Gang Hua

68

Papers

333

Total Citations

Papers (68)

DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision

Towards Generalizable Multi-Object Tracking

Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perception

Componential Prompt-Knowledge Alignment for Domain Incremental Learning

Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding

Jigsaw++: Imagining Complete Shape Priors for Object Reassembly

Token Coordinated Prompt Attention is Needed for Visual Prompting

State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding

A Convolutional Neural Network Cascade for Face Detection

A Multi-Level Contextual Model For Person Recognition in Photo Albums

Ordinal Regression With Multiple Output CNN for Age Estimation

Correlational Gaussian Processes for Cross-Domain Visual Recognition

Order-Preserving Wasserstein Distance for Sequence Matching

Collaborative Deep Reinforcement Learning for Joint Object Search

StyleBank: An Explicit Representation for Neural Image Style Transfer

ER3: A Unified Framework for Event Retrieval, Recognition and Recounting

Neural Aggregation Network for Video Face Recognition

Stereoscopic Neural Style Transfer

Towards Open-Set Identity Preserving Face Synthesis

Revisiting Deep Intrinsic Image Decompositions

gDLS*: Generalized Pose-and-Scale Estimation Given Scale and Gravity Priors

Few-Shot Open-Set Recognition Using Meta-Learning

LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud Based Deep Networks

SaccadeNet: A Fast and Accurate Object Detector

Self-Robust 3D Point Recognition via Gather-Vector Guidance

Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking

Diverse Semantic Image Synthesis via Probability Distribution Modeling

Learning View Selection for 3D Scenes

SGCN: Sparse Graph Convolution Network for Pedestrian Trajectory Prediction

Diversity-Aware Meta Visual Prompting

MotionTrack: Learning Robust Short-Term and Long-Term Motions for Multi-Object Tracking

Regularizing Second-Order Influences for Continual Learning

Progressive Backdoor Erasing via Connecting Backdoor and Adversarial Attacks

Learning Discriminative Reconstructions for Unsupervised Outlier Removal

Multi-Class Multi-Annotator Active Learning With Robust Gaussian Process for Visual Recognition

Coherent Online Video Style Transfer

Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding

CVAE-GAN: Fine-Grained Image Generation Through Asymmetric Training

A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing

Weakly Supervised Temporal Action Localization Through Contrast Based Evaluation Networks

Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction

Enriching Local and Global Contexts for Temporal Action Localization

Practical Relative Order Attack in Deep Ranking

Towards Precise Embodied Dialogue Localization via Causality Guided Diffusion

GistNet: A Geometric Structure Transfer Network for Long-Tailed Recognition

Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance

SOAR: Scene-debiasing Open-set Action Recognition

Trajectory Unified Transformer for Pedestrian Trajectory Prediction

Sparse Instance Conditioned Multimodal Trajectory Prediction

Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting

HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending

Parallel Attention Interaction Network for Few-Shot Skeleton-Based Action Recognition

Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning

Learning from Noisy Pseudo Labels for Semi-Supervised Temporal Action Localization

Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization

Adversarial Ranking Attack and Defense

Uncertainty-Based Spatial-Temporal Attention for Online Action Detection

Breadcrumbs: Adversarial Class-Balanced Sampling for Long-Tailed Recognition

Meta Pairwise Relationship Distillation for Unsupervised Person Re-Identification

Boosting Point-Supervised Temporal Action Localization through Integrating Query Reformation and Optimal Transport

Moment Quantization for Video Temporal Grounding

SAMPO: Scale-wise Autoregression with Motion Prompt for Generative World Models

Temporal Correlation Vision Transformer for Video Person Re-Identification

Enhancing Implicit Shape Generators Using Topological Regularizations

Similarity Learning on an Explicit Polynomial Kernel Feature Map for Person Re-Identification

Hierarchical-PEP Model for Real-World Face Recognition

Passport-aware Normalization for Deep Model Protection

Robust Pose Estimation in Crowded Scenes with Direct Pose-Level Inference