About

The "Gaze Meets Computer Vision (GMCV): Bridging Human Attention and Machine Perception" workshop explores the integration of eye-tracking technology and computer vision. It focuses on how gaze data can improve visual understanding, enhance human-computer interaction, and support applied computer vision tasks. Building on two successful editions at NeurIPS, the workshop will highlight advancements in combining eye gaze with AI, with applications in AR/VR, scene understanding, and attention modeling. It aims to bring together researchers and industry experts to discuss challenges, opportunities, and future directions in gaze-assisted computer vision. The workshop fosters innovation at the intersection of human cognition and machine perception through panels, presentations, and cross-disciplinary collaborations.

👉 Call for papers

👉 Important dates

Confirmed Invited Speakers

Enkelejda Kasneci
(Technische Universität München)

Ulas Bagci
(Northwestern University)

Ipek Oruç
(University of British Columbia)

Shuaib Ahmed
(Mercedes-Benz Research and Development India )

Schedule

08:00 - 08:15
Opening remarks

08:15 - 08:40
Keynote 1: Prof. Enkelejda Kasneci
08:40 - 09:05
Keynote 2: Prof. Ulas Bagci
09:05 - 09:45
Paper presentations (4x10min)
- FlatTrack: Eye-tracking with ultra-thin lensless cameras - Purvam Jain et al.
- Causal Representation-Based Domain Generalization on Gaze Estimation - Younghan Kim et al.
- SIGN: A Statistically-Informed Gaze Network for Gaze Time Prediction - Jianping Ye et el.
- On Segmenting Pupil Contours in Terms of Elliptical Fourier Series - Felix O'Mahony et el.
09:45 - 10.00
Coffee break
10:00 - 10:25
Keynote 3: Prof. Ipek Oruç
10:25 - 10:50
Keynote 4: Dr. Shuaib Ahmed
10:50 - 11:30
Paper presentations (4x10min)
- Human Gaze Improves Vision Transformers by Token Masking - Jacqueline Kockwelp et al.
- Comparative Analysis of 2D and 3D Visualization on Cognitive Workload and Performance in Surgical Peg Transfer Task Using Eye-Tracking Data - Ruoshan Lan et al.
- Addressing Age Bias in the Application of Appearance-Based Gaze-Tracking for Older Adults - Manuela Kunz et al.
- VISTA: A Visual and Textual Attention Dataset for Interpreting Multimodal Models - Fnu Harshit et al.
11:30 - 12:00
Sponsors presentation, Awards ceremony, Closing remarks