Workshop
Gaze Meets ML
Amarachi Blessing Mbakwe 路 Joy T Wu 路 Dario Zanca 路 Elizabeth Krupinski 路 Satyananda Kashyap 路 Alexandros Karargyris
Room 240 - 241
Sat 16 Dec, 6:15 a.m. PST
Eye gaze has proven to be a cost-efficient way to collect large-scale physiological data that can reveal the underlying human attentional patterns in real-life workflows, and thus has long been explored as a signal to directly measure human-related cognition in various domains. Physiological data (including but not limited to eye gaze) offer new perception capabilities, which could be used in several ML domains, e.g., egocentric perception, embodied AI, NLP, etc. They can help infer human perception, intentions, beliefs, goals, and other cognition properties that are much needed for human-AI interactions and agent coordination. In addition, large collections of eye-tracking data have enabled data-driven modeling of human visual attention mechanisms, both for saliency or scan path prediction, with twofold advantages: from the neuro-scientific perspective to understand biological mechanisms better, and from the AI perspective to equip agents with the ability to mimic or predict human behavior and improve interpretability and interactions.
The Gaze meets ML workshop aims at bringing together an active research community to collectively drive progress in defining and addressing core problems in gaze-assisted machine learning. This year the workshop will run its 2nd edition at NeurIPS again and it attracts a diverse group of researchers from academia and industry presenting novel works in this area of research.
Schedule
Sat 6:15 a.m. - 6:30 a.m.
|
Open Remarks
(
Opening Remarks
)
>
|
馃敆 |
Sat 6:30 a.m. - 7:15 a.m.
|
Bertram Emil SHI (HKUST)
(
Invited Talk
)
>
SlidesLive Video |
馃敆 |
Sat 7:15 a.m. - 8:00 a.m.
|
Vidhya Navalpakkam (Google) - Accelerating human attention research via smartphones
(
Invited Talk
)
>
SlidesLive Video |
Vidhya Navalpakkam 馃敆 |
Sat 8:00 a.m. - 8:30 a.m.
|
Coffee Break
|
馃敆 |
Sat 8:00 a.m. - 8:30 a.m.
|
Poster Session
(
Poster Session
)
>
|
馃敆 |
Sat 8:30 a.m. - 8:45 a.m.
|
Interaction-aware Dynamic 3D Gaze Estimation in Videos
(
Oral
)
>
link
SlidesLive Video |
Chenyi Kuang 路 Jeffrey O Kephart 路 Qiang Ji 馃敆 |
Sat 8:45 a.m. - 9:00 a.m.
|
SuperVision: Self-Supervised Super-Resolution for Appearance-Based Gaze Estimation
(
Oral
)
>
link
SlidesLive Video |
Galen O'Shea 路 Majid Komeili 馃敆 |
Sat 9:00 a.m. - 9:15 a.m.
|
EG-SIF: Improving Appearance Based Gaze Estimation using Self Improving Features
(
Oral
)
>
link
SlidesLive Video |
Vasudev Singh 路 Chaitanya Langde 路 Sourav Lakhotia 路 Vignesh Kannan 路 Shuaib Ahmed 馃敆 |
Sat 9:15 a.m. - 9:30 a.m.
|
Planning by Active Sensing
(
Oral
)
>
link
SlidesLive Video |
Kaushik Lakshminarasimhan 路 Seren Zhu 路 Dora Angelaki 馃敆 |
Sat 9:30 a.m. - 9:45 a.m.
|
Crafting Good Views of Medical Images for Contrastive Learning via Expert-level Visual Attention
(
Oral
)
>
link
SlidesLive Video |
Sheng Wang 路 Zihao Zhao 路 Lichi Zhang 路 Dinggang Shen 路 Qian Wang 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
Evaluating Peripheral Vision as an Input Transformation to Understand Object Detection Model Behavior ( Poster ) > link | Anne Harrington 路 Vasha DuTell 路 Mark Hamilton 路 Ayush Tewari 路 Simon Stent 路 Bill Freeman 路 Ruth Rosenholtz 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
Leveraging Multi-Modal Saliency and Fusion for Gaze Target Detection ( Poster ) > link | Athul Mathew 路 Arshad Ali Khan 路 Thariq Khalid 路 Faroq AL-Tam 路 Riad Souissi 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
Exploring Foveation and Saccade for Improved Weakly-Supervised Localization ( Poster ) > link | Timur Ibrayev 路 Manish Nagaraj 路 Amitangshu Mukherjee 路 Kaushik Roy 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
SAM meets Gaze: Passive Eye Tracking for Prompt-based Instance Segmentation ( Poster ) > link | Daniel Beckmann 路 Jacqueline Kockwelp 路 Joerg Gromoll 路 Friedemann Kiefer 路 Benjamin Risse 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
GazeSAM: Interactive Image Segmentation with Eye Gaze and Segment Anything Model ( Poster ) > link | Bin Wang 路 Armstrong Aboah 路 Zheyuan Zhang 路 Hongyi Pan 路 Ulas Bagci 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
FoVAE: Reconstructive Foveation as a Self-Supervised Variational Inference Task for Visual Representation Learning ( Poster ) > link | Ivan Vegner 路 Siddharth N 路 Leonidas Doumas 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
Human-like multiple object tracking through occlusion via gaze-following ( Poster ) > link | Benjamin Peters 路 Eivinas Butkus 路 Nikolaus Kriegeskorte 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
Inverting cognitive models with machine learning to infer preferences from fixations ( Poster ) > link | Evan Russek 路 Frederick Callaway 路 Tom Griffiths 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
Detection of Drowsiness and Impending Microsleep from Eye Movements ( Poster ) > link | Silvia Makowski 路 Paul Prasse 路 Lena A. J盲ger 路 Tobias Scheffer 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
StatTexNet: Evaluating the Importance of Statistical Parameters for Pyramid-Based Texture and Peripheral Vision Models ( Poster ) > link | Christian Koevesdi 路 Vasha DuTell 路 Anne Harrington 路 Mark Hamilton 路 Bill Freeman 路 Ruth Rosenholtz 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
Temporal Understanding of Gaze Communication with GazeTransformer ( Poster ) > link | Ryan Anthony de Belen 路 Gelareh Mohammadi 路 Arcot Sowmya 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
Interaction-aware Dynamic 3D Gaze Estimation in Videos ( Poster ) > link | Chenyi Kuang 路 Jeffrey O Kephart 路 Qiang Ji 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
SuperVision: Self-Supervised Super-Resolution for Appearance-Based Gaze Estimation ( Poster ) > link | Galen O'Shea 路 Majid Komeili 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
An Attention-based Predictive Agent for Handwritten Numeral/Alphabet Recognition via Generation ( Poster ) > link | Bonny Banerjee 路 Murchana Baruah 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
EG-SIF: Improving Appearance Based Gaze Estimation using Self Improving Features ( Poster ) > link | Vasudev Singh 路 Chaitanya Langde 路 Sourav Lakhotia 路 Vignesh Kannan 路 Shuaib Ahmed 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
Planning by Active Sensing ( Poster ) > link | Kaushik Lakshminarasimhan 路 Seren Zhu 路 Dora Angelaki 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
Crafting Good Views of Medical Images for Contrastive Learning via Expert-level Visual Attention ( Poster ) > link | Sheng Wang 路 Zihao Zhao 路 Lichi Zhang 路 Dinggang Shen 路 Qian Wang 馃敆 |
Sat 9:45 a.m. - 11:30 a.m.
|
Memory-Based Sequential Attention ( Poster ) > link | Jason Stock 路 Charles Anderson 馃敆 |
Sat 10:00 a.m. - 11:30 a.m.
|
Lunch Break
|
馃敆 |
Sat 11:30 a.m. - 12:15 p.m.
|
Tim Rolff (Universit盲t Hamburg) - Gazing into the Crystal Ball: Predicting Future Gaze Events in Virtual Reality
(
Invited Talk
)
>
SlidesLive Video |
馃敆 |
Sat 12:15 p.m. - 12:30 p.m.
|
Memory-Based Sequential Attention
(
Oral
)
>
link
SlidesLive Video |
Jason Stock 路 Charles Anderson 馃敆 |
Sat 12:30 p.m. - 12:45 p.m.
|
An Attention-based Predictive Agent for Handwritten Numeral/Alphabet Recognition via Generation
(
Oral
)
>
link
SlidesLive Video |
Bonny Banerjee 路 Murchana Baruah 馃敆 |
Sat 12:45 p.m. - 1:00 p.m.
|
Breakout Session (Instructions)
(
Break out session
)
>
|
馃敆 |
Sat 1:00 p.m. - 1:30 p.m.
|
Coffee Break
|
馃敆 |
Sat 1:00 p.m. - 2:30 p.m.
|
Breakout session
(
Breakout session
)
>
|
馃敆 |
Sat 2:30 p.m. - 2:45 p.m.
|
Sponsors Talk and Award Ceremony
(
Sponsors
)
>
SlidesLive Video |
馃敆 |
Sat 2:45 p.m. - 3:00 p.m.
|
Closing Remarks
(
Closing remarks
)
>
SlidesLive Video |
馃敆 |