Qiang Xu

21

Papers

471

Total Citations

Papers (21)

SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach

MMA-Diffusion: MultiModal Attack on Diffusion Models

MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control

DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception

MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls

Text Image Inpainting via Global Structure-Guided Diffusion Models

Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

DIFFGUARD: Semantic Mismatch-Guided Out-of-Distribution Detection Using Pre-Trained Diffusion Models

HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation

DeciWatch: A Simple Baseline for 10× Efficient 2D and 3D Pose Estimation

SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos

Out-of-Distribution Detection with Semantic Mismatch under Masking

FullDiT: Video Generative Foundation Models with Multimodal Control via Full Attention

Multi-Patch Prediction: Adapting Language Models for Time Series Representation Learning

Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning

nuScenes: A Multimodal Dataset for Autonomous Driving

Active Teacher for Semi-Supervised Object Detection

Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes

TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks

SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction

HiBug: On Human-Interpretable Model Debug