On the day of my PhD defense (May 17, 2024), we are also organizing a workshop with 4 talks focusing on various aspects of modeling vision and language in deep neural networks ranging from grounding to evaluation. You can see my thesis here.
Location: Potgieterszaal, University Library Singel, Amsterdam
14:30 Doors open
15:00 Albert Gatt: Time and Events: Explorations in Multimodal Models
15:30 Sina Zarrieß: Context in Referring Expression Generation: Pressure or Resource?
16:00 Break
16:30 Yuki Asano: Self-Supervised Learning in the Age of GPT4-V
17:00 Emiel van Miltenburg: Towards Human-Centered Evaluation of Image Captioning Systems
17:30 Closing
This workshop is sponsored by the ERC CoG project DREAM (grant agreement No. 819455).