# SSVEP-028: Cross-subject dual-domain fusion network with task-related and task-discriminant component analysis enhancing one-shot SSVEP classification

> Generated from a local paper card. Do not edit this page directly; edit the source card and rerun `vp run docs:generate`.

> Internal wiki boundary: paper-card evidence and user-provided PDF downloads are available for private reading. Extracted full-paper text is not published.

> Source: `library/paper_cards/SSVEP-028.md`

## Paper Access

* Internal PDF: <a href={"/papers/SSVEP-028.pdf"} download style={{ display: "inline-flex", alignItems: "center", justifyContent: "center", minHeight: "2.25rem", padding: "0.45rem 0.8rem", borderRadius: "6px", backgroundColor: "#047857", color: "#ffffff", fontWeight: 700, lineHeight: 1, textDecoration: "none", boxShadow: "0 1px 2px rgba(15, 23, 42, 0.22)" }}>Download Paper</a>
* DOI / official page: [needs confirmation](https://arxiv.org/abs/2311.07932)
* Open-access page: [Open access page](https://arxiv.org/abs/2311.07932)
* Deployment boundary: these PDF links are intended only for a private/protected internal wiki.

## SSVEP-028: Cross-subject dual-domain fusion network with task-related and task-discriminant component analysis enhancing one-shot SSVEP classification

## Metadata

* ID: SSVEP-028
* Title: Cross-subject dual-domain fusion network with task-related and task-discriminant component analysis enhancing one-shot SSVEP classification
* Year: 2023
* DOI / URL: https://arxiv.org/abs/2311.07932
* Local PDF: see Paper Access section above
* Text artifact: local-only path withheld from docs site
* Review status: `extracted`

## Study Type

* Track: SSVEP
* Task: one-shot cross-subject SSVEP classification
* Participants or dataset: three public SSVEP datasets: UCSD, Benchmark, and BETA
* Device/electrode setup: public dataset montages vary; exact channels should be extracted per dataset if cited
* Protocol/task: limited calibration, one labeled calibration trial per target

## Methods

* Signal processing or analysis: cross-subject dual-domain fusion network with TRCA and TDCA components
* Training/calibration: transfers information from source subjects with one-shot target-subject calibration
* Comparators: knowledge-driven and data-driven baselines

## Key Results

* The abstract reports best performance on two datasets and competitive performance on another.
* The paper explicitly frames the challenge as extreme calibration scarcity.

## Limitations

* arXiv/preprint status; published version needs confirmation.
* Results are offline on public datasets.
* Does not test detector-bound dynamic stimuli.

## Relevance To Current Review

* Useful for the recent trend: cross-subject, low-calibration SSVEP.
* Could guide later Exp1/Exp4 work if the project collects only a small calibration set.

## Evidence Status

| Claim | Status | Evidence Note |
| --- | --- | --- |
| One-shot SSVEP classification is an active recent problem. | verified | Abstract defines the one-calibration-per-target scenario. |
| TRCA/TDCA components are being combined with neural models for transfer. | verified | Methods describe TRCA and TDCA within the fusion network. |
| This model is ready for online SAH-BRI-Grasp use. | needs confirmation | No online grasping or dynamic overlay evidence. |

## Open Questions

* Is one-shot calibration enough for per-object dynamic targets or only per-frequency targets?
* Can TRCA/TDCA assumptions hold when targets move or are resized?