Research Field

Title Multimodal AI
Content ¤ýDistinguishing Homophenes using Multi-head Visual-audio Memory for Lip Reading (AAAI 2022)
¤ýTalking Face Generation with Precise Lip-syncing via Audio-Lip Memory (AAAI 2022)
¤ýTowards Versatile Pedestrian Detector with Multisensory-Matching and Multispectral Recalling Memory (AAAI 2022)
¤ýLip to Speech Synthesis with Visual Context Attentional GAN (NeurIPS 2021)
¤ýMulti-modality Associative Bridging through Memory: Speech Sound Recollected from Face Video (ICCV 2021)
¤ýCybersickness Assessment of Individual Viewers for VR Content via Graph-based Symptom Relation Embedding (ECCV 2020)
¤ýCross-Modal Memory Augmented Visual Speech Recognition (IEEE Trans. on Multimedia)
¤ýSpeech Reconstruction with Reminiscent Sound via Visual Voice Memory (IEEE Trans. on Audio Speech and Language Processing)
¤ýAssessing Individual VR Sickness through Deep Feature Fusion of VR Video and Physiological Response (IEEE Trans. on Circuits and Systems for Video Technology)
Title Robust and Reliable AI
Content ¤ýDistilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck (NeurIPS 2021)
¤ýTowards Robust Training of Multi-Sensor data Fusion Network Against Adversarial Examples in Semantic Segmentation (ICASSP 2021)
¤ýAdversarially Robust Multi-Sensor Fusion Model Training via Random Feature Fusion for Semantic Segmentation (ICIP 2021)
¤ýRobust Ensemble Model Training via Random Layer Sampling Against Adversarial Attack (BMVC 2021)
¤ýRobust Decision-based black-box adversarial attack via Coarse-to-fine Random Search (ICIP 2021)
¤ýRevisiting Role of Autoencoders In Adversarial Settings (ICIP 2021)
¤ýAdversarially Robust Hyperspectral Image Classification via Random Spectral Sampling and Spectral Shape Encoding (IEEE Access)
Title Explainable AI
Content ¤ýRobust Perturbation for Visual Explanation: Cross-checking Mask Optimization to Avoid Class Distortion (IEEE Trans. on Image Processing)
¤ýVisual Explanation of Challenging Conditioned Dataset with Bias-reducing Memory (BMVC 2021)
¤ýInterpretation of Lesional Detection via Counterfactual Generation (ICIP 2021)
¤ýTowards Human-Like Interpretable Object Detection Via Spatial Relation Encoding (ICIP 2020)
¤ýRealistic Breast Mass Generation through BIRADS Category (MICCAI 2019)
¤ýGeneration of Multimodal Justification Using Visual Word Constraint Model for Explainable Computer-Aided Diagnosis (MICCAIW 2019)
¤ýBuilding a Breast-Sentence Dataset: Its Usefulness for Computer-Aided Diagnosis (ICCVW 2019)
¤ýVisual evidence for interpreting diagnostic decision of deep neural network in computer-aided diagnosis (Medical Imaging 2019)
¤ýFacial Dynamics Interpreter Network: What are the Important Relations between Local Dynamics for Facial Trait Estimation? (ECCV 2018)
Title Computer Vision and Image Processing with Deep Learning
Content ¤ýVideo Prediction Recalling Long-term Motion Context via Memory Alignment Learning (CVPR 2021)
¤ýRobust Small-scale Pedestrian Detection with Cued Recall via Memory Learning (ICCV 2021)
¤ýTowards a Better Understanding of VR Sickness: Physical Symptom Prediction for VR Contents (AAAI 2021)
¤ýVisual Comfort Aware-Reinforcement Learning for Depth Adjustment of Stereoscopic 3D Images (AAAI 2021)
¤ýStructure Boundary Preserving Segmentation for Medical Image with Ambiguous Boundary (CVPR 2020)
¤ýMode Variational LSTM Robust to Unseen Modes of Variation: Application to Facial Expression Recognition (AAAI 2019)
¤ýBidirectional Multi-scale Aggregation Networks for Abnormal Event Detection (IEEE Trans. on Image Processing)
¤ýUncertainty-Guided Cross-Modal Learning for Robust Multispectral Pedestrian Detection (IEEE Trans. on Circuits and Systems for Video Technology)
¤ýClass Uncertainty-Aware Gradient Modulation for Robust Object Detection (IEEE Trans. on Circuits and Systems for Video Technology)
¤ýRobust Video Frame Interpolation with Exceptional Motion Map (IEEE Trans. on Circuits and Systems for Video Technology)
Title Previous research topics
Content [link]