EUSIPCO2022 “Auto-weighted sequential Wasserstein distance”


2022年8月29日から9月2日にベオグラード(セルビア)で開催される信号処理分野・欧州フラッグシップ会議 30th International European Signal Processing Conference (EUSIPCO) 20202 に1件の研究論文が採択されました.

  • Authors: M.Horie (M1, 1st-year graduate student) and H.Kasai
  • Title: Auto-weighted Sequential Wasserstein Distance and Application to Sequence Matching
  • Abstract: Sequence matching problems have been central to the field of data analysis for decades. Such problems arise in widely diverse areas including computer vision, speech processing, bioinformatics, and natural language processing. However, solving such problems efficiently is difficult because one must consider temporal consistency, neighborhood structure similarity, robustness to noise and outliers, and flexibility on start-end matching points. This paper presents a proposal of a shape-aware Wasserstein distance between sequences building upon optimal transport (OT) framework. The proposed distance considers similarity measures of the elements, their neighborhood structures, and temporal positions. We incorporate these similarity measures into three ground cost matrixes of the OT formulation. The noteworthy contribution is that we formulate these measures as independent OT distances with a single shared optimal transport matrix, and adjust those weights automatically according to their effects on the total OT distance. Numerical evaluations suggest that the sequence matching method using our proposed Wasserstein distance robustly outperforms state-of-the-art methods across different real-world datasets.
  • Paper: Publisher site, arXiv paper. 
  • Code: The software is available at Github.

Conference information: EUSIPCO

  • EUSIPCO is the flagship conference of EURASIP and offers a comprehensive technical program addressing all the latest developments in research and technology for signal processing. EUSIPCO 2022 will feature world-class speakers, oral and poster sessions, plenaries, exhibitions, demonstrations, tutorials, and satellite workshops, and is expected to attract many leading researchers and industry figures from all over the world. 
  • Google Scholar Metric H5-index: 28 (checked on June 4, 2020)