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

arXiv: https://arxiv.org/abs/2605.31115 · HTML: https://mlsanity.com/paper/2605.31115/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 49 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [Expanding Language-Image Pretrained Models for General Video Recognition](https://mlsanity.com/paper/2208.02816/) (2022)
- [ActionCLIP: A New Paradigm for Video Action Recognition](https://mlsanity.com/paper/2109.08472/) (2021)
- [ASFormer: Transformer for Action Segmentation](https://mlsanity.com/paper/2110.08568/) (2021)
- [Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks](https://mlsanity.com/paper/1912.09930/) (2019)
- [Diffusion Action Segmentation](https://mlsanity.com/paper/2303.17959/) (2023)
- [How Much Temporal Long-Term Context is Needed for Action Segmentation?](https://mlsanity.com/paper/2308.11358/) (2023)
- [Temporal Relational Modeling with Self-Supervision for Action Segmentation](https://mlsanity.com/paper/2012.07508/) (2020)
- [Robot Cooking with Stir-fry: Bimanual Non-prehensile Manipulation of Semi-fluid Objects](https://mlsanity.com/paper/2205.05960/) (2022)
- [C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentation](https://mlsanity.com/paper/2212.11078/) (2022)
- [HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding](https://mlsanity.com/paper/2307.05721/) (2023)
- [ATTACH Dataset: Annotated Two-Handed Assembly Actions for Human Action Understanding](https://mlsanity.com/paper/2304.08210/) (2023)
- [Aligning AI with Public Values: Deliberation and Decision-Making for Governing Multimodal LLMs in Political Video Analysis](https://mlsanity.com/paper/2410.01817/) (2024)
- [Disentangled Action Recognition with Knowledge Bases](https://mlsanity.com/paper/2207.01708/) (2022)

## Built on by (most cited first, 1 of 1)

- [Lag-aware cross-hand alignment for dual-hand action segmentation](https://mlsanity.com/paper/2607.26215/) (2026)

## Abstract (arXiv)

Dual-hand action segmentation, densely predicting actions for both hands from untrimmed videos, is essential for understanding complex bimanual activities. However, it poses several unique challenges: complex inter-hand dependencies, visual asymmetry between hands, representation conflicts where the dominant hand monopolizes gradients, and semantic ambiguity in fine-grained actions. We propose Polyphony, a three-stage method to address these challenges through: (1) an Alternating Dual-Hand Vision Transformer that alternates training between left- and right-hand mini-batches to ensure balanced gradient contributions from both hands while sharing a spatio-temporal encoder; (2) Semantic Feature Conditioning that aligns visual features with structured, compositional action descriptions to enhance discrimination of semantically similar actions; and (3) Diffusion-Based Segmentation with cross-hand feature fusion for inter-hand coordination and adaptive loss weighting for balancing performance. Polyphony achieves state-of-the-art on both dual-hand datasets (HA-ViD, ATTACH) with improvements up to 16.8 points, and on the single-stream Breakfast dataset (82.5%), outperforming the prior best method that uses a 12x larger backbone. Notably, our unified model with a single shared backbone surpasses baselines requiring separate per-hand models. Code is at https://github.com/x-labs-xyz/Polyphony-Dual-hand-Action-Segmentation.