In this paper, we propose Hierarchical Action Segmentation Refiner (HASR), which can refine temporal action segmentation results from various models by understanding the overall context of a given video in a hierarchical way. When a backbone model for action segmentation estimates how the given video can be segmented, our model extracts segment-level representations based on frame-level features, and extracts a video-level representation based on the segment-level representations. Based on these hierarchical representations, our model can refer to the overall context of the entire video, and predict how the segment labels that are out of context should be corrected. Our HASR can be plugged into various action segmentation models (MS-TCN, SSTDA, ASRF), and improve the performance of state-of-the-art models based on three challenging datasets (GTEA, 50Salads, and Breakfast). For example, in 50Salads dataset, the segmental edit score improves from 67.9% to 77.4% (MS-TCN), from 75.8% to 77.3% (SSTDA), from 79.3% to 81.0% (ASRF). In addition, our model can refine the segmentation result from the unseen backbone model, which was not referred to when training HASR. This generalization performance would make HASR be an effective tool for boosting up the existing approaches for temporal action segmentation. Our code is available at https://github.com/cotton-ahn/HASR_iccv2021.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Refining action segmentation with hierarchical video representations


    Beteiligte:
    Ahn, Hyemin (Autor:in) / Lee, Dongheui (Autor:in)

    Kongress:

    2021 ; Virtual



    Erscheinungsdatum :

    2021-10-01



    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Hierarchical probabilistic image segmentation

    Knapman, J. / Dickson, W. | British Library Online Contents | 1994


    Nonlinear Multiscale Representations for Image Segmentation

    Niessen, W. J. / Vincken, K. L. / Weiekert, J. A. et al. | British Library Online Contents | 1997


    Hierarchical Vehicle Action Prediction

    YANG I-HSUAN / WANG YU | Europäisches Patentamt | 2024

    Freier Zugriff

    Adaptive hierarchical image segmentation technique

    Kharinov, M. | British Library Online Contents | 2011


    Hierarchical vehicle action prediction

    YANG I-HSUAN / WANG YU | Europäisches Patentamt | 2023

    Freier Zugriff