Home /
Research
Showing 487 - 492 / 904
iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering
AmanChadha, GurneetArora, NavpreetKaloty....
Published date-11/16/2020
CommonSenseReasoning, DenseVideoCaptioning, MachineTranslation, QuestionAnswering, VideoCaptioning, VideoQuestionAnswering
Most prior art in visual understanding relies solely on analyzing the "what" (e.g., event recognition) and "where" (e.g., event localization), which in some cases, fails to describe correct contextual relationships …
Automatic selection of clustering algorithms using supervised graph embedding
NoyCohen-Shapira, LiorRokach....
Published date-11/16/2020
AutoML, Clustering, GraphEmbedding, Meta-Learning
The widespread adoption of machine learning (ML) techniques and the extensive expertise required to apply them have led to increased interest in automated ML solutions that reduce the need for …
Cluster-Specific Predictions with Multi-Task Gaussian Processes
ArthurLeroy, PierreLatouche, BenjaminGuedj....
Published date-11/16/2020
Clustering, GaussianProcesses, Multi-TaskLearning
A model involving Gaussian processes (GPs) is introduced to simultaneously handle multi-task learning, clustering, and prediction for multiple functional data. This procedure acts as a model-based clustering method for functional …
Enforcing robust control guarantees within neural network policies
PriyaL.Donti, MelroseRoderick, MahyarFazlyab....
Published date-11/16/2020
When designing controllers for safety-critical systems, practitioners often face a challenging tradeoff between robustness and performance. While robust control methods provide rigorous guarantees on system stability under certain worst-case disturbances, …
Fast and Robust Cascade Model for Multiple Degradation Single Image Super-Resolution
SantiagoLópez-Tapia, NicolásPérezdelaBlanca....
Published date-11/16/2020
Deblurring, ImageSuper-Resolution, SuperResolution, Super-Resolution
Single Image Super-Resolution (SISR) is one of the low-level computer vision problems that has received increased attention in the last few years. Current approaches are primarily based on harnessing the …
Learning Associative Inference Using Fast Weight Memory
ImanolSchlag, TsendsurenMunkhdalai, JürgenSchmidhuber....
Published date-11/16/2020
LanguageModelling, MetaReinforcementLearning
Humans can quickly associate stimuli to solve problems in novel contexts. Our novel neural network model learns state representations of facts that can be composed to perform such associative inference. …