As AI systems have obtained significant performance to be deployed widel...
This paper studies the q-learning, recently coined as the continuous-tim...
Effective modeling of complex spatiotemporal dependencies in long-form v...
In recent years, convolutional neural networks (CNNs) have shown great
p...
Graph Contrastive Learning (GCL) has shown promising performance in grap...
Learning transferable and domain adaptive feature representations from v...
Face recognition models trained under the assumption of identical traini...
Physiological computing uses human physiological data as system inputs i...
Face anti-spoofing (FAS) seeks to discriminate genuine faces from fake o...
The recommendation system is an important commercial application of mach...
While federated learning (FL) enables distributed agents to collaborativ...
While deep face recognition has benefited significantly from large-scale...
This paper studies competitions with rank-based reward among a large num...
Based on previous work for the static problem, in this paper we first de...
Recognizing wild faces is extremely hard as they appear with all kinds o...
Blind video deblurring restores sharp frames from a blurry sequence with...
We address the challenging problem of generating facial attributes using...
Trust management of Internet of connected vehicles has been a hot topic
...
This paper presents the IMS contribution to the PolEval 2018 Shared Task...
We propose a machine reading comprehension model based on the
compare-ag...
Real-world face recognition datasets exhibit long-tail characteristics, ...
Recent developments in deep domain adaptation have allowed knowledge tra...
Recent data-driven approaches to scene interpretation predominantly pose...
Despite rapid advances in face recognition, there remains a clear gap be...
We present a general-purpose tagger based on convolutional neural networ...
We present a transition-based dependency parser that uses a convolutiona...
Deep neural networks (DNNs) trained on large-scale datasets have recentl...
Monocular 3D object parsing is highly desirable in various scenarios
inc...