AI Paper Atlas

Research map / Video / Action recognition

Polyphony: Diffusion-based Dual-Hand Action Segmentation with Alternating Vision Transformer and Semantic Conditioning

Hao Zheng, Hu Wang, Tiantian Zheng, Prajjwal Bhattarai, Tuka Alhanai

CVPR 2026 · Video › Action recognition · approach: Temporal action segmentation · 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 cross-hand feature fusion (ablation)Polyphony · HA-ViD LHaccuracy: 55.5 -> 57.1Improved
add cross-hand feature fusion (ablation)Polyphony · HA-ViD RHaccuracy: 59.5 -> 60.6Improved
add adaptive loss weighting on top of feature fusion (ablation)Polyphony · HA-ViD LHaccuracy: 55.3 -> 55.5Improved
add action (classification logit) features to motion features (ablation)Polyphony · HA-ViD LHaccuracy: 56.0 -> 55.8No clear effect
add action (classification logit) features to motion features (ablation)Polyphony · HA-ViD RHaccuracy: 58.0 -> 58.3No clear effect
add semantic features (ablation)Polyphony · HA-ViD RHaccuracy: 58.3 -> 60.6Improved
add semantic features (ablation)Polyphony · HA-ViD LHaccuracy: 55.8 -> 57.1Improved
use alternating instead of joint training (ablation)Polyphony ADH-ViT · HA-ViD side-view segmentation LHaccuracy: 53.0 -> 56.9Improved
use alternating instead of joint training (ablation)Polyphony ADH-ViT · HA-ViD side-view segmentation RHaccuracy: 55.4 -> 55.7Improved
add random clip sampling to segment-based sampling (ablation)ADH-ViT · HA-ViD action recognition LHtop-1 accuracy: 47.0 -> 60.1Improved
use structured compositional descriptions instead of naive (ablation)MiniLM-L6 semantic conditioning · HA-ViD side-viewaccuracy: 55.0 -> 57.4Improved
use larger language model for semantic embedding (BGE-large vs MiniLM-L6) (ablation)Polyphony · HA-ViD side-viewaccuracy: 57.4 -> 56.6Hurt

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