Publications

DisCLIP: Open-Vocabulary Referring Expression Generation.
BMVC, 2023.
Oral presentation.
Lior Bracha *, Eitan Shaar*, Aviv Shamsian, Ethan Fetaya, Gal Chechik,
[paper] [code] [bibtex]

Auxiliary Learning as an Asymmetric Bargaining Game.
ICML, 2023.
Aviv Shamsian *, Aviv Navon *, Neta Glazer, Kenji Kawaguchi, Gal Chechik, Ethan Fetaya
[paper] [project page] [code] [bibtex]

Equivariant Architectures for Learning in Deep Weight Spaces.
ICML, 2023.
Oral presentation.
Aviv Navon *, Aviv Shamsian *, Idan Achituve, Ethan Fetaya, Gal Chechik, Haggai Maron
[paper] [project page] [video] [poster] [code] [blog] [bibtex]

COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality.
ECCV, 2022.

Honglu Zhou, Asim Kadav, Aviv Shamsian, Shijie Geng, Long Zaho, Ting Liu, Mubbasir Kapadia Hans Peter Graf
[paper] [code] [bibtex]

Multi-Task Learning as a Bargaining Game.
ICML, 2022.

Aviv Navon *, Aviv Shamsian *, Idan Achituve, Haggai Maron, Kenji Kawaguchi, Gal Chechik, Ethan Fetaya
[paper] [project page] [code] [bibtex]

Personalized Federated Learning with Gaussian Processes.
NeurIPS, 2021.

Idan Achituve, Aviv Shamsian, Aviv Navon, Gal Chechik, Ethan Fetaya
[paper] [code]

Personalized Federated Learning using Hypernetworks.
ICML 2021.

Aviv Shamsian *, Aviv Navon *, Ethan Fetaya, Gal Chechik,
(* equal contribution)
[paper] [project page] [code] [bibtex]

Learning the Pareto Front with Hypernetworks.
ICLR 2021.

Aviv Navon *, Aviv Shamsian *, Gal Chechik, Ethan Fetaya
(* equal contribution)
[paper] [project page] [code] [bibtex]

Learning Object Permanence From Video.
ECCV 2020.

Aviv Shamsian *, Ofri Kleinfeld *, Amir Globerson, Gal Chechik,
(* equal contribution)
[paper] [project page] [code] [bibtex]

Preprint

Open-vocabulary Keyword-spotting with Adaptive Instance Normalization.
Preprint, 2023.
Aviv Navon, Aviv Shamsian, Neta Glazer, Gill Hetz, Joseph Keshet
[paper]

FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning.
Preprint, 2023.
Rishub Tamirisa, Chulin Xie, Wenxuan Bao, Andy Zhou, Ron Arel, Aviv Shamsian
[paper]

LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading .
Preprint, 2023.
Yochai Yemini, Aviv Shamsian, Lior Bracha, Sharon Gannot, Ethan Fetaya
[paper] project page