Jessica A. F. Thompson, Hannah Sheahan, Christopher Summerfield. Learning to count visual objects by combining “what” and “where” in recurrent memory. In Ismini Lourentzou, Joy T. Wu, Satyananda Kashyap, Alexandros Karargyris, Leo Anthony Celi, Ban Kawas, Sachin S. Talathi, editors, Proceedings of The 1st Gaze Meets ML workshop, in conjunction with the Annual Conference on Neural Information Processing Systems, 03 December 2022, New Orleans, USA. Volume 210 of Proceedings of Machine Learning Research, pages 199-218, PMLR, 2022. [doi]
Abstract is missing.