Identifying visible actions in lifestyle vlogs O Ignat, L Burdick, J Deng, R Mihalcea Proceedings of the 57th Annual Meeting of the Association for Computational …, 2019 | 17 | 2019 |
FIBER: Fill-in-the-blanks as a challenging video understanding evaluation framework S Castro, R Wang, P Huang, I Stewart, O Ignat, N Liu, JC Stroud, ... Proceedings of the 60th Annual Meeting of the Association for Computational …, 2021 | 15 | 2021 |
A PhD Student's Perspective on Research in NLP in the Era of Very Large Language Models O Ignat, Z Jin, A Abzaliev, L Biester, S Castro, N Deng, X Gao, A Gunal, ... Proceedings of the 2024 Joint International Conference on Computational …, 2023 | 11 | 2023 |
WhyAct: Identifying Action Reasons in Lifestyle Vlogs O Ignat, S Castro, H Miao, W Li, R Mihalcea Proceedings of the 2021 Conference on Empirical Methods in Natural Language …, 2021 | 11 | 2021 |
OCR Improves Machine Translation for Low-Resource Languages O Ignat, J Maillard, V Chaudhary, F Guzmán Proceedings of the 61th Annual Meeting of the Association for Computational …, 2022 | 9 | 2022 |
Bridging the Digital Divide: Performance Variation across Socio-Economic Factors in Vision-Language Models J Nwatu, O Ignat, R Mihalcea Proceedings of the 2023 Conference on Empirical Methods in Natural Language …, 2023 | 6 | 2023 |
Detecting Inspiring Content on Social Media O Ignat, YL Boureau, JA Yu, A Halevy 9th International Conference on Affective Computing & Intelligent …, 2021 | 6 | 2021 |
Disparity image segmentation for free-space detection I Oana 2016 IEEE 12th international conference on intelligent computer …, 2016 | 6 | 2016 |
Scalable Performance Analysis for Vision-Language Models S Castro, O Ignat, R Mihalcea Proceedings of the 12th Joint Conference on Lexical and Computational …, 2023 | 4 | 2023 |
When did it happen? Duration-informed temporal localization of narrated actions in vlogs O Ignat, S Castro, Y Zhou, J Bao, D Shan, R Mihalcea ACM Transactions on Multimedia Computing, Communications, and Applications …, 2022 | 2 | 2022 |
MAiDE-up: Multilingual Deception Detection of GPT-generated Hotel Reviews O Ignat, X Xu, R Mihalcea arXiv preprint arXiv:2404.12938, 2024 | 1 | 2024 |
Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models O Ignat, Z Jin, A Abzaliev, L Biester, S Castro, N Deng, X Gao, A Gunal, ... arXiv preprint arXiv:2305.12544, 2023 | 1 | 2023 |
Building a Flexible Knowledge Graph to Capture Real-World Events. L Burdick, O Ignat, Y Zhang, R Mihalcea, M Wang, S Wilson, Y Wei, ... TAC, 2019 | 1 | 2019 |
CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark D Romero, C Lyu, HA Wibowo, T Lynn, I Hamed, AN Kishore, A Mandal, ... arXiv preprint arXiv:2406.05967, 2024 | | 2024 |
Cross-cultural Inspiration Detection and Analysis in Real and LLM-generated Social Media Data O Ignat, GG Lakshmy, R Mihalcea arXiv preprint arXiv:2404.12933, 2024 | | 2024 |
Towards Algorithmic Fidelity: Mental Health Representation across Demographics in Synthetic vs. Human-generated Data S Mori, O Ignat, A Lee, R Mihalcea Proceedings of the 2024 Joint International Conference on Computational …, 2024 | | 2024 |
Annotations on a Budget: Leveraging Geo-Data Similarity to Balance Model Performance and Annotation Cost O Ignat, L Bai, J Nwatu, R Mihalcea Proceedings of the 2024 Joint International Conference on Computational …, 2024 | | 2024 |
Augment the Pairs: Semantics-Preserving Image-Caption Pair Augmentation for Grounding-Based Vision and Language Models J Yi, B Uzkent, O Ignat, Z Li, A Garg, X Yu, L Liu Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2024 | | 2024 |
Human Action Co-occurrence in Lifestyle Vlogs using Graph Link Prediction O Ignat, S Castro, W Li, R Mihalcea Proceedings of the 2024 TextGraphs-17: Graph-based Methods for Natural …, 2023 | | 2023 |
Towards Human Action Understanding in Social Media Videos Using Multimodal Models O Ignat University of Michigan, 2022 | | 2022 |