Learnable Sample Selection For Monocular 3D Detection

Dec 22, 2023
Viaarxiv icon

DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perception

Add code
Oct 12, 2023
Figure 1 for DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perception
Figure 2 for DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perception
Figure 3 for DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perception
Figure 4 for DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perception
Viaarxiv icon

V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting

Add code
May 10, 2023
Figure 1 for V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting
Figure 2 for V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting
Figure 3 for V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting
Figure 4 for V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting
Viaarxiv icon

Multimodal Understanding Through Correlation Maximization and Minimization

May 04, 2023
Figure 1 for Multimodal Understanding Through Correlation Maximization and Minimization
Figure 2 for Multimodal Understanding Through Correlation Maximization and Minimization
Figure 3 for Multimodal Understanding Through Correlation Maximization and Minimization
Figure 4 for Multimodal Understanding Through Correlation Maximization and Minimization
Viaarxiv icon

Open-TransMind: A New Baseline and Benchmark for 1st Foundation Model Challenge of Intelligent Transportation

Add code
Apr 12, 2023
Figure 1 for Open-TransMind: A New Baseline and Benchmark for 1st Foundation Model Challenge of Intelligent Transportation
Figure 2 for Open-TransMind: A New Baseline and Benchmark for 1st Foundation Model Challenge of Intelligent Transportation
Figure 3 for Open-TransMind: A New Baseline and Benchmark for 1st Foundation Model Challenge of Intelligent Transportation
Figure 4 for Open-TransMind: A New Baseline and Benchmark for 1st Foundation Model Challenge of Intelligent Transportation
Viaarxiv icon

A High Fidelity Simulation Framework for Potential Safety Benefits Estimation of Cooperative Pedestrian Perception

Oct 18, 2022
Figure 1 for A High Fidelity Simulation Framework for Potential Safety Benefits Estimation of Cooperative Pedestrian Perception
Figure 2 for A High Fidelity Simulation Framework for Potential Safety Benefits Estimation of Cooperative Pedestrian Perception
Figure 3 for A High Fidelity Simulation Framework for Potential Safety Benefits Estimation of Cooperative Pedestrian Perception
Figure 4 for A High Fidelity Simulation Framework for Potential Safety Benefits Estimation of Cooperative Pedestrian Perception
Viaarxiv icon

DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection

Add code
Apr 12, 2022
Figure 1 for DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection
Figure 2 for DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection
Figure 3 for DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection
Figure 4 for DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection
Viaarxiv icon

Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task

Mar 25, 2022
Figure 1 for Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task
Figure 2 for Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task
Figure 3 for Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task
Figure 4 for Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task
Viaarxiv icon

DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning

Add code
May 25, 2021
Figure 1 for DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning
Figure 2 for DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning
Figure 3 for DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning
Figure 4 for DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning
Viaarxiv icon