Home /
Research
Showing 847 - 852 / 897
MARNet: Multi-Abstraction Refinement Network for 3D Point Cloud Analysis
RahulChakwate, ArulkumarSubramaniam, AnuragMittal....
Published date-11/02/2020
RepresentationLearning, SemanticSegmentation
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
YaoyaoDing, LigengZhu, ZhihaoJia....
Published date-11/02/2020
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
SahanBulathwela, MariaPerez-Ortiz, EmineYilmaz....
Published date-11/02/2020
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
JosePatino, NataliaTomashenko, MassimilianoTodisco....
Published date-11/02/2020
SpeakerRecognition
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
ZhuangLi, LizhenQu, GholamrezaHaffari....
Published date-11/02/2020
SemanticParsing
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
DavidSamuel, MilanStraka....
Published date-11/02/2020
SemanticParsing
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 …