Dengxin Dai

46

Papers

161

Total Citations

Papers (46)

Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search

Nighttime Defogging Using High-Low Frequency Decomposition and Grayscale-Color Networks

FreePoint: Unsupervised Point Cloud Instance Segmentation

MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation

Fast Algorithms for Linear and Kernel SVM+

Domain Adaptive Faster R-CNN for Object Detection in the Wild

Object Referring in Videos With Language and Human Gaze

Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation

Self-Aligned Video Deraining With Transmission-Depth Consistency

Three Ways To Improve Semantic Segmentation With Self-Supervised Depth Estimation

CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning

Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding

Continual Test-Time Domain Adaptation

Adiabatic Quantum Computing for Multi Object Tracking

Pix2NeRF: Unsupervised Conditional p-GAN for Single Image to Neural Radiance Fields Translation

Sound and Visual Representation Learning With Multiple Pretraining Tasks

Scribble-Supervised LiDAR Semantic Segmentation

Decoupling Zero-Shot Semantic Segmentation

Bi-Level Alignment for Cross-Domain Crowd Counting

DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation

LiDAR Snowfall Simulation for Robust 3D Object Detection

HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation

MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation

Self-Supervised Pre-Training With Masked Shape Prediction for 3D Scene Understanding

Weakly-Supervised Domain Adaptive Semantic Segmentation With Prototypical Contrastive Learning

Federated Incremental Semantic Segmentation

Continuous Pseudo-Label Rectified Domain Adaptive Semantic Segmentation With Implicit Neural Representations

PathTrack: Fast Trajectory Annotation With Path Supervision

Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation

Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather

ACDC: The Adverse Conditions Dataset With Correspondences for Semantic Driving Scene Understanding

Domain Adaptive Semantic Segmentation With Self-Supervised Depth Estimation

mDALU: Multi-Source Domain Adaptation and Label Unification With Partial Datasets

Task Switching Network for Multi-Task Learning

EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation

SSB: Simple but Strong Baseline for Boosting Performance of Open-Set Semi-Supervised Learning

Semantic Object Prediction and Spatial Sound Super-Resolution with Binaural Sounds

Weakly Supervised 3D Object Detection from Lidar Point Cloud

HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation

Class-Agnostic Object Counting Robust to Intraclass Diversity

TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation

End-to-End Urban Driving by Imitating a Reinforcement Learning Coach

Joint Vanishing Point Extraction and Tracking

Metric Imitation by Manifold Transfer for Efficient Vision Applications

Scale-Aware Alignment of Hierarchical Image Segmentation

Motion Transformer with Global Intention Localization and Local Movement Refinement