Home /
Research
Showing 799 - 804 / 897
Pixel-wise Dense Detector for Image Inpainting
RuisongZhang, WeizeQuan, BaoyuanWu....
Published date-11/04/2020
ImageInpainting
Recent GAN-based image inpainting approaches adopt an average strategy to discriminate the generated image and output a scalar, which inevitably lose the position information of visual artifacts. Moreover, the adversarial …
Registration Loss Learning for Deep Probabilistic Point Set Registration
FelixJäremoLawin, Per-ErikForssén....
Published date-11/04/2020
Probabilistic methods for point set registration have interesting theoretical properties, such as linear complexity in the number of used points, and they easily generalize to joint registration of multiple point …
MTLB-STRUCT @PARSEME 2020: Capturing Unseen Multiword Expressions Using Multi-task Learning and Pre-trained Masked Language Models
ShivaTaslimipoor, SaraBahaadini, EkaterinaKochmar....
Published date-11/04/2020
Multi-TaskLearning
This paper describes a semi-supervised system that jointly learns verbal multiword expressions (VMWEs) and dependency parse trees as an auxiliary task. The model benefits from pre-trained multilingual BERT. BERT hidden …
Guided Navigation from Multiple Viewpoints using Qualitative Spatial Reasoning
DaniloPerico, PauloE.Santos, ReinaldoBianchi....
Published date-11/03/2020
Navigation is an essential ability for mobile agents to be completely autonomous and able to perform complex actions. However, the problem of navigation for agents with limited (or no) perception …
A spatial hue similarity measure for assessment of colourisation
SeánMullery, PaulF.Whelan....
Published date-11/03/2020
SSIM
Automatic colourisation of grey-scale images is an ill-posed multi-modal problem. Where full-reference images exist, objective performance measures rely on pixel-difference techniques such as MSE and PSNR. These measures penalise any …
Minimum Bayes Risk Training for End-to-End Speaker-Attributed ASR
NaoyukiKanda, ZhongMeng, LiangLu....
Published date-11/03/2020
SpeakerIdentification, SpeechRecognition
Recently, an end-to-end speaker-attributed automatic speech recognition (E2E SA-ASR) model was proposed as a joint model of speaker counting, speech recognition and speaker identification for monaural overlapped speech. In the …