# NeuralWarp: Time-Series Similarity with Warping Networks

arXiv: https://arxiv.org/abs/1812.08306 · HTML: https://mlsanity.com/paper/1812.08306/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2018.

## Built on by (most cited first, 13 of 13)

- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [Quadratic Gaussian Splatting: High Quality Surface Reconstruction with Second-order Geometric Primitives](https://mlsanity.com/paper/2411.16392/) (2024)
- [Towards Similarity-Aware Time-Series Classification](https://mlsanity.com/paper/2201.01413/) (2022)
- [Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths](https://mlsanity.com/paper/2303.10778/) (2023)
- [NeRF-Det++: Incorporating Semantic Cues and Perspective-aware Depth Supervision for Indoor Multi-View 3D Detection](https://mlsanity.com/paper/2402.14464/) (2024)
- [Attention to Warp: Deep Metric Learning for Multivariate Time Series](https://mlsanity.com/paper/2103.15074/) (2021)
- [PSEUDo: Interactive Pattern Search in Multivariate Time Series with Locality-Sensitive Hashing and Relevance Feedback](https://mlsanity.com/paper/2104.14962/) (2021)
- [Deep Attentive Time Warping](https://mlsanity.com/paper/2309.06720/) (2023)
- [Full-Reference Speech Quality Estimation with Attentional Siamese Neural Networks](https://mlsanity.com/paper/2105.00783/) (2021)
- [Temporal Alignment Prediction for Few-Shot Video Classification](https://mlsanity.com/paper/2107.11960/) (2021)
- [Time Elastic Neural Networks](https://mlsanity.com/paper/2405.17516/) (2024)
- [Deep Time Warping for Multiple Time Series Alignment](https://mlsanity.com/paper/2502.16324/) (2025)
- [Contrastive Learning for Correlating Network Incidents](https://mlsanity.com/paper/2509.24446/) (2025)

## Abstract (arXiv)

Research on time-series similarity measures has emphasized the need for elastic methods which align the indices of pairs of time series and a plethora of non-parametric have been proposed for the task. On the other hand, deep learning approaches are dominant in closely related domains, such as learning image and text sentence similarity. In this paper, we propose textitNeuralWarp, a novel measure that models the alignment of time-series indices in a deep representation space, by modeling a warping function as an upper level neural network between deeply-encoded time series values. Experimental results demonstrate that textitNeuralWarp outperforms both non-parametric and un-warped deep models on a range of diverse real-life datasets.