Urmăriți
Isma Hadji
Isma Hadji
Adresă de e-mail confirmată pe cse.yorku.ca - Pagina de pornire
Titlu
Citat de
Citat de
Anul
What do we understand about convolutional networks?
I Hadji, RP Wildes
arXiv preprint arXiv:1803.08834, 2018
1362018
Representation learning via global temporal alignment and cycle-consistency
I Hadji, KG Derpanis, AD Jepson
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2021
502021
Drop-dtw: Aligning common signal between sequences while dropping outliers
M Dvornik, I Hadji, KG Derpanis, A Garg, A Jepson
Advances in Neural Information Processing Systems 34, 13782-13793, 2021
382021
A Spatiotemporal Oriented Energy Network for Dynamic Texture Recognition
I Hadji, RP Wildes
IEEE International Conference on Computer Vision (ICCV), 2017
382017
P3iv: Probabilistic procedure planning from instructional videos with weak supervision
H Zhao, I Hadji, N Dvornik, KG Derpanis, RP Wildes, AD Jepson
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
332022
A new large scale dynamic texture dataset with application to convnet understanding
I Hadji, RP Wildes
Proceedings of the European Conference on Computer Vision (ECCV), 320-335, 2018
332018
Stepformer: Self-supervised step discovery and localization in instructional videos
N Dvornik, I Hadji, R Zhang, KG Derpanis, RP Wildes, AD Jepson
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023
142023
Local-to-Global Signature Descriptor for 3D Object Recognition
I Hadji, GN DeSouza
Asian Conference on Computer Vision, 570-584, 2014
132014
Flow graph to video grounding for weakly-supervised multi-step localization
N Dvornik, I Hadji, H Pham, D Bhatt, B Martinez, A Fazly, AD Jepson
European Conference on Computer Vision, 319-335, 2022
82022
Prediction of diffusional conductance in extracted pore network models using convolutional neural networks
N Misaghian, M Agnaou, MA Sadeghi, H Fathiannasab, I Hadji, E Roberts, ...
Computers & Geosciences 162, 105086, 2022
82022
What do we understand about convolutional networks? arXiv 2018
I Hadji, RP Wildes
arXiv preprint arXiv:1803.08834, 1803
81803
Graph2vid: Flow graph to video grounding for weakly-supervised multi-step localization
N Dvornik, I Hadji, H Pham, D Bhatt, B Martinez, A Fazly, AD Jepson
arXiv preprint arXiv:2210.04996, 2022
52022
What do we understand about convolutional networks. arXiv
I Hadji, RP Wildes
arXiv preprint arXiv:1803.08834, 2018
52018
Why convolutional networks learn oriented bandpass filters: Theory and empirical support
I Hadji, RP Wildes
arXiv preprint arXiv:2011.14665, 2020
42020
GePSAn: Generative Procedure Step Anticipation in Cooking Videos
MA Abdelsalam, SB Rangrej, I Hadji, N Dvornik, KG Derpanis, A Fazly
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023
32023
Clustering algorithms used in 3D scene segmentation
I Hadji, D Nabelek
2
Depth Image Dimension Reduction Using Deep Belief Networks
I Hadji, A Jain
1
Step discovery and localization in instructional videos using a self-supervised transformer
M Dvornik, I Hadji, R Zhang, K Derpanis, R Wildes, G Animesh, ...
US Patent App. 18/227,560, 2024
2024
You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation
M Noroozi, I Hadji, B Martinez, A Bulat, G Tzimiropoulos
arXiv preprint arXiv:2401.17258, 2024
2024
Graph Guided Question Answer Generation for Procedural Question-Answering
HX Pham, I Hadji, X Xu, Z Degutyte, J Rainey, E Kazakos, A Fazly, ...
arXiv preprint arXiv:2401.13594, 2024
2024
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–20