Adobe researchers co-authored ten papers at the annual AAAI Conference on Artificial Intelligence (AAAI-23). The conference is hybrid, with both virtual and in-person components. AAAI is one of the top research conferences on machine learning. In recent years, deep learning approaches have made a significant impact at this conference. Nine papers will be presented at the main conference, and one at the AAAI Workshop on Scientific Document Understanding.
Adobe Research will also co-organize two workshops at AAAI 2023: the Scientific Document Understanding (SDU) workshop and the Multimodal AI for Financial Forecasting (Muffin) workshop, both of which attracted 28 paper submissions in total. Adobe Research also organized one shared task, Jargon/Terminology Detection. The results of the shared task will be presented during the conference.
AAAI 2023 conference – Adobe co-authored papers
Main conference papers
Audio-Visual Contrastive Learning with Temporal Self-Supervision
Simon Jenni, Alexander Black, John Collomosse
DocEdit: Language-guided Document Editing
Puneet Mathur, Rajiv Jain, Jiuxiang Gu, Franck Dernoncourt, Dinesh Manocha, Vlad Morariu
Few-Shot Composition Learning for Image Retrieval with Prompt Tuning
Junda Wu, Rui Wang, Handong Zhao, Ruiyi Zhang, Chaochao Lu, Shuai Li, Ricardo Henao
Layout Representation Learning with Spatial and Structural Hierarchies
Yue Bai, Dipu Manandhar, Zhaowen Wang, John Collomosse, Yun Fu
Learning Relational Causal Models with Cycles through Relational Acyclification
Ragib Ahsan, David Arbour, Elena Zheleva
Persuasion Strategies in Advertisements
Yaman Kumar Singla, Rajat Jha, Arunim Gupta, Milan Aggarwal, Aditya Garg, Ayush Bhardwaj, Tushar, Balaji Krishnamurthy, Rajiv Ratn Shah, Changyou Chen
Reinforced Approximate Exploratory Data Analysis
Shaddy Garg, Subrata Mitra, Tong Yu, Yash Gadhia, Arjun Kashettiwar
Representation Learning by Detecting Incorrect Location Embeddings
Sepehr Sameni, Simon Jenni, Paolo Favaro
Smoothed Online Combinatorial Optimization Using Imperfect Predictions
Kai Wang, Zhao Song, Georgios Theocharous, Sridhar Mahadevan
Workshop paper
Envisioning the Next-Gen Document Reader
Catherine Yeh, Nedim Lipka, Franck Dernoncourt
Presented at the Scientific Document Understanding Workshop
Learning the Visualness of Text Using Large Vision-Language Models
Gaurav Verma, Ryan Rossi, Christopher Tensmeyer, Jiuxiang Gu, Ani Nenkova
Presented at Creative AI Across Modalities Workshop
