RESEARCH AREA
Adversarial Attack & Defense
Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Input [CVPR 2022]
Geometrically Adaptive Dictionary Attack on Face Recognition [WACV 2022]
On the Effectiveness of Small Input Noise for Defending Against Query-based Black-Box Attacks [WACV 2022]
HIDDEN CONDITIONAL ADVERSARIAL ATTACKS [ICIP 2022]
EXPLOITING DOUBLY ADVERSARIAL EXAMPLES FOR IMPROVING ADVERSARIAL ROBUSTNESS [ICIP 2022]
ADVERSARIAL TRAINING WITH CHANNEL ATTENTION REGULARIZATION [ICIP 2022]
ADAPTIVE WARPING NETWORK FOR TRANSFERABLE ADVERSARIAL ATTACKS [ICIP 2022]
Rethinking Training Schedules for Verifiably Robust Networks [ICIP 2021]
Meta learning & deep network
Few-shot Open-set Recognition by Transformation Consistency [CVPR 2021]
A Parameter Efficient Multi-Scale Capsule Network [ICIP 2021]
Reinforcement Learning-based Layer-wise Quantization For Lightweight Deep Neural Networks [ICIP 2020]
image recognition
Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization [IJCV 2022]
Fine-Grained Multi-Class Object Counting [ICIP 2021]
MobileHumanPose: Toward Real-Time 3D Human Pose Estimation in Mobile Devices [CVPRW 2021]
RPM-Net: Robust Pixel-Level Matching Networks for Self-Supervised Video Object Segmentation [WACV 2020]
Combinational Class Activation Maps for Weakly Supervised Object Localization [WACV 2020]
Multi-Step Quantization of a Multi-Scale Network for Crowd Counting [ICIP 2020]
A Global-local Embedding Module for Fashion Landmark Detection [ICCVW 2019]
CNN-based Semantic Segmentation Using Level Set Loss [WACV 2019]
Domain Adaptation
Semi-Supervised Domain Adaptation via Selective Pseudo Labeling and Progressive Self-Training [ICPR 2021]
Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation [ECCV 2020]
Arbitrary Style Transfer Using Graph Instance Normalization [ICIP 2020]
Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation [ICCV 2019]
Self-Training with Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection [ICCV 2019]
Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection [CVPR 2019]
Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation [BMVC 2019]
Visual Tracking & Person Re-Id
Meta Batch-Instance Normalization for Generalizable Person Re-Identification [CVPR 2021]
Weakly-Supervised Multiple Object Tracking via a Masked Center Point Warping Loss [ICIP 2021]
Multi-Target Multi-Camera Vehicle Tracking for City-Scale Traffic Management [CVPRW 2021]
Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification [CVPR 2020]
3D Vision
A Few Depth Points are All You Need for Multi-view Stereo: A Novel Semi-supervised Learning Method for Multi-view Stereo [ICCV 2021]
DnD: Dense Depth Estimation in Crowded Dynamic Indoor Scenes [ICCV 2021]
SAFENet: Self-Supervised Monocular Depth Estimation with Semantic-Aware Feature Extraction [NeurIPSW 2020]
Captioning & Explainable A.I
Explanation-based Graph Neural Networks for Graph Classification [ICPR 2022]
Understanding VQA for Negative Answers through Visual and Linguistic Inference [ICIP 2021]
Action analysis
Audio-Visual Glance Network for Efficient Video Recognition [ICCV 2023]
Towards Good Practices for Missing Modality Robust Action Recognition [AAAI 2023]
Modality Mixer for Multi-modal Action Recognition [WACV 2023]
Contrastive Accelerometer-Gyroscope Embedding for Human Activity Recognition [Sensors 2022]
Temporal Filtering Networks for Online Action Detection [Pattern Recognition 2021]
Learning to Discriminate Information for Online Action Detection: Analysis and Application [TPAMI 2022]
Learning to Discriminate Information for Online Action Detection [CVPR 2020]