Multi-Stage Temporal Convolutional Network For Action Segmentation

Happy Open Access Week from arXiv!

YOU make open access possible! Tell us why you support #openaccess and give to arXiv this week to help keep science open for all.

Donate! Computer Science > Computer Vision and Pattern Recognition arXiv:1903.01945 (cs) [Submitted on 5 Mar 2019 (v1), last revised 2 Apr 2019 (this version, v2)] Title:MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation Authors:Yazan Abu Farha, Juergen Gall View a PDF of the paper titled MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation, by Yazan Abu Farha and Juergen Gall View PDF

Abstract:Temporally locating and classifying action segments in long untrimmed videos is of particular interest to many applications like surveillance and robotics. While traditional approaches follow a two-step pipeline, by generating frame-wise probabilities and then feeding them to high-level temporal models, recent approaches use temporal convolutions to directly classify the video frames. In this paper, we introduce a multi-stage architecture for the temporal action segmentation task. Each stage features a set of dilated temporal convolutions to generate an initial prediction that is refined by the next one. This architecture is trained using a combination of a classification loss and a proposed smoothing loss that penalizes over-segmentation errors. Extensive evaluation shows the effectiveness of the proposed model in capturing long-range dependencies and recognizing action segments. Our model achieves state-of-the-art results on three challenging datasets: 50Salads, Georgia Tech Egocentric Activities (GTEA), and the Breakfast dataset.

Comments:	CVPR 2019 Camera Ready
Subjects:	Computer Vision and Pattern Recognition (cs.CV)
Cite as:	arXiv:1903.01945 [cs.CV]
(or arXiv:1903.01945v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.1903.01945 Focus to learn more arXiv-issued DOI via DataCite

Submission history

From: Yazan Abu Farha [view email] [v1] Tue, 5 Mar 2019 17:29:37 UTC (1,944 KB) [v2] Tue, 2 Apr 2019 15:35:40 UTC (1,747 KB) Full-text links:

Access Paper:

View a PDF of the paper titled MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation, by Yazan Abu Farha and Juergen Gall
• View PDF
• TeX Source

view license Current browse context: cs.CV < prev | next > new | recent | 2019-03 Change to browse by: cs

References & Citations

• NASA ADS
• Google Scholar
• Semantic Scholar

DBLP - CS Bibliography

listing | bibtex Yazan Abu FarhaJuergen Gall export BibTeX citation

BibTeX formatted citation

× loading... Data provided by:

Bookmark

Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) Links to Code Toggle Papers with Code (What is Papers with Code?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?)

• Author
• Venue
• Institution
• Topic

About arXivLabs arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)