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.
Charades
Paper : Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding
Author : Gunnar A. Sigurdsson and G{"u}l Varol and Xiaolong Wang and Ali Farhadi and Ivan Laptev and Abhinav Gupta
Dataset URL
Description : Charades is dataset composed of 9848 videos of daily indoors activities collected through Amazon Mechanical Turk. 267 different users were presented with a sentence, that includes objects and actions from a fixed vocabulary, and they recorded a video acting out the sentence. The dataset contains 66,500 temporal annotations for 157 action classes, 41,104 labels for 46 object classes, and 27,847 textual descriptions of the videos.
Number of Videos : 9848
Number of Classes : 157
Evaluation: Video classification
Description: Video action classification performance is evaluated with the standard mean average precision (mAP) measure.
Results
Result |
Paper |
Description |
URL |
Peer Reviewed |
Year |
Result |
Paper |
Description |
URL |
Peer Reviewed |
Year |
18.6 |
Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding[Gunnar A. Sigurdsson and G{"u}l Varol and Xiaolong Wang and Ali Farhadi and Ivan Laptev and Abhinav Gupta]
|
Combined Baslines |
URL
|
Yes
|
2016
|
22.4 |
Asynchronous Temporal Fields for Action Recognition[Gunnar A. Sigurdsson, Santosh Divvala, Ali Farhadi, Abhinav Gupta]
|
Asynchronous Temporal Field |
URL
|
Yes
|
2017
|
21 |
ActionVLAD: Learning spatio-temporal aggregation for action classification[Rohit Girdhar, Deva Ramanan, Abhinav Gupta, Josef Sivic, Bryan Russell]
|
ActionVLAD (RGB only, BN-inception) + iDT |
URL
|
Yes
|
2017
|
39.5 |
Non-local Neural Networks[Xiaolong Wang, Ross Girshick, Abhinav Gupta, Kaiming He]
|
NL I3D (RGB) |
URL
|
No
|
2017
|
24.1 |
Compressed Video Action Recognition[Chao-Yuan Wu and Manzil Zaheer and Hexiang Hu and R. Manmatha and Alexander J. Smola and Philipp Kraehenbuehl]
|
CoViAR + optical flow |
URL
|
No
|
2017
|
19.5 |
Temporal Dynamic Graph LSTM for Action-driven Video Object Detection[Yuan Yuan, Xiaodan Liang, Xiaolong Wang, Dit-Yan Yeung, Abhinav Gupta]
|
TD-Graph LSTM |
URL
|
Yes
|
2017
|
26.7 |
Video Representation Learning Using Discriminative Pooling[Jue Wang, Anoop Cherian, Fatih Porikli, Stephen Gould]
|
SVMP(VGG+IDT) |
URL
|
Yes
|
2018
|
42.5 |
Long-Term Feature Banks for Detailed Video Understanding[Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, Kaiming He, Philipp Krähenbühl, Ross Girshick]
|
LFB-NL (on validation set) |
URL
|
No
|
2018
|
43.4 |
Long-Term Feature Banks for Detailed Video Understanding[Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, Kaiming He, Philipp Krähenbühl, Ross Girshick]
|
LFB-NL (on test set) |
URL
|
No
|
2018
|
37.8 |
VideoGraph: Recognizing Minutes-Long Human Activities in Videos[Noureldien Hussein, Efstratios Gavves, Arnold W.M. Smeulders]
|
I3D + VideoGraph |
URL
|
No
|
2019
|
36.2 |
Videos as Space-Time Region Graphs[Xiaolong Wang, Abhinav Gupta]
|
I3D + Joint GCN |
URL
|
Yes
|
2018
|
39.7 |
Videos as Space-Time Region Graphs[Xiaolong Wang, Abhinav Gupta]
|
NL I3D + GCN |
URL
|
Yes
|
2018
|
42.5 |
Long-Term Feature Banks for Detailed Video Understanding[Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, Kaiming He, Philipp Krähenbühl, Ross Girshick]
|
LFB NL |
URL
|
Yes
|
2019
|
41.1 |
Timeception for Complex Action Recognition[Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders]
|
|
URL
|
Yes
|
2019
|
43.1 |
Hallucinating IDT Descriptors and I3D Optical Flow Features for ActionRecognition with CNNs[Lei Wang, Piotr Koniusz, Du Q. Huynh]
|
HAF+BoW/FV/OFF halluc. +MSKx8/PN |
URL
|
Yes
|
2019
|
41 |
PA3D: Pose-Action 3D Machine for Video Recognition[An Yan, Yali Wang, Zhifeng Li, Yu Qiao]
|
PA3D + (GCN + I3D + NL I3D) |
URL
|
Yes
|
2019
|
58.6 |
AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures[Michael S. Ryoo, AJ Piergiovanni, Mingxing Tan, Anelia Angelova]
|
AssembleNet RGB+Flow |
URL
|
Yes
|
2019
|
38.1 |
Evolving Space-Time Neural Architectures for Videos[AJ Piergiovanni, Anelia Angelova, Alexander Toshev, and Michael Ryoo]
|
|
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:
Evaluation: Temporal localization
Description: Temporal localization/segmentation performance is evaluated with the standard mean average precision (mAP) measure
Results
Result |
Paper |
Description |
URL |
Peer Reviewed |
Year |
Result |
Paper |
Description |
URL |
Peer Reviewed |
Year |
12.8 |
Asynchronous Temporal Fields for Action Recognition[Gunnar A. Sigurdsson, Santosh Divvala, Ali Farhadi, Abhinav Gupta]
|
Asynchronous Temporal Field |
URL
|
Yes
|
2017
|
12.7 |
R-C3D: Region Convolutional 3D Network for Temporal Activity Detection[Huijuan Xu,Abir Das,Kate Saenko]
|
Region Convolutional 3D Network |
URL
|
Yes
|
2017
|
8.9 |
Predictive-Corrective Networks for Action Detection[Achal Dave,Olga Russakovsky,Deva Ramanan]
|
Predictive-Corrective Networks (RGB Only) |
URL
|
Yes
|
2017
|
8.9 |
Asynchronous Temporal Fields for Action Recognition[Gunnar A. Sigurdsson, Santosh Divvala, Ali Farhadi, Abhinav Gupta]
|
Two-Stream baseline |
URL
|
Yes
|
2017
|
1.98 |
Temporal Dynamic Graph LSTM for Action-driven Video Object Detection[Yuan Yuan, Xiaodan Liang, Xiaolong Wang, Dit-Yan Yeung, Abhinav Gupta]
|
TD-Graph LSTM |
URL
|
Yes
|
2017
|
14.2 |
Video Representation Learning Using Discriminative Pooling[Jue Wang, Anoop Cherian, Fatih Porikli, Stephen Gould]
|
SVMP(VGG+IDT) |
URL
|
Yes
|
2018
|
19.4 |
Learning Latent Super-Events to Detect Multiple Activities in Videos[AJ Piergiovanni, Michael S. Ryoo]
|
I3D + super-events |
URL
|
Yes
|
2018
|
22.3 |
Temporal Gaussian Mixture Layer for Videos[AJ Piergiovanni and Michael Ryoo]
|
|
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: