Author: Susang Kim

GIRAFFE : Representing Scenes as Compositional Generative Neural Feature Fields (CVPR 2021 Best Paper Award)

Read more

Multiscale Vision Transformers(MViT)

Read more

detectors: detecting objects with recursive feature pyramid and switchable atrous convolution

Read more

GroupFace: Learning Latent Groups and Constructing Group-based Representations for Face Recognition

Read more

EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks

Read more

AutoML : Bayesian Optimization, AMC, Auto Augmentation, Active Learning

Read more

long-term feature banks for detailed video understanding

Read more

learning video representations from correspondence proposals

Read more

Action Recognition / A New Model and the Kinetics Dataset

https://docs.google.com/presentation/d/e/2PACX-1vQG3Pi_j13d15qoz_mPoszeKPi5pKqSOq3rmtqjD-M1v6SNyEAWrUIx6EpBUN4eUZ-1sCvtKLXaupuL/pub?start=false&loop=false&delayms=3000

Read more

eXplainable AI (XAI)

Read more