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

• URL: http://arxiv.org/abs/2603.18343v1
• Date: Wed, 18 Mar 2026 23:01:12 GMT
• Title: VISTA: Validation-Guided Integration of Spatial and Temporal Foundation Models with Anatomical Decoding for Rare-Pathology VCE Event Detection
• Abstract summary: We formulate the RARE-VISION task as a metric-aligned event detection problem instead of a purely frame-wise classification task.<n>Our framework combines two complementary backbones, EndoFM-LV for local temporal context and DINOv3 ViT-L/16 for strong frame-level visual semantics.<n> validation ablations indicate that complementary backbones, validation-guided fusion, and anatomy-aware temporal decoding all contribute to event-level performance.
• Score: 39.50945484737978
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Capsule endoscopy event detection is challenging because diagnostically relevant findings are sparse, visually heterogeneous, and embedded in long, noisy video streams, while evaluation is performed at the event level rather than by frame accuracy alone. We therefore formulate the RARE-VISION task as a metric-aligned event detection problem instead of a purely frame-wise classification task. Our framework combines two complementary backbones, EndoFM-LV for local temporal context and DINOv3 ViT-L/16 for strong frame-level visual semantics, followed by a Diverse Head Ensemble, Validation-Guided Hierarchical Fusion, and Anatomy-Aware Temporal Event Decoding. The fusion stage uses validation-derived class-wise model weighting, backbone weighting, and probability calibration, while the decoding stage applies temporal smoothing, anatomical constraints, threshold refinement, and per-label event generation to produce stable event predictions. Validation ablations indicate that complementary backbones, validation-guided fusion, and anatomy-aware temporal decoding all contribute to event-level performance. On the official hidden test set, the proposed method achieved an overall temporal mAP@0.5 of 0.3530 and temporal mAP@0.95 of 0.3235.

Related papers

• TimeLAVA: Learning-Agnostic Data Valuation for Time Series [48.76711740818533]
  TimeLAVA is a learning-agnostic framework that values temporal segments by their marginal contribution to minimize distributional discrepancy between evaluated and reference data.<n>We provide theoretical guarantees linking valuation to model-agnostic generalization and prove bounded sensitivity to contamination.
  arXiv  Detail & Related papers  (2026-06-17T06:16:16Z)
• VISTA: Validation-Guided Integration of Spatial and Temporal Foundation Models with Anatomical Decoding for Rare-Pathology VCE Event Detection -- after competition results [9.248504942839382]
  We propose VISTA, a metric-aligned multi-backbone framework for the RAREVISION task.<n>The original official submission achieved hidden-test temporal mAP@0.5 of 0.3530 and mAP@0.95 of 0.3235.<n>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.
  arXiv  Detail & Related papers  (2026-05-21T07:35:02Z)
• Rethinking Event-Based Object Dtection through Representation-Level Temporal Aggregation and Model-Level Hypergraph Reasoning [65.08890312027314]
  Event cameras provide microsecond-level temporal resolution, low latency, and high dynamic range.<n>Event Dual Temporal-Relational Aggregation Detector (Ev-DTAD) integrates representation-level temporal encoding with model-level temporal-hypergraph reasoning.<n>We show that Ev-DTAD achieves a competitive accuracy-efficiency trade-off, validating the complementarity between compact temporal representation and temporal-hypergraph feature reasoning.
  arXiv  Detail & Related papers  (2026-05-09T09:20:34Z)
• ConvFormer3D-TAP: Phase/Uncertainty-Aware Front-End Fusion for Cine CMR View Classification Pipelines [0.879504058268139]
  ConvFormer3D-TAP integrates 3D convolutional tokenization with multiscale self-attention to enhance robustness across cardiac phases and ambiguous temporal segments.<n>On a cohort of 150,974 clinically acquired cine sequences, ConvFormer3D- achieved 96% validation accuracy with per-class F1-scores.<n>These results support ConvFormer3DTAP as a scalable front-end for view routing, filtering and quality control in end-to-end cMRI.
  arXiv  Detail & Related papers  (2026-04-13T12:29:16Z)
• From Frames to Events: Rethinking Evaluation in Human-Centric Video Anomaly Detection [9.404376027901277]
  Pose-based Video Anomaly Detection (VAD) has gained significant attention for its privacy-preserving nature and robustness to environmental variations.<n>Traditional frame-level evaluations treat video as a collection of isolated frames, fundamentally misaligned with how anomalies manifest and are acted upon in the real world.<n>We introduce two strategies for temporal event localization: a score-refinement pipeline with hierarchical Gaussian smoothing and adaptive binarization, and an end-to-end Dual-Branch Model that directly generates event-level detections.
  arXiv  Detail & Related papers  (2026-04-10T13:52:18Z)
• Benchmarking LLM Summaries of Multimodal Clinical Time Series for Remote Monitoring [6.415950855665798]
  Large language models (LLMs) can generate fluent clinical summaries of remote therapeutic monitoring time series.<n> Existing evaluation metrics primarily focus on semantic similarity and linguistic quality, leaving event-level correctness largely unmeasured.<n>We introduce an event-based evaluation framework for multimodal time-series summarization using the Technology-Integrated Health Management (TIHM)-1.5 dementia monitoring dataset.
  arXiv  Detail & Related papers  (2026-03-02T07:33:11Z)
• LEFT: Learnable Fusion of Tri-view Tokens for Unsupervised Time Series Anomaly Detection [53.191369031661885]
  Unsupervised time series anomaly detection aims to build a model for identifying abnormal timestamps without assuming the availability of annotations.<n>We present Learnable Fusion of Tri-view Tokens (LEFT), a unified unsupervised TSAD framework that models anomalies as inconsistencies across complementary representations.<n>Experiments on real-world benchmarks show that LEFT yields the best detection accuracy against SOTA baselines, while achieving a 5x reduction on FLOPs and 8x speed-up for training.
  arXiv  Detail & Related papers  (2026-02-09T13:33:49Z)
• E.M.Ground: A Temporal Grounding Vid-LLM with Holistic Event Perception and Matching [87.38371267983263]
  Temporal Video Grounding aims to precisely localize time segments corresponding to query events.<n>E.M.Ground is a novel Vid-LLM for TVG that focuses on holistic and coherent event perception.<n>E.M.Ground consistently outperforms state-of-the-art Vid-LLMs by significant margins.
  arXiv  Detail & Related papers  (2026-02-05T02:16:00Z)
• TARDis: Time Attenuated Representation Disentanglement for Incomplete Multi-Modal Tumor Segmentation and Classification [10.329406702659123]
  Tumor segmentation and diagnosis in contrast-enhanced Computed Tomography (CT) rely heavily on the physiological dynamics of contrast agents.<n>Existing deep learning approaches typically treat missing phases as absent independent channels, ignoring the inherent temporal continuity of hemodynamics.<n>We propose Time Attenuated Representation Disentanglement (TARDis), a novel physics-aware framework that redefines missing modalities as missing sample points on a continuous Time-Attenuation Curve.
  arXiv  Detail & Related papers  (2025-12-04T08:44:50Z)
• BayesTTA: Continual-Temporal Test-Time Adaptation for Vision-Language Models via Gaussian Discriminant Analysis [41.09181390655176]
  Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but degrade significantly under textittemporally evolving distribution shifts common in real-world scenarios.<n>We formalize this practical problem as textitContinual-Temporal Test-Time Adaptation (CT-TTA), where test distributions evolve gradually over time.<n>We propose textitBayesTTA, a Bayesian adaptation framework that enforces temporally consistent predictions and dynamically aligns visual representations.
  arXiv  Detail & Related papers  (2025-07-11T14:02:54Z)
• Q-PART: Quasi-Periodic Adaptive Regression with Test-time Training for Pediatric Left Ventricular Ejection Fraction Regression [45.69922532213079]
  We address the challenge of adaptive pediatric Left Ventricular Ejection Fraction (LVEF) assessment.<n>We propose a novel textbfQuasi-textbfPeriodic textbfAdaptive textbfRegression with textbfTest-time Training (Q-PART) framework.
  arXiv  Detail & Related papers  (2025-03-06T06:24:51Z)
• Periodontal Bone Loss Analysis via Keypoint Detection With Heuristic Post-Processing [1.918319133902462]
  This study proposes a deep learning framework and annotation methodology for the automatic detection of periodontal bone loss landmarks, associated conditions, and staging.<n>192 periapical domains were collected and annotated with a stage PRC methodology, labelling relevant landmarks regardless of disease presence or extent.<n>We propose a post-processing module that aligns keypoints to tooth boundaries using an auxiliary instance segmentation model.
  arXiv  Detail & Related papers  (2025-03-05T00:34:29Z)
• Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach [49.995833831087175]
  This work proposes a novel method for generating generic Video-temporal PAs by inpainting a masked out region of an image. In addition, we present a simple unified framework to detect real-world anomalies under the OCC setting. Our method performs on par with other existing state-of-the-art PAs generation and reconstruction based methods under the OCC setting.
  arXiv  Detail & Related papers  (2023-11-27T13:14:06Z)
• Abnormal Event Detection via Hypergraph Contrastive Learning [54.80429341415227]
  Abnormal event detection plays an important role in many real applications. In this paper, we study the unsupervised abnormal event detection problem in Attributed Heterogeneous Information Network. A novel hypergraph contrastive learning method, named AEHCL, is proposed to fully capture abnormal event patterns.
  arXiv  Detail & Related papers  (2023-04-02T08:23:20Z)

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.