Deep learning-based face super-resolution: A survey
Face super-resolution (FSR), also known as face hallucination, which is aimed at enhancing
the resolution of low-resolution (LR) face images to generate high-resolution face images, is …
the resolution of low-resolution (LR) face images to generate high-resolution face images, is …
Face Detection and Segmentation Based on Improved Mask R‐CNN
K Lin, H Zhao, J Lv, C Li, X Liu… - Discrete dynamics in …, 2020 - Wiley Online Library
Deep convolutional neural networks have been successfully applied to face detection
recently. Despite making remarkable progress, most of the existing detection methods only …
recently. Despite making remarkable progress, most of the existing detection methods only …
Dynamic spatial-temporal representation learning for traffic flow prediction
As a crucial component in intelligent transportation systems, traffic flow prediction has
recently attracted widespread research interest in the field of artificial intelligence (AI) with …
recently attracted widespread research interest in the field of artificial intelligence (AI) with …
Tree-structured policy based progressive reinforcement learning for temporally language grounding in video
Temporally language grounding in untrimmed videos is a newly-raised task in video
understanding. Most of the existing methods suffer from inferior efficiency, lacking …
understanding. Most of the existing methods suffer from inferior efficiency, lacking …
Propagating facial prior knowledge for multitask learning in face super-resolution
Existing face hallucination methods always achieve improved performance through
regularizing the model with facial prior. Most of them always estimate facial prior information …
regularizing the model with facial prior. Most of them always estimate facial prior information …
MO-MIX: Multi-objective multi-agent cooperative decision-making with deep reinforcement learning
Deep reinforcement learning (RL) has been applied extensively to solve complex decision-
making problems. In many real-world scenarios, tasks often have several conflicting …
making problems. In many real-world scenarios, tasks often have several conflicting …
RestoreFormer++: Towards real-world blind face restoration from undegraded key-value pairs
Blind face restoration aims at recovering high-quality face images from those with unknown
degradations. Current algorithms mainly introduce priors to complement high-quality details …
degradations. Current algorithms mainly introduce priors to complement high-quality details …
Improving face-based age estimation with attention-based dynamic patch fusion
With the increasing popularity of convolutional neural networks (CNNs), recent works on
face-based age estimation employ these networks as the backbone. However, state-of-the …
face-based age estimation employ these networks as the backbone. However, state-of-the …
A novel approach to detect face mask using CNN
MS Islam, EH Moon, MA Shaikat… - 2020 3rd International …, 2020 - ieeexplore.ieee.org
Face detection and recognition will be considered as one of the most intriguing modalities
for biometric models. Those researches are mainly required for ensuring security in a most …
for biometric models. Those researches are mainly required for ensuring security in a most …
Reinforcement learning for weakly supervised temporal grounding of natural language in untrimmed videos
Temporal grounding of natural language in untrimmed videos is a fundamental yet
challenging multimedia task facilitating cross-media visual content retrieval. We focus on the …
challenging multimedia task facilitating cross-media visual content retrieval. We focus on the …