Home /
Research
Showing 805 - 810 / 904
Mutual Modality Learning for Video Action Classification
StepanKomkov, MaksimDzabraev, AleksandrPetiushko....
Published date-11/04/2020
ActionClassification, ActionClassification, ActionRecognition, OpticalFlowEstimation
The construction of models for video action classification progresses rapidly. However, the performance of those models can still be easily improved by ensembling with the same models trained on different …
Uncertainty-Aware Voxel based 3D Object Detection and Tracking with von-Mises Loss
YuanxinZhong, MinghanZhu, HueiPeng....
Published date-11/04/2020
3DObjectDetection, ObjectDetection, ObjectTracking
Object detection and tracking is a key task in autonomy. Specifically, 3D object detection and tracking have been an emerging hot topic recently. Although various methods have been proposed for …
Quantized Variational Inference
AmirDib....
Published date-11/04/2020
VariationalInference
We present Quantized Variational Inference, a new algorithm for Evidence Lower Bound maximization. We show how Optimal Voronoi Tesselation produces variance free gradients for ELBO optimization at the cost of …
Handwriting Classification for the Analysis of Art-Historical Documents
ChristianBartz, HendrikRätz, ChristophMeinel....
Published date-11/04/2020
OpticalCharacterRecognition, TextClassification
Digitized archives contain and preserve the knowledge of generations of scholars in millions of documents. The size of these archives calls for automatic analysis since a manual analysis by specialists …
BGGAN: Bokeh-Glass Generative Adversarial Network for Rendering Realistic Bokeh
MingQian, CongyuQiao, JiaminLin....
Published date-11/04/2020
A photo captured with bokeh effect often means objects in focus are sharp while the out-of-focus areas are all blurred. DSLR can easily render this kind of effect naturally. However, …
Tweet Sentiment Quantification: An Experimental Re-Evaluation
AlejandroMoreo, FabrizioSebastiani....
Published date-11/04/2020
SentimentAnalysis
Sentiment quantification is the task of estimating the relative frequency (or "prevalence") of sentiment-related classes (such as Positive, Neutral, Negative) in a sample of unlabelled texts; this is especially important …