What Actions are Needed for Understanding Human Actions in Videos?
@article{Sigurdsson2017WhatAA, title={What Actions are Needed for Understanding Human Actions in Videos?}, author={Gunnar A. Sigurdsson and Olga Russakovsky and A. Gupta}, journal={2017 IEEE International Conference on Computer Vision (ICCV)}, year={2017}, pages={2156-2165} }
What is the right way to reason about human activities? What directions forward are most promising? In this work, we analyze the current state of human activity understanding in videos. The goal of this paper is to examine datasets, evaluation metrics, algorithms, and potential future directions. We look at the qualitative attributes that define activities such as pose variability, brevity, and density. The experiments consider multiple state-of-the-art algorithms and multiple datasets. The… CONTINUE READING
Supplemental Code
Github Repo
Via Papers with Code
Diagnostic tools and additional visualizations from "What Actions are Needed for Understanding Human Actions in Videos?" ICCV 2017
Figures and Topics from this paper
86 Citations
Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization
- Computer Science
- ECCV
- 2018
- 47
- PDF
CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning
- Computer Science
- ICLR
- 2020
- 21
- PDF
Weakly Supervised Gaussian Networks for Action Detection
- Computer Science, Mathematics
- 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
- 2020
- 7
- PDF
Structured Learning for Action Recognition in Videos
- Computer Science
- IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- 2019
Generating Videos of Zero-Shot Compositions of Actions and Objects
- Computer Science, Engineering
- ECCV
- 2020
- 1
- PDF
References
SHOWING 1-10 OF 44 REFERENCES
Learning realistic human actions from movies
- Computer Science
- 2008 IEEE Conference on Computer Vision and Pattern Recognition
- 2008
- 3,423
- PDF
Asynchronous Temporal Fields for Action Recognition
- Computer Science
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2017
- 116
- PDF
A combined pose, object, and feature model for action understanding
- Computer Science
- 2012 IEEE Conference on Computer Vision and Pattern Recognition
- 2012
- 62
Recognizing realistic actions from videos “in the wild”
- Computer Science
- 2009 IEEE Conference on Computer Vision and Pattern Recognition
- 2009
- 924
- PDF
ActivityNet: A large-scale video benchmark for human activity understanding
- Computer Science
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2015
- 881
- Highly Influential
- PDF
Detecting activities of daily living in first-person camera views
- Computer Science
- 2012 IEEE Conference on Computer Vision and Pattern Recognition
- 2012
- 598
- PDF
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos
- Computer Science
- International Journal of Computer Vision
- 2017
- 240
- PDF
HMDB: A large video database for human motion recognition
- Computer Science
- 2011 International Conference on Computer Vision
- 2011
- 1,966
- PDF
Machine Recognition of Human Activities: A Survey
- Computer Science
- IEEE Transactions on Circuits and Systems for Video Technology
- 2008
- 1,349
- PDF
ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification
- Computer Science
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2017
- 268
- PDF