Search Results for author:
Found 16 papers, 8 papers with code
ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions
Compared to the state-of-the-art, ViT-CoMer has the following advantages: (1) We inject spatial pyramid multi-receptive field convolutional features into the ViT architecture, which effectively alleviates the problems of limited local information interaction and single-feature representation in ViT.
MonoLSS: Learnable Sample Selection For Monocular 3D Detection
To select samples adaptively, we propose a Learnable Sample Selection (LSS) module, which is based on Gumbel-Softmax and a relative-distance sample divider.
Ranked #2 on
Monocular 3D Object Detection
on KITTI Cars Moderate
DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perception
To take full advantage of simulated data, we present a new unsupervised sim2real domain adaptation method for V2X collaborative detection named Decoupled Unsupervised Sim2Real Adaptation (DUSA).
V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting
Utilizing infrastructure and vehicle-side information to track and forecast the behaviors of surrounding traffic participants can significantly improve decision-making and safety in autonomous driving.
Multimodal Understanding Through Correlation Maximization and Minimization
To answer 2), we propose novel scores that summarize the learned common and individual structures and visualize the score gradients with respect to the input, visually discerning what the different representations capture.
Open-TransMind: A New Baseline and Benchmark for 1st Foundation Model Challenge of Intelligent Transportation
To address these, we designed the 1st Foundation Model Challenge, with the goal of increasing the popularity of foundation model technology in traffic scenarios and promoting the rapid development of the intelligent transportation industry.
Ranked #1 on
2D Object Detection
on CeyMo
INT2: Interactive Trajectory Prediction at Intersections
One of the most challenging problems in motion forecasting is interactive trajectory prediction, whose goal is to jointly forecasts the future trajectories of interacting agents.
TransIFF: An Instance-Level Feature Fusion Framework for Vehicle-Infrastructure Cooperative 3D Detection with Transformers
Furthermore, it can align the domain gaps between vehicle and infrastructure features, and improve the robustness of feature fusion, leading to a high cooperative perception accuracy.
A High Fidelity Simulation Framework for Potential Safety Benefits Estimation of Cooperative Pedestrian Perception
This paper proposes a high-fidelity simulation framework that can estimate the potential safety benefits of vehicle-to-infrastructure (V2I) pedestrian safety strategies.
DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection
Autonomous driving faces great safety challenges for a lack of global perspective and the limitation of long-range perception capabilities.
Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task
On the other hand, the data captured from roadside cameras have strengths over frontal-view data, which is believed to facilitate a safer and more intelligent autonomous driving system.
Rope3D: The Roadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task
On the other hand, the data captured from roadside cameras have strengths over frontal-view data, which is believed to facilitate a safer and more intelligent autonomous driving system.
DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning
Long-range and short-range temporal modeling are two complementary and crucial aspects of video recognition.
Ranked #6 on
Action Recognition
on ActivityNet
Deep Goal-Oriented Clustering
Clustering and prediction are two primary tasks in the fields of unsupervised and supervised learning, respectively.
Defense Through Diverse Directions
In this work we develop a novel Bayesian neural network methodology to achieve strong adversarial robustness without the need for online adversarial training.
Deep Message Passing on Sets
DMPS not only connects learning on graphs with learning on sets via deep kernel learning, but it also bridges message passing on sets and traditional diffusion dynamics commonly used in denoising models.
