ActivityNet-1.3

Generating human action proposals in untrimmed videos is an important yet challenging task with wide applications. Current methods often suffer from the noisy boundary locations and the inferior quality of confidence scores used for proposal retrieving.

Data and Resources

Cite this as

F. C. Heilbron, V. Escorcia, B. Ghanem, J. C. Niebles (2024). Dataset: ActivityNet-1.3. https://doi.org/10.57702/dwomv3bw

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2207.07097
Citation
  • https://doi.org/10.48550/arXiv.2210.14284
  • https://doi.org/10.48550/arXiv.1806.02964
  • https://doi.org/10.48550/arXiv.1908.00707
  • https://doi.org/10.48550/arXiv.2009.07641
  • https://doi.org/10.48550/arXiv.2303.07347
Author F. C. Heilbron
More Authors
V. Escorcia
B. Ghanem
J. C. Niebles
Homepage https://activitynet.org/