Author

Idan Schwartz

Observed name: Schwartz, Idan

Institutions: Bar-Ilan University, Tel Aviv University

Observed institutions: Bar-Ilan University, Tel Aviv University, Technion – Israel Institute of Technology, Hebrew University of Jerusalem

OpenAlex ID: A5082617813

ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic

2022 · Yoad Tewel, Yoav Shalev, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 157

PDF

Factor Graph Attention

2019 · Idan Schwartz, Seunghak Yu, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 108

PDF

High-Order Attention Models for Visual Question Answering

2017 · Schwartz, Idan, Schwing, Alexander G., et al. · arXiv (Cornell University) · 80

PDF

A Simple Baseline for Audio-Visual Scene-Aware Dialog

2019 · Idan Schwartz, Alexander G. Schwing, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 68

PDF

Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies

2020 · Gat, Itai, Schwartz, Idan, et al. · arXiv (Cornell University) · 63

PDF

Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation

2024 · Guy Yariv, Itai Gat, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 40

PDF

Optimizing Relevance Maps of Vision Transformers Improves Robustness

2022 · Hila Chefer, Idan Schwartz, et al. · neural information processing systems · 24

PDF

Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation

2023 · Guy Yariv, Itai Gat, et al. · Interspeech (USB) · 22

Perceptual Score: What Data Modalities Does Your Model Perceive?

2021 · Gat, Itai, Schwartz, Idan, et al. · arXiv (Cornell University) · 17

PDF

Zero-Shot Video Captioning with Evolving Pseudo-Tokens

2022 · Tewel, Yoad, Shalev, Yoav, et al. · arXiv (Cornell University) · 16

PDF

Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic

2021 · Yoad Tewel, Yoav Shalev, et al. · 13

Ordered Attention for Coherent Visual Storytelling

2022 · Tom Braude, Idan Schwartz, et al. · ACM International Conference on Multimedia (ACM MM) · 12

PDF

Discriminative Class Tokens for Text-to-Image Diffusion Models

2023 · Idan Schwartz, Vésteinn Snæbjarnarson, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 11

PDF

Latent Space Explanation by Intervention

2022 · Itai Gat, Guy Lorberbom, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 11

PDF

Video and Text Matching with Conditioned Embeddings

2022 · Ameen Ali, Idan Schwartz, et al. · IEEE Winter Conference on Applications of Computer Vision · 11

PDF

AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation

2023 · Yariv, Guy, Gat, Itai, et al. · arXiv (Cornell University) · 9

PDF

Ensemble of MRR and NDCG models for Visual Dialog

2021 · Idan Schwartz · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 7

PDF

Towards Coherent Visual Storytelling with Ordered Image Attention

2021 · Tom Braude, Idan Schwartz, et al. · arXiv (Cornell University) · 5

Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models

2026 · Oz Zafar, Yuval Cohen, et al. · IEEE Winter Conference on Applications of Computer Vision · 1

PDF

Reasoning Models Can Control Their Chains of Thought When They Tell Themselves To

2026 · Dolev, Uriel, Schwartz, Idan, et al. · arXiv (Cornell University)

PDF

LaMI: Augmenting Large Language Models via Late Multi-Image Fusion

2026 · Association for Computational Linguistics 2026, Adi, Yossi, et al. · Underline Science Inc.

LaMI: Augmenting Large Language Models via Late Multi-Image Fusion