Disclaimer
If you're planing to use information provided on this site, please keep in mind that all numbers and papers are added by authors without double checking. We of course try to keep results as accurate as possible, and whenever we got notice of an error it will be fixed, but this does not release you from the obligation of reading the papers and double checking the numbers listed here before using them.
JHMDB
Paper : Towards understanding action recognition
Author : H. Jhuang and J. Gall and S. Zuffi and C. Schmid and M. J. Black
Dataset URL
Description : Joints for the HMDB dataset (J-HMDB) is based on 928 clips from HMDB51 comprising 21 action categories. Each frame has a 2D pose annotation based on a 2D articulated human puppet model that provides scale, pose, segmentation, coarse viewpoint, and dense optical flow for the humans in action.
Number of Videos : 928
Number of Classes : 21
Resources
Evaluation: JHMDB Action classification
Description: Action classifiaction as described by authors
Results
Result |
Paper |
Description |
URL |
Peer Reviewed |
Year |
Result |
Paper |
Description |
URL |
Peer Reviewed |
Year |
71.08 |
Multi-region two-stream R-CNN for action detection[Xiaojiang Peng, Cordelia Schmid]
|
MR-TS R-CNN |
URL
|
Yes
|
2016
|
62.5 |
Finding Action Tubes[Georgia Gkioxari, Jitendra Malik]
|
Action Tubes |
URL
|
Yes
|
2015
|
72.2 |
P-CNN: Pose-based CNN Features for Action Recognition[Guilhem Cheron, Ivan Laptev, Cordelia Schmid]
|
P-CNN + IDT-FV |
URL
|
Yes
|
2015
|
69.03 |
Action Recognition with Stacked Fisher Vectors[Xiaojiang Peng, Changqing Zou, Yu Qiao, Qiang Peng]
|
Stacked Fisher Vectors (FV+SFV) |
URL
|
Yes
|
2014
|
73.3 |
Higher-order Pooling of CNN Features via Kernel Linearization for Action Recognition[A. Cherian, P. Koniusz, S. Gould]
|
HOK + second-order + Trajectories |
URL
|
Yes
|
2017
|
73.7 |
Generalized Rank Pooling for Activity Recognition[Anoop Cherian, Basura Fernando, Mehrtash Harandi, Stephen Gould]
|
Generalized Rank Pooling + IDT-FV |
URL
|
Yes
|
2017
|
76.1 |
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection[Mohammadreza Zolfaghari , Gabriel L. Oliveira, Nima Sedaghat, Thomas Brox]
|
Chained Multi-stream Networks |
URL
|
Yes
|
2017
|
67.2 |
An End-to-end 3D Convolutional Neural Network for Action Detection and Segmentation in Videos[Rui Hou and Chen Chen and Mubarak Shah]
|
T-CNN |
URL
|
No
|
2017
|
85.5 |
PoTion: Pose MoTion Representation for Action Recognition[Vasileios Choutas, Philippe Weinzaepfel, Jérôme Revaud, Cordelia Schmid]
|
I3D + PoTion |
URL
|
Yes
|
2018
|
57 |
PoTion: Pose MoTion Representation for Action Recognition[Vasileios Choutas, Philippe Weinzaepfel, Jérôme Revaud, Cordelia Schmid]
|
PoTion |
URL
|
Yes
|
2018
|
74.2 |
Non-Linear Temporal Subspace Representations for Activity Recognition[Anoop Cherian, Suvrit Sra, Stephen Gould, Richard Hartley]
|
KRP-FS + IDT-FV |
URL
|
Yes
|
2018
|
62.9 |
Adding Attentiveness to the Neurons in Recurrent Neural Networks[Pengfei Zhang, Jianru Xue, Cuiling Lan, Wenjun Zeng, Zhanning Gao, Nanning Zheng]
|
EleAtt-GRU |
URL
|
Yes
|
2018
|
71.8 |
Relational Action Forecasting[Chen Sun, Abhinav Shrivastava, Carl Vondrick, Rahul Sukthankar, Kevin Murphy, Cordelia Schmid]
|
DR2N at 50% |
URL
|
No
|
2019
|
86.1 |
PA3D: Pose-Action 3D Machine for Video Recognition[An Yan, Yali Wang, Zhifeng Li, Yu Qiao]
|
PA3D + RPAN |
URL
|
Yes
|
2019
|
If you want to add this result data into your web page, please insert the following HTML code on your web page: