Schedule

SVRHM @ NeurIPS 2022 Workshop | Location: Room 394+395 @ New Orleans Ernest N. Morial Convention Center

December 2nd, 2022 | All times below are in CST (Central Standard Time)

New Orleans, Louisiana

8.45 - 9.00 : Opening Remarks

Session 1: Beyond Object Recognition in Humans and Machines

9.00 - 9.10: Michael Cohen (Amherst/MIT) [Invited Oral/Talk] | The bandwidth of perceptual awareness is constrained by specific high-level visual features | virtual

9.10 - 9.20: Matthew Koichi Grimes (DeepMind) [Invited Oral/Talk] | Learning to Look by Self-Prediction | in-person

9.20 - 9.40: Iris Groen (University of Amsterdam) | Do deep neural networks explain how humans represent scenes? | in-person

9.40 - 10.00: Dirk B. Walther (University of Toronto) | Gestalt grouping cues for understanding complex scenes: evidence from psychophysics, neuroscience, and computer vision | in-person

10.00 - 10.20: Josue Ortega-Caro (Yale University) | Local Convolutions Cause an Implicit Bias towards High Frequency Adversarial Examples | virtual

10.20 - 10.40: Katharina Dobs (Justus-Liebig University Giessen) | Using machines to test ‘why’ human face perception works the way it does | virtual

10.40 - 11.00: Kate Storrs (University of Auckland) | Learning about Materials by Learning to Predict Images and Videos | virtual

------

11.00 - 12.00: Poster Session 1 & Lunch Break

------

Session 2: Visual Aesthetics & Creativity in Humans and Machines

12.00 - 12.10: Balázs Meszéna (Wigner Research Centre for Physics) [Invited Oral/Talk] | Top-down effects in an early visual cortex inspired hierarchical Variational Autoencoder | in-person

12.10 - 12.20: Ching Fang (Columbia University) [Invited Oral/Talk] | Predictive Dynamics Improve Noise Robustness in a Deep Network Model of the Human Auditory System | in-person

12.20 - 12.40: Colin Conwell (Harvard University) | The Perceptual Primacy of Feeling: Affectless machine vision models explain the majority of variance in visually evoked affect and aesthetics | in-person

12.40 - 13.00: Piotr Mirowski (DeepMind) | Generative Collage and its Sticky Questions on Human-AI Co-Creativity | in-person

13.00 - 13.20: Philip Isola (MIT) | Generating Imagery Optimized for Human Consumption | in-person

13.20 - 14.40: Tom White (Victoria University of Wellington) | Tangible Abstractions | virtual

13.40 - 14.00 : Aenne Brielmann (Max-Planck Institute for Biological Cybernetics) | A computational model predicts humans' aesthetic judgments based on deep neural network feature values | virtual

14.00 - 15.00: Keynote: Margaret Livingstone (Harvard Medical School) | What Art can tell us about the Brain | virtual

------

15.00 - 16.00: Poster Session 2 & Artificio Reception

------

Session 3: The Future of Human and Machine Visual Intelligence

16.00 - 16.30: Jim DiCarlo (MIT) [Innaugural Quest Talk] | A report on recent experimental tests of two predictions of contemporary computable models of the biological deep neural network underling primate visual intelligence | virtual

16.30 - 16.40: Dawn Finzi (Stanford University) [Invited Oral/Talk] | Topographic DCNNs trained on a single self-supervised task capture the functional organization of cortex into visual processing streams | in-person

16.40 - 16.50: Tal Golan & Wenxuan Guo (Columbia University) [Invited Oral/Talk] | Distinguishing representational geometries with controversial stimuli: Bayesian experimental design and its application to face dissimilarity judgments | in-person

16.50 - 17.10: Jenelle Feather (Flatiron Institute) | Evaluating neural network models of vision and audition with model metamers | in-person

17.10 - 17.30: Tyler Bonnen (Stanford University) | Complimenting Learning Systems supporting 3D object perception | in-person

17.30 - 17.50: Patrick Mineault (xcorr) | What's the endgame of neuroAI? | virtual

17.50 - 18.15: Awards Ceremony + Closing Remarks + Ending Reception (Toast/Drinks)