# VISTA: Validation-Guided Integration of Spatial and Temporal Foundation Models with Anatomical Decoding for Rare-Pathology VCE Event Detection -- after competition results

arXiv: https://arxiv.org/abs/2605.22096 · HTML: https://mlsanity.com/paper/2605.22096/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 9 references that are in the map.
- First posted on arXiv 21 May 2026.

## Builds on (most cited first, 3 of 3)

- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Robust Asymmetric Loss for Multi-Label Long-Tailed Learning](https://mlsanity.com/paper/2308.05542/) (2023)
- [Taming Domain Shift in Multi-source CT-Scan Classification via Input-Space Standardization](https://mlsanity.com/paper/2507.19858/) (2025)

## Abstract (arXiv)

Capsule endoscopy event detection is challenging because clinically relevant findings are sparse, visually heterogeneous, and evaluated at the event level rather than by frame accuracy. We propose VISTA, a metric-aligned multi-backbone framework for the RAREVISION task. VISTA combines EndoFM-LV for temporal context and DINOv3 ViTL/16 for frame-level visual semantics, followed by a Diverse Head Ensemble (DHE), Validation-Guided Weighted Fusion (VGWF), and Anatomy-Aware Temporal Event Decoding (ATED). The original official submission achieved hidden-test temporal mAP@0.5 of 0.3530 and mAP@0.95 of 0.3235. After the competition, extending local threshold refinement with a global coarse search improved performance to 0.3726 mAP@0.5 and 0.3431 mAP@0.95, ranking Team ACVLab second in the post-competition evaluation.