Multiscale Manifold Warping

• URL: http://arxiv.org/abs/2109.09222v1
• Date: Sun, 19 Sep 2021 21:00:23 GMT
• Title: Multiscale Manifold Warping
• Authors: Sridhar Mahadevan, Anup Rao, Georgios Theocharous and Jennifer Healey
• Abstract summary: We show that exploiting the multiscale manifold latent structure of real-world data can yield improved alignment. We introduce a novel framework called Warping on Wavelets (WOW) that integrates DTW with a a multi-scale manifold learning framework.
• Score: 28.628750841401
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many real-world applications require aligning two temporal sequences, including bioinformatics, handwriting recognition, activity recognition, and human-robot coordination. Dynamic Time Warping (DTW) is a popular alignment method, but can fail on high-dimensional real-world data where the dimensions of aligned sequences are often unequal. In this paper, we show that exploiting the multiscale manifold latent structure of real-world data can yield improved alignment. We introduce a novel framework called Warping on Wavelets (WOW) that integrates DTW with a a multi-scale manifold learning framework called Diffusion Wavelets. We present a theoretical analysis of the WOW family of algorithms and show that it outperforms previous state of the art methods, such as canonical time warping (CTW) and manifold warping, on several real-world datasets.

Related papers

• Riemannian Time Warping: Multiple Sequence Alignment in Curved Spaces [5.777642571856656]
  Temporal alignment of multiple signals through time warping is crucial in many fields, such as speech recognition or robot motion learning.<n>We introduce a novel approach efficiently aligning multiple signals by considering the geometric structure of the Riemannian manifold in which the data is embedded.<n>Experiments on synthetic and real-world data, including tests with an LBR iiwa robot, demonstrate that RTW consistently outperforms state-of-the-art baselines in both averaging and classification tasks.
  arXiv  Detail & Related papers  (2025-06-02T13:12:02Z)
• T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Models [51.08566687549047]
  We introduce Text-to-Series (T2S), a diffusion-based framework that bridges the gap between natural language and time series.<n>T2S employs a length-adaptive variational autoencoder to encode time series of varying lengths into consistent latent embeddings.<n>We train T2S in an interleaved paradigm across multiple lengths, allowing it to generate sequences of any desired length.
  arXiv  Detail & Related papers  (2025-05-05T07:22:54Z)
• Deep Time Warping for Multiple Time Series Alignment [0.0]
  Time Series Alignment is a critical task in signal processing with numerous real-world applications. This paper introduces a novel approach for Multiple Time Series Alignment leveraging Deep Learning techniques.
  arXiv  Detail & Related papers  (2025-02-22T18:55:51Z)
• TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation [47.58016750718323]
  We propose TimeDART, a novel self-supervised time series pre-training framework. TimeDART unifies two powerful generative paradigms to learn more transferable representations. We conduct extensive experiments on public datasets for time series forecasting and classification.
  arXiv  Detail & Related papers  (2024-10-08T06:08:33Z)
• DRFormer: Multi-Scale Transformer Utilizing Diverse Receptive Fields for Long Time-Series Forecasting [3.420673126033772]
  We propose a dynamic tokenizer with a dynamic sparse learning algorithm to capture diverse receptive fields and sparse patterns of time series data. Our proposed model, named DRFormer, is evaluated on various real-world datasets, and experimental results demonstrate its superiority compared to existing methods.
  arXiv  Detail & Related papers  (2024-08-05T07:26:47Z)
• Generalizable Implicit Neural Representation As a Universal Spatiotemporal Traffic Data Learner [46.866240648471894]
  Spatiotemporal Traffic Data (STTD) measures the complex dynamical behaviors of the multiscale transportation system. We present a novel paradigm to address the STTD learning problem by parameterizing STTD as an implicit neural representation. We validate its effectiveness through extensive experiments in real-world scenarios, showcasing applications from corridor to network scales.
  arXiv  Detail & Related papers  (2024-06-13T02:03:22Z)
• Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective [63.60312929416228]
  textbftextitAttraos incorporates chaos theory into long-term time series forecasting. We show that Attraos outperforms various LTSF methods on mainstream datasets and chaotic datasets with only one-twelfth of the parameters compared to PatchTST.
  arXiv  Detail & Related papers  (2024-02-18T05:35:01Z)
• Self-supervised novel 2D view synthesis of large-scale scenes with efficient multi-scale voxel carving [77.07589573960436]
  We introduce an efficient multi-scale voxel carving method to generate novel views of real scenes. Our final high-resolution output is efficiently self-trained on data automatically generated by the voxel carving module. We demonstrate the effectiveness of our method on highly complex and large-scale scenes in real environments.
  arXiv  Detail & Related papers  (2023-06-26T13:57:05Z)
• Gait Recognition in the Wild with Multi-hop Temporal Switch [81.35245014397759]
  gait recognition in the wild is a more practical problem that has attracted the attention of the community of multimedia and computer vision. This paper presents a novel multi-hop temporal switch method to achieve effective temporal modeling of gait patterns in real-world scenes.
  arXiv  Detail & Related papers  (2022-09-01T10:46:09Z)
• Dynamic Time Warping based Adversarial Framework for Time-Series Domain [32.45387153404849]
  We propose a novel framework for the time-series domain referred as Dynamic Time Warping for Adrial Robustness (DTW-AR) We develop a principled algorithm justified by theoretical analysis to efficiently create diverse adversarial examples using random alignment paths. Experiments on diverse real-world benchmarks show the effectiveness of DTW-AR to fool DNNs for time-series data and to improve their robustness using adversarial training.
  arXiv  Detail & Related papers  (2022-07-09T17:23:00Z)
• MD-CSDNetwork: Multi-Domain Cross Stitched Network for Deepfake Detection [80.83725644958633]
  Current deepfake generation methods leave discriminative artifacts in the frequency spectrum of fake images and videos. We present a novel approach, termed as MD-CSDNetwork, for combining the features in the spatial and frequency domains to mine a shared discriminative representation.
  arXiv  Detail & Related papers  (2021-09-15T14:11:53Z)
• Matrix Profile XXII: Exact Discovery of Time Series Motifs under DTW [1.282368486390644]
  We present the first scalable exact method to discover time series motifs under Dynamic Time Warping. Our algorithm can admissibly prune up to 99.99% of the DTW computations.
  arXiv  Detail & Related papers  (2020-09-16T19:35:43Z)
• Manifold Learning via Manifold Deflation [105.7418091051558]
  dimensionality reduction methods provide a valuable means to visualize and interpret high-dimensional data. Many popular methods can fail dramatically, even on simple two-dimensional Manifolds. This paper presents an embedding method for a novel, incremental tangent space estimator that incorporates global structure as coordinates. Empirically, we show our algorithm recovers novel and interesting embeddings on real-world and synthetic datasets.
  arXiv  Detail & Related papers  (2020-07-07T10:04:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.