Realization of an Inverse Yarbus Process via Hidden Markov Models for Visual-Task Inference
Bibliographic record
Abstract
It has been known for a long time that visual task greatly influences eye movement patterns. Perhaps the best demonstration of this is the celebrated study of Yarbus showing that different eye movement scanpaths emerge depending on the visual. Forward Yarbus process, the effect of visual task on eye movement pattern, has been investigated for various tasks. In this work, we have developed an inverse Yarbus process whereby we can infer the visual task by observing the measurements of a viewer's eye movements while executing the visual task. To do so, first we need to track the allocation of attention, for different tasks entail attending various locations in an image and therefore tracking attention will lead us to task inference. Eye position does not tell the whole story when it comes to tracking attention. While it is well known that there is a strong link between eye movements and attention, the attentional focus is nevertheless frequently well away from the current eye position. Eye tracking methods may be appropriate when the subject is carrying out a task that requires foveation. However, these methods are of little use (and even counter-productive) when the subject is engaged in tasks requiring peripheral vigilance. The model we have developed for attention tracking uses Hidden Markov Models (HMMs), where covert (and overt) attention is represented by the hidden states of task-dependent HMMs. Fixation locations, thus, correspond to the observations of an HMM and were used in training (by using Baum-Welch algorithm) task-dependent models whereby we could evaluate the likelihood of observing an eye trajectory given a task (forward algorithm). Having this likelihood term, we were able to use the Bayesian inference and recognize the ongoing task by viewing the eye movements of subjects while performing a number of simple visual tasks.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".