Synthesizing attributes with unreal engine for fine-grained activity analysis

Tae Soo Kim, Mike Peven, Weichao Qiu, Alan Yuille, Gregory Hager

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We examine the problem of activity recognition in video using simulated data for training. In contrast to the expensive task of obtaining accurate labels from real data, synthetic data creation is not only fast and scalable, but provides ground-truth labels for more than just the activities of interest, including segmentation masks, 3D object keypoints, and more. We aim to successfully transfer a model trained on synthetic data to work on video in the real world. In this work, we provide a method of transferring from synthetic to real at intermediate representations of a video. We wish to perform activity recognition from the low-dimensional latent representation of a scene as a collection of visual attributes. As the ground-truth data does not exist in the ActEV dataset for attributes of interest, specifically orientation of cars in the ground-plane with respect to the camera, we synthesize this data. We show how we can successfully transfer a car orientation classifier, and use its predictions in our defined set of visual attributes to classify actions in video.

Original languageEnglish (US)
Title of host publicationProceedings - 2019 IEEE Winter Conference on Applications of Computer Vision Workshops, WACVW 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages35-37
Number of pages3
ISBN (Electronic)9781728113920
DOIs
StatePublished - Feb 8 2019
Event19th IEEE Winter Conference on Applications of Computer Vision Workshops, WACVW 2019 - Waikoloa Village, United States
Duration: Jan 7 2019Jan 11 2019

Publication series

NameProceedings - 2019 IEEE Winter Conference on Applications of Computer Vision Workshops, WACVW 2019

Conference

Conference19th IEEE Winter Conference on Applications of Computer Vision Workshops, WACVW 2019
CountryUnited States
CityWaikoloa Village
Period1/7/191/11/19

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Synthesizing attributes with unreal engine for fine-grained activity analysis'. Together they form a unique fingerprint.

Cite this