Следене
Heng Wang
Heng Wang
TikTok
Потвърден имейл адрес: fb.com - Начална страница
Заглавие
Позовавания
Позовавания
Година
Action Recognition by Dense Trajectories
Heng Wang, Alexander Klaser, Cordelia Schmid, Cheng-Lin Liu
Proceedings of the IEEE conference on Computer Vision and Pattern …, 2011
3817*2011
Action recognition with improved trajectories
H Wang, C Schmid
Proceedings of the IEEE international conference on computer vision, 3551-3558, 2013
37472013
A closer look at spatiotemporal convolutions for action recognition
D Tran, H Wang, L Torresani, J Ray, Y LeCun, M Paluri
Proceedings of the IEEE conference on Computer Vision and Pattern …, 2018
24772018
Dense trajectories and motion boundary descriptors for action recognition
H Wang, A Kläser, C Schmid, CL Liu
International journal of computer vision 103, 60-79, 2013
19452013
Evaluation of local spatio-temporal features for action recognition
H Wang, MM Ullah, A Klaser, I Laptev, C Schmid
Bmvc 2009-british machine vision conference, 124.1-124.11, 2009
17522009
Is space-time attention all you need for video understanding?
G Bertasius, H Wang, L Torresani
ICML 2 (3), 4, 2021
9202021
Video Classification with Channel-Separated Convolutional Networks
D Tran, H Wang, L Torresani, M Feiszli
Proceedings of the IEEE International Conference on Computer Vision, 5552-5561, 2019
4962019
A robust and efficient video representation for action recognition
H Wang, D Oneata, J Verbeek, C Schmid
International journal of computer vision 119, 219-238, 2016
3412016
Large-scale weakly-supervised pre-training for video action recognition
D Ghadiyaram, M Feiszli, D Tran, X Yan, H Wang, D Mahajan
arXiv preprint arXiv:1905.00561, 2019
3202019
Video Modeling with Correlation Networks
H Wang, D Tran, L Torresani, M Feiszli
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020
1212020
Lear-inria submission for the thumos workshop
H Wang, C Schmid
ICCV workshop on action recognition with a large number of classes 2 (7), 8, 2013
1162013
Leveraging the present to anticipate the future in videos
A Miech, I Laptev, J Sivic, H Wang, L Torresani, D Tran
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2019
632019
FASTER Recurrent Networks for Efficient Video Classification
L Zhu, D Tran, L Sevilla-Lara, Y Yang, M Feiszli, H Wang
The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2020
562020
The AXES submissions at TrecVid 2013
R Aly, R Arandjelovic, K Chatfield, M Douze, B Fernando, Z Harchaoui, ...
50*2013
Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation
W Wang, M Feiszli, H Wang, D Tran
arXiv preprint arXiv:2104.04691, 2021
492021
Axes at trecvid 2012: Kis, ins, and med
D Oneata, M Douze, J Revaud, S Jochen, D Potapov, H Wang, ...
TRECVID workshop, 2012
37*2012
Devon: Deformable Volume Network for Learning Optical Flow
Y Lu, J Valmadre, H Wang, J Kannala, M Harandi, PHS Torr
IEEE Winter Conference on Applications of Computer Vision, 2020
352020
SLAC: A sparsely labeled dataset for action classification and localization
H Zhao, Z Yan, H Wang, L Torresani, A Torralba
arXiv preprint arXiv:1712.09374 2, 2017
332017
Scenes-Objects-Actions: A Multi-Task, Multi-Label Video Dataset
J Ray, H Wang, D Tran, Y Wang, M Feiszli, L Torresani, M Paluri
The European Conference on Computer Vision (ECCV), 2018
322018
Interactive Prototype Learning for Egocentric Action Recognition
X Wang, L Zhu, H Wang, Y Yang
ICCV 2021, 2021
282021
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20