GALAR-TemporalNet v2: Anatomy-Guided Dual-Branch Temporal Classification with Bidirectional Mamba and Dual-Graph GCN for Video Capsule Endoscopy -- after competition results
On the map: State-space sequence models (S4, Mamba) → Mamba for medical image analysis
Abstract (arXiv)
Video Capsule Endoscopy (VCE) poses a challenging multi-label temporal classification problem, requiring simultaneous localization of 8 anatomical regions and detection of 9 pathological findings across tens of thousands of frames. We present GALAR-TemporalNet v2, a hierarchical temporal model that addresses three core challenges: extreme class imbalance, long-range temporal dependencies, and pathology--anatomy entanglement. Our architecture combines windowed self-attention for local modeling, a Dual-Graph GCN for global frame relationships, and Bidirectional Mamba for selective boundary context encoding. A novel anatomy prototype residual pathway decouples pathological deviation signals from normal organ appearance, and a frame-level GCN skip connection stabilizes training of visually confusable rare classes. The competition version, GALAR-TemporalNet, achieved an overall [email protected] of 0.2644 and [email protected] of 0.2353 on the RARE-VISION test set. Following the competition, the redesigned GALAR-TemporalNet v2 -- incorporating a restructured pathology branch, refined loss functions, and extended post-processing -- improved these results to [email protected] of 0.3409 and [email protected] of 0.3333.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Mamba for medical image analysis, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 0 of its 3 references that are in the map. First posted on arXiv 21 May 2026.
Builds on
0 of 3 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Anatomy-Guided Vision-Language Learning with Angular Prototype Separation for Multi-Label Video Capsule Endoscopy Classification Under Class Imbalance
- 2025EndoMamba: An Efficient Foundation Model for Endoscopic Videos via Hierarchical Pre-training
- 2026EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive Alignment
- 2026Representation-driven Endoscopic Visual Embedding Alignment for Latent Generation
- 2023Semantic Map Guided Synthesis of Wireless Capsule Endoscopy Images using Diffusion Models
- 2026CapCLIP: A Vision-Language Representation Alignment Approach for Wireless Capsule Endoscopy Analysis
- 2026LUX: A Lesion-Aware Graph-Conditioned Visual - Language Architecture for Explainable Endoscopic Captioning
- 2026Disentangled Anatomy-Disease Diffusion (DADD) for Controllable Ulcerative Colitis Progression Synthesis