AI Paper Atlas

Research map / 3D vision / Human pose estimation

A Dual-Transformer Architecture with Cross-Attention for Multi-Camera View Recommendation

Josep Cabacas Maso, Carles Ventura, Ismael Benito-Altamirano

ECCV 2026 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add focal loss in place of BCE (ablation)Dual-Transformer (SwinV1) · TVMCEPrecision@0.5 (%): 52.60 -> 56.60Improved
decouple history and candidates with dual-transformer cross-attention vs single transformer (BCE + SwinV1)Single Transformer re-impl. · TVMCEPrecision@0.5 (%): 47.97 -> 52.60Improved
decouple history and candidates vs single transformer (BCE + SwinV2)Single Transformer re-impl. · TVMCEPrecision@0.5 (%): 54.06 -> 69.65Improved
replace SwinV1 backbone with SwinV2 (ablation)Dual-Transformer (Focal) · TVMCEPrecision@0.5 (%): 56.60 -> 69.65Improved
replace SwinV2 with MaxViT-Tiny backbone (ablation)Dual-Transformer (Focal) · TVMCEPrecision@0.5 (%): 69.65 -> 58.63Hurt
replace SwinV2 with ViT-Base backbone (ablation)Dual-Transformer (Focal) · TVMCEPrecision@0.5 (%): 69.65 -> 25.85Hurt
replace SwinV2 with ConvNeXtV2-Tiny backbone (ablation)Dual-Transformer (Focal) · TVMCEPrecision@0.5 (%): 69.65 -> 56.23Hurt
replace SwinV2 with ResNet-50 backbone (ablation)Dual-Transformer (Focal) · TVMCEPrecision@0.5 (%): 69.65 -> 46.74Hurt
lower decision threshold from 0.5 to 0.3Dual-Transformer (SwinV2, Focal) · TVMCE validation (macro)F1 (%): 74.53 -> 81.41Improved
fine-tune on 20% of target video vs zero-shotDual-Transformer · video_0000Precision@0.5 (%): 74.44 -> 83.65Improved
fine-tune on 30% of target video vs zero-shotDual-Transformer · video_0000Precision@0.5 (%): 74.44 -> 90.41Improved
fine-tune on 10% of video_0001 vs zero-shotDual-Transformer · video_0001Precision@0.5 (%): 81.76 -> 77.06Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy