FoAViS: Analyzing Learned Fixation Strategies in a Foveated Active Vision System
cs.CV
Submitted: 2026-10-30
Updated: 2026-10-30
Code: https://github.com/ecker-lab/FoAViS
Terminology
Sources
- CanViT: Toward Active-Vision Foundation Models
- Where to Look: A Unified Attention Model for Visual Recognition with Reinforcement Learning
- FoveaTer: Foveated Transformer for Image Classification
- State-of-the-Art in Human Scanpath Prediction
- DINOv3
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs