Seguir
Shervin Ardeshir
Shervin Ardeshir
Senior Research Scientist, Netflix
Dirección de correo verificada de netflix.com - Página principal
Título
Citado por
Citado por
Año
GIS-assisted object detection and geospatial localization
S Ardeshir, AR Zamir, A Torroella, M Shah
Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland …, 2014
742014
Ego2Top: Matching Viewers in Egocentric and Top-view Videos
S Ardeshir, A Borji
European Conference on Computer Vision (ECCV), 2016
532016
Gps-tag refinement using random walks with an adaptive damping factor
A Roshan Zamir, S Ardeshir, M Shah
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2014
422014
Geo-semantic segmentation
S Ardeshir, K Malcolm Collins-Sibley, M Shah
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2015
382015
Egocentric Meets Top-view
S Ardeshir, A Borji
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018
282018
On Attention Modules for Audio-Visual Synchronization.
N Khosravan, S Ardeshir, R Puri
CVPR Workshops, 25-28, 2019
172019
Integrating egocentric videos in top-view surveillance videos: Joint identification and temporal alignment
S Ardeshir, A Borji
Proceedings of the European Conference on Computer Vision (ECCV), 285-300, 2018
162018
From third person to first person: Dataset and baselines for synthesis and retrieval
M Elfeki, K Regmi, S Ardeshir, A Borji
arXiv preprint arXiv:1812.00104, 2018
132018
A novel utilization of cluster-tree wireless sensor networks for situation awareness in smart grids
MS Ebrahimi, MH Daraei, V Behzadan, A Khajooeizadeh, SA Behrostaghi, ...
2011 IEEE PES Innovative Smart Grid Technologies, 1-5, 2011
102011
An exocentric look at egocentric actions and vice versa
S Ardeshir, A Borji
Computer Vision and Image Understanding 171, 61-68, 2018
82018
Estimating structural disparities for face models
S Ardeshir, C Segalin, N Kallus
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
52022
Egotransfer: Transferring motion across egocentric and exocentric domains using deep neural networks
S Ardeshir, K Regmi, A Borji
arXiv preprint arXiv:1612.05836, 2016
52016
Uncertainty in Contrastive Learning: On the Predictability of Downstream Performance
S Ardeshir, N Azizan
arXiv preprint arXiv:2207.09336, 2022
22022
On Negative Sampling for Audio-Visual Contrastive Learning from Movies
MM Kalayeh, S Ardeshir, L Liu, N Kamath, A Chandrashekar
arXiv preprint arXiv:2205.00073, 2022
22022
Character-focused Video Thumbnail Retrieval
S Ardeshir, N Kamath, H Taghavi
arXiv preprint arXiv:2204.06563, 2022
12022
Identifying representative frames in video content
SA Behrostaghi, NK Kamath
US Patent App. 17/344,752, 2021
12021
Techniques for identifying synchronization errors in media titles
R Puri, N Khosravan, SA Behrostaghi
US Patent App. 16/687,209, 2020
12020
From egocentric to top-view
S Ardeshir, A Borji
1
Representation Reliability and Its Impact on Downstream Tasks
YJ Park, H Wang, S Ardeshir, N Azizan
arXiv preprint arXiv:2306.00206, 2023
2023
LLM2Loss: Leveraging Language Models for Explainable Model Diagnostics
S Ardeshir
arXiv preprint arXiv:2305.03212, 2023
2023
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–20