Prati
Kiana Ehsani
Kiana Ehsani
Research Scientist @ PRIOR, AI2
Potvrđena adresa e-pošte na allenai.org - Početna stranica
Naslov
Citirano
Citirano
Godina
Ai2-thor: An interactive 3d environment for visual ai
E Kolve, R Mottaghi, W Han, E VanderBilt, L Weihs, A Herrasti, M Deitke, ...
arXiv preprint arXiv:1712.05474, 2017
7542017
Objaverse: A universe of annotated 3d objects
M Deitke, D Schwenk, J Salvador, L Weihs, O Michel, E VanderBilt, ...
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023
2602023
Learning to learn how to learn: Self-adaptive visual navigation using meta-learning
M Wortsman, K Ehsani, M Rastegari, A Farhadi, R Mottaghi
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2019
2182019
Segan: Segmenting and generating the invisible
K Ehsani, R Mottaghi, A Farhadi
Proceedings of the IEEE conference on computer vision and pattern …, 2018
1712018
🏘 ProcTHOR: Large-Scale Embodied AI Using Procedural Generation
M Deitke, E VanderBilt, A Herrasti, L Weihs, K Ehsani, J Salvador, W Han, ...
Advances in Neural Information Processing Systems 35, 5982-5994, 2022
1012022
Manipulathor: A framework for visual object manipulation
K Ehsani, W Han, A Herrasti, E VanderBilt, L Weihs, E Kolve, A Kembhavi, ...
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2021
912021
Watching the world go by: Representation learning from unlabeled videos
D Gordon, K Ehsani, D Fox, A Farhadi
arXiv preprint arXiv:2003.07990, 2020
842020
Objaverse-xl: A universe of 10m+ 3d objects
M Deitke, R Liu, M Wallingford, H Ngo, O Michel, A Kusupati, A Fan, ...
Advances in Neural Information Processing Systems 36, 2024
792024
Who let the dogs out? modeling dog behavior from visual data
K Ehsani, H Bagherinezhad, J Redmon, R Mottaghi, A Farhadi
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2018
762018
Contrasting contrastive self-supervised representation learning pipelines
K Kotar, G Ilharco, L Schmidt, K Ehsani, R Mottaghi
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
512021
Use the force, luke! learning to predict physical forces by simulating effects
K Ehsani, S Tulsiani, S Gupta, A Farhadi, A Gupta
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020
422020
Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery
S Yitzhak Gadre, K Ehsani, S Song
arXiv e-prints, arXiv: 2105.01047, 2021
40*2021
Retrospectives on the embodied ai workshop
M Deitke, D Batra, Y Bisk, T Campari, AX Chang, DS Chaplot, C Chen, ...
arXiv preprint arXiv:2210.06849, 2022
372022
Continuous scene representations for embodied ai
SY Gadre, K Ehsani, S Song, R Mottaghi
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
332022
Learning generalizable visual representations via interactive gameplay
L Weihs, A Kembhavi, K Ehsani, SM Pratt, W Han, A Herrasti, E Kolve, ...
arXiv preprint arXiv:1912.08195, 2019
252019
Structure from action: Learning interactions for articulated object 3d structure discovery
N Nie, SY Gadre, K Ehsani, S Song
arXiv preprint arXiv:2207.08997, 2022
142022
Towards disturbance-free visual mobile manipulation
T Ni, K Ehsani, L Weihs, J Salvador
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2023
62023
Object manipulation via visual target localization
K Ehsani, A Farhadi, A Kembhavi, R Mottaghi
European Conference on Computer Vision, 321-337, 2022
62022
Phone2proc: Bringing robust robots into our chaotic world
M Deitke, R Hendrix, A Farhadi, K Ehsani, A Kembhavi
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023
52023
Harmonic mobile manipulation
R Yang, Y Kim, A Kembhavi, X Wang, K Ehsani
arXiv preprint arXiv:2312.06639, 2023
42023
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20