Why We Look Where We Look: Emergent Human-like Fixations of a Foveated Visual Language Model Maximizing Scene Understanding

• URL: http://arxiv.org/abs/2605.17823v1
• Date: Mon, 18 May 2026 03:55:28 GMT
• Title: Why We Look Where We Look: Emergent Human-like Fixations of a Foveated Visual Language Model Maximizing Scene Understanding
• Abstract summary: We show that a computational agent with simulated foveation, trained to optimize scene comprehension, exhibits emergent human fixation signature patterns.<n>Human free-viewing fixation patterns may emerge as a functional byproduct of optimizing scene comprehension under the biological constraints of foveated vision.
• Score: 3.6425317770998125
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When humans view scenes without a specific task (free-viewing), they initially direct their eye movements toward the scene center and then fixate on people, text, objects being gazed at or grasped, and semantically meaningful regions. What these signature fixation patterns reflect and whether they optimize an underlying perceptual task remain unknown. We show that a computational agent with simulated foveation, trained to optimize scene comprehension, exhibits emergent human fixation signature patterns. In contrast, versions of the agent trained to search or classify scenes, or equipped with peripheral vision that was better or worse than human vision, predicted human fixation patterns less accurately. Thus, human free-viewing fixation patterns may emerge as a functional byproduct of optimizing scene comprehension under the biological constraints of foveated vision.

Related papers

• Personalized Image Descriptions from Attention Sequences [55.65023709100682]
  People can view the same image differently: they focus on different regions, objects, and details in varying orders and describe them in distinct linguistic styles.<n>Existing models for personalized image description focus on linguistic style alone, with no prior work leveraging individual viewing patterns.<n>We address this gap by explicitly modeling personalized viewing behavior as a core factor in description generation.<n>Our method, DEPER, learns a subject embedding that captures both linguistic style and viewing behavior, guided by an auxiliary attention-prediction task. A lightweight adapter aligns these embeddings with a frozen vision-language model, enabling few-shot personalization without retraining.
  arXiv  Detail & Related papers  (2025-12-07T05:23:18Z)
• Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models [51.58859621164201]
  We introduce visual stimuli and human judgments on visual cognition tasks to evaluate performance across cognitive domains.<n>We fine-tune models on ground truth data for intuitive physics and causal reasoning.<n>We find that task-specific fine-tuning does not contribute to robust human-like generalization to data with other visual characteristics.
  arXiv  Detail & Related papers  (2025-02-21T18:58:30Z)
• Human Gaze Boosts Object-Centered Representation Learning [7.473473243713322]
  Recent self-supervised learning models trained on human-like egocentric visual inputs substantially underperform on image recognition tasks compared to humans.<n>Here, we investigate whether focusing on central visual information boosts egocentric visual object learning.<n>Our experiments demonstrate that focusing on central vision leads to better object-centered representations.
  arXiv  Detail & Related papers  (2025-01-06T12:21:40Z)
• When Does Perceptual Alignment Benefit Vision Representations? [76.32336818860965]
  We investigate how aligning vision model representations to human perceptual judgments impacts their usability. We find that aligning models to perceptual judgments yields representations that improve upon the original backbones across many downstream tasks. Our results suggest that injecting an inductive bias about human perceptual knowledge into vision models can contribute to better representations.
  arXiv  Detail & Related papers  (2024-10-14T17:59:58Z)
• Text2Place: Affordance-aware Text Guided Human Placement [26.041917073228483]
  This work tackles the problem of realistic human insertion in a given background scene termed as textbfSemantic Human Placement. For learning semantic masks, we leverage rich object-scene priors learned from the text-to-image generative models. The proposed method can generate highly realistic scene compositions while preserving the background and subject identity.
  arXiv  Detail & Related papers  (2024-07-22T08:00:06Z)
• Self-supervised video pretraining yields robust and more human-aligned visual representations [14.599429594703539]
  General representations far outperform prior video pretraining methods on image understanding tasks.<n>VITO representations are significantly more robust to natural and synthetic deformations than image-, video-, and adversarially-trained ones.<n>These results suggest that video pretraining could be a simple way of learning unified, robust, and human-aligned representations of the visual world.
  arXiv  Detail & Related papers  (2022-10-12T17:30:12Z)
• GIMO: Gaze-Informed Human Motion Prediction in Context [75.52839760700833]
  We propose a large-scale human motion dataset that delivers high-quality body pose sequences, scene scans, and ego-centric views with eye gaze. Our data collection is not tied to specific scenes, which further boosts the motion dynamics observed from our subjects. To realize the full potential of gaze, we propose a novel network architecture that enables bidirectional communication between the gaze and motion branches.
  arXiv  Detail & Related papers  (2022-04-20T13:17:39Z)
• Pose-Guided Human Animation from a Single Image in the Wild [83.86903892201656]
  We present a new pose transfer method for synthesizing a human animation from a single image of a person controlled by a sequence of body poses. Existing pose transfer methods exhibit significant visual artifacts when applying to a novel scene. We design a compositional neural network that predicts the silhouette, garment labels, and textures. We are able to synthesize human animations that can preserve the identity and appearance of the person in a temporally coherent way without any fine-tuning of the network on the testing scene.
  arXiv  Detail & Related papers  (2020-12-07T15:38:29Z)
• VisualEchoes: Spatial Image Representation Learning through Echolocation [97.23789910400387]
  Several animal species (e.g., bats, dolphins, and whales) and even visually impaired humans have the remarkable ability to perform echolocation. We propose a novel interaction-based representation learning framework that learns useful visual features via echolocation. Our work opens a new path for representation learning for embodied agents, where supervision comes from interacting with the physical world.
  arXiv  Detail & Related papers  (2020-05-04T16:16:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.