Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100

Dima Damen; Hazel Doughty; Giovanni Maria Farinella; Antonino Furnari; Evangelos Kazakos; Jian Ma; Davide Moltisanti; Jonathan Munro; Toby Perrett; Will Price; Michael Wray

doi:10.1007/s11263-021-01531-2

Keywords

Computer sciencePipeline (software)Artificial intelligenceAction (physics)Task (project management)Anticipation (artificial intelligence)Adaptation (eye)EPICAction recognitionPattern recognition (psychology)Computer visionPsychology

Affiliated Institutions

Related Publications

Deep Domain Confusion: Maximizing for Domain Invariance

Eric Tzeng , Judy Hoffman , Ning Zhang +2 more

Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias on a standard benchmark. Fine-tuning ...

2014 arXiv (Cornell University) 2347 citations

Biased Representation Learning for Domain Adaptation

Fei Huang , Alexander Yates

Representation learning is a promising technique for discovering features that allow supervised classifiers to generalize from a source domain dataset to arbitrary new domains. ...

2012 23 citations

Learning Transferable Features with Deep Adaptation Networks

Mingsheng Long , Yue Cao , Jianmin Wang +1 more

Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. However, as deep features eventually...

2015 arXiv (Cornell University) 1222 citations

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

Jeff Donahue , Yangqing Jia , Oriol Vinyals +4 more

We evaluate whether features extracted from the activation of a deep convolutional network trained in a fully supervised fashion on a large, fixed set of object recognition task...

2013 arXiv (Cornell University) 3559 citations

A continual learning survey: Defying forgetting in classification tasks

Matthias Delange , Rahaf Aljundi , Marc Masana +5 more

Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct t...

2021 IEEE Transactions on Pattern Analysis... 1488 citations

Publication Info

Year: 2021
Type: article
Volume: 130
Issue: 1
Pages: 33-55
Citations: 309
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

309

OpenAlex

Cite This

APA Style

                            
                                
                                    Dima Damen, 
                                
                                    Hazel Doughty, 
                                
                                    Giovanni Maria Farinella
                                
                                et al.
                            
                            (2021). 
                            Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100. 
                            International Journal of Computer Vision
                            , 130
                            (1)
                            , 33-55.
                            https://doi.org/10.1007/s11263-021-01531-2
                        

Identifiers

DOI: 10.1007/s11263-021-01531-2