Home /

Research

Showing 847 - 852 / 897

MARNet: Multi-Abstraction Refinement Network for 3D Point Cloud Analysis


Authors:  RahulChakwate, ArulkumarSubramaniam, AnuragMittal....
Published date-11/02/2020
Tasks:  RepresentationLearning, SemanticSegmentation

Abstract: Representation learning from 3D point clouds is challenging due to their inherent nature of permutation invariance and irregular distribution in space. Existing deep learning methods follow a hierarchical feature extraction …

IOS: Inter-Operator Scheduler for CNN Acceleration


Authors:  YaoyaoDing, LigengZhu, ZhihaoJia....
Published date-11/02/2020

Abstract: To accelerate CNN inference, existing deep learning frameworks focus on optimizing intra-operator parallelization. However, a single operator can no longer fully utilize the available parallelism given the rapid advances in …

VLEngagement: A Dataset of Scientific Video Lectures for Evaluating Population-based Engagement


Authors:  SahanBulathwela, MariaPerez-Ortiz, EmineYilmaz....
Published date-11/02/2020

Abstract: With the emergence of e-learning and personalised education, the production and distribution of digital educational resources have boomed. Video lectures have now become one of the primary modalities to impart …

Speaker anonymisation using the McAdams coefficient


Authors:  JosePatino, NataliaTomashenko, MassimilianoTodisco....
Published date-11/02/2020
Tasks:  SpeakerRecognition

Abstract: Anonymisation has the goal of manipulating speech signals in order to degrade the reliability of automatic approaches to speaker recognition, while preserving other aspects of speech, such as those relating …

Context Dependent Semantic Parsing: A Survey


Authors:  ZhuangLi, LizhenQu, GholamrezaHaffari....
Published date-11/02/2020
Tasks:  SemanticParsing

Abstract: Semantic parsing is the task of translating natural language utterances into machine-readable meaning representations. Currently, most semantic parsing methods are not able to utilize contextual information (e.g. dialogue and comments …

ÚFAL at MRP 2020: Permutation-invariant Semantic Parsing in PERIN


Authors:  DavidSamuel, MilanStraka....
Published date-11/02/2020
Tasks:  SemanticParsing

Abstract: We present PERIN, a novel permutation-invariant approach to sentence-to-graph semantic parsing. PERIN is a versatile, cross-framework and language independent architecture for universal modeling of semantic structures. Our system participated in …

Filter by

Categories

Tags