A landmark-free approach for automatic, dense and robust correspondence of 3D faces
WITS: Weakly-supervised individual tooth segmentation model trained on box-level labels
Decoupling multi-task causality for improved skin lesion segmentation and classification
Co-Attention Fusion Network for Multimodal Skin Cancer Diagnosis
Retinal image enhancement with artifact reduction and structure retention
Multi-scale multi-hierarchy attention convolutional neural network for fetal brain extraction
Low-rank 2D local discriminant graph embedding for robust image feature extraction
Conditional mixture modeling and model-based clustering
DisRFC: a dissimilarity-based Random Forest Clustering approach
Few-shot learning with unsupervised part discovery and part-aligned similarity
Adaptive momentum variance for attention-guided sparse adversarial attacks
Adversarial scratches: Deployable attacks to CNN classifiers
A unified model for the sparse optimal scoring problem
Grouping-based Oversampling in Kernel Space for Imbalanced Data Classification
Better pseudo-label: Joint domain-aware label and dual-classifier for semi-supervised domain generalization
BP-triplet net for unsupervised domain adaptation: A Bayesian perspective
Margin embedding net for robust margin collaborative representation-based classification
Towards prior gap and representation gap for long-tailed recognition
Graph-embedded subspace support vector data description
SaberNet: Self-attention based effective relation network for few-shot learning
Noise-robust oversampling for imbalanced data classification
Transformed domain convolutional neural network for Alzheimer's disease diagnosis using structural MRI
Pyramid Geometric Consistency Learning For Semantic Segmentation
Collaborative Learning with Unreliability Adaptation for Semi-Supervised Image Classification
Robust Table Detection and Structure Recognition from Heterogeneous Document Images
GCM: Efficient video recognition with glance and combine module
Answering knowledge-based visual questions via the exploration of Question Purpose
A full data augmentation pipeline for small object detection based on generative adversarial networks
An accurate stereo matching method based on color segments and edges
Self-regularized prototypical network for few-shot semantic segmentation
UAVformer: A Composite Transformer Network for Urban Scene Segmentation of UAV Images
Dynamic dense CRF inference for video segmentation and semantic SLAM
LAE-Net: A locally-adaptive embedding network for low-light image enhancement
Image inpainting via spatial projections
Single image super‐resolution based on progressive fusion of orientation‐aware features
Image manipulation detection by multiple tampering traces and edge artifact enhancement
Investigating intrinsic degradation factors by multi-branch aggregation for real-world underwater image enhancement
From Distortion Manifold to Perceptual Quality: a Data Efficient Blind Image Quality Assessment Approach
Incremental learning for transductive support vector machine
A new algorithm for support vector regression with automatic selection of hyperparameters
ScribbleNet: Efficient interactive annotation of urban city scenes for semantic segmentation
BH2I-GAN: Bidirectional Hash_code-to-Image Translation using Multi-Generative Multi-Adversarial Nets
LongReMix: Robust learning with high confidence samples in a noisy label environment
Deep autoregressive models with spectral attention
Query efficient black-box adversarial attack on deep neural networks
Single image super-resolution based on directional variance attention network
Online change-point detection with kernels
Online and offline streaming feature selection methods with bat algorithm for redundancy analysis
Neural graph embeddings as explicit low-rank matrix factorization for link prediction
GripNet: Graph information propagation on supergraph for heterogeneous graphs
AEDNet: Adaptive Edge-Deleting Network For Subgraph Matching
Game-theoretic hypergraph matching with density enhancement
Back-compatible Color QR Codes for colorimetric applications
Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices
CSR: Cascade Conditional Variational Auto Encoder with Socially-aware Regression for Pedestrian Trajectory Prediction
OW-TAL: Learning Unknown Human Activities for Open-World Temporal Action Localization
Robust Physical-World Attacks on Face Recognition
Temporal sparse adversarial attack on sequence-based gait recognition
