Corpus ID: 195345805

Large-Scale Human Activity Mapping using Geo-Tagged Videos

@article{Zhu2017LargeScaleHA,
  title={Large-Scale Human Activity Mapping using Geo-Tagged Videos},
  author={Yi Zhu and Sen Liu and S. Newsam},
  journal={ArXiv},
  year={2017},
  volume={abs/1706.07911}
}
This paper is the first work to perform spatio-temporal mapping of human activity using the visual content of geo-tagged videos. We utilize a recent deep-learning based video analysis framework, termed hidden two-stream networks, to recognize a range of activities in YouTube videos. This framework is efficient and can run in real time or faster which is important for recognizing events as they occur in streaming video or for reducing latency in analyzing already captured video. This is, in turn… Expand

References

SHOWING 1-10 OF 51 REFERENCES
Spatio-temporal sentiment hotspot detection using geotagged photos
  • 24
  • PDF
Event geo-localization and tracking from crowd-sourced video metadata
  • 4
ActivityNet: A large-scale video benchmark for human activity understanding
  • 966
  • PDF
Single Frame Based Video Geo-Localisation Using Structure Projection
  • 5
  • PDF
Event-Based Analysis of People's Activities and Behavior Using Flickr and Panoramio Geotagged Photo Collections
  • 107
  • PDF
Hidden Two-Stream Convolutional Networks for Action Recognition
  • 176
  • PDF
Depth2Action: Exploring Embedded Depth for Large-Scale Action Recognition
  • 35
  • PDF
YouTube-8M: A Large-Scale Video Classification Benchmark
  • 689
  • PDF
...
1
2
3
4
5
...