Xiang Yu

CONDITIONAL SIMILARITY-BASED IMAGE IDENTIFICATION AND MATCHING WITH REDUCED LABELS

MULTIMODAL SEMANTIC ANALYSIS AND IMAGE RETRIEVAL

IMAGE FEATURE MATCHING WITH FORMAL PRIVACY GUARANTEES

GRADIENT SPLIT SYSTEM FOR RICH HUMAN ANALYSIS

DOMAIN GENERALIZATION BY GSNR OF PARAMETERS

SINGLE TRAINING SEQUENCE FOR NEURAL NETWORK USEABLE FOR MULTI-TASK SCENARIOS

OPTICAL ENCRYPTION CAMERA

VISUAL QUESTION ANSWERING WITH UNLABELED IMAGE AUGMENTATION

VIDEO DOMAIN ADAPTATION VIA CONTRASTIVE LEARNING

VIDEO DOMAIN ADAPTATION VIA CONTRASTIVE LEARNING

VIDEO DOMAIN ADAPTATION VIA CONTRASTIVE LEARNING

SINGLE STREAM MULTI-LEVEL ALIGNMENT FOR VISION-LANGUAGE PRETRAINING

CONTROLLABLE DYNAMIC MULTI-TASK ARCHITECTURES

DOMAIN GENERALIZABLE CONTINUAL LEARNING USING COVARIANCES

Domain generalized margin via meta-learning for deep face recognition

Face recognition from unseen domains via learning of semantic features

VIDEO DOMAIN ADAPTATION VIA CONTRASTIVE LEARNING

Face-aware person re-identification system

MULTI-TASK LEARNING VIA GRADIENT SPLIT FOR RICH HUMAN ANALYSIS

VOTING-BASED APPROACH FOR DIFFERENTIALLY PRIVATE FEDERATED LEARNING

LEARNING PRIVACY-PRESERVING OPTICS VIA ADVERSARIAL TRAINING

Face spoofing detection using a physical-cue-guided multi-source multi-channel framework

Deep face recognition based on clustering over unlabeled face data

Universal feature representation learning for face recognition

Pose-variant 3D facial attribute generation

Unsupervised cross-domain distance metric adaptation with feature transfer network

Surveillance system with activity recognition

Mobile device with activity recognition

Video representation of first-person videos for activity recognition without labels

Long-tail large scale face recognition by non-linear feature level domain adaptation

Long-tail large scale face recognition by non-linear feature level domain adaptation

Long-tail large scale face recognition by non-linear feature level domain adaptation

Long-tail large scale face recognition by non-linear feature level domain adaption

Viewpoint invariant object recognition by synthesization and domain adaptation

Parking lot surveillance with viewpoint invariant object recognition by synthesization and domain adaptation

LEARNING EFFICIENT OBJECT DETECTION MODELS WITH KNOWLEDGE DISTILLATION

Surveillance system for recognition in unlabeled videos with domain adversarial learning and knowledge distillation

Recognition in unlabeled videos with domain adversarial learning and knowledge distillation

Action recognition system for action recognition in unlabeled videos with domain adversarial learning and knowledge distillation

Face recognition system for face recognition in unlabeled videos with domain adversarial learning and knowledge distillation

Video surveillance system based on larger pose face frontalization

Face recognition using larger pose face frontalization

Video retrieval system based on larger pose face frontalization

Advanced driver-assistance system with landmark localization on objects in images using convolutional neural networks

Video security system using a Siamese reconstruction convolutional neural network for pose-invariant face recognition

Surveillance system with landmark localization on objects in images using convolutional neural networks

Landmark localization on objects in images using convolutional neural networks

Siamese reconstruction convolutional neural network for pose-invariant face recognition

Action recognition system with landmark localization on objects in images using convolutional neural networks

Login access control for secure/private data

Security system for facility access control

Liveness detection for antispoof face recognition

Camera system for traffic enforcement

Physical system access control

Deep deformation network for object landmark localization