GazeMoE: Perception of Gaze Target with Mixture-of-Experts

Dimensions overall score 8.0

GitHub Code Pulse

No public code linked for this paper yet.

• GazeMoE is a novel end-to-end framework that selectively leverages gaze-target-related cues from a frozen foundation model through MoE modules.method 70%
• GazeMoE incorporates a class-balancing auxiliary loss and strategic data augmentations to address class imbalance and enhance robustness.method 70%
• GazeMoE achieves state-of-the-art performance on challenging gaze estimation tasks.result 70%
• The model requires fine-tuning for optimal performance.limitation 70%
• The model may not be as effective with low-quality input data.limitation 70%
• GazeMoE uses DINOv2 as a frozen foundation model for feature extraction.technical 70%
• The market for accurate gaze tracking is substantial, including robotics, automotive, retail, and healthcare.market 70%
• GazeMoE demonstrates superior performance in prediction accuracy and robustness in diverse and out-of-distribution visual environments.result 70%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card