Fetching the paper…
Reading the bibliography…
Current state-of-the-art human activity recognition is focused on the classification of temporally trimmed videos in which only one action occurs per frame.
Random forests
L. Breiman · 2001
Earlier work this paper cites.
Action Recognition with Improved Trajectories
H. Wang and C. Schmid · 2013
Earlier work this paper cites.
Continuous gesture recognition from articulated poses
G. Evangelidis, G. Singh, and R. Horaud · 2014
Earlier work this paper cites.
Learning spatiotemporal features with 3d convolutional networks
D. Tran, L. Bourdev, R. Fergus, L. Torresani, and M. Paluri · 2014
Cited alongside, same era.
Activitynet: A large-scale video benchmark for human activity understanding
F. Caba Heilbron, V. Escorcia, B. Ghanem, and J. Carlos Niebles · 2015
Cited alongside, same era.
Going deeper with convolutions
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich · 2015
Later among the works it cites.
The imagenet shuffle: Reorganized pre-training for video event detection
P. Mettes, D. Koelma, and C. G. M. Snoek · 2016
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…