CoChat

Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment

Xu, Chenliang, Ding, Li · 2018 · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Cited by 104

The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.

Abstract

In this work, we address the task of weakly-supervised human action segmentation in long, untrimmed videos. Recent methods have relied on expensive learning models, such as Recurrent Neural Networks (RNN) and Hidden Markov Models (HMM). However, these methods suffer from expensive computational cost, thus are unable to be deployed in large scale. To overcome the limitations, the keys to our design are efficiency and scalability. We propose a novel action modeling framework, which consists of a new temporal convolutional network, named Temporal Convolutional Feature Pyramid Network (TCFPN), for predicting frame-wise action labels, and a novel training strategy for weakly-supervised sequence modeling, named Iterative Soft Boundary Assignment (ISBA), to align action sequences and update the network in an iterative fashion. The proposed framework is evaluated on two benchmark datasets, Breakfast and Hollywood Extended, with four different evaluation metrics. Extensive experimental results show that our methods achieve competitive or superior performance to state-of-the-art methods.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr.2018.00681

Cites

8 of 8 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 16

  1. laptev, 2008, Learning realistic human actions from movies, Computer Vision and Pattern Recognition 2008 CVPR 2008 IEEE Conference on, 1
  2. 10.1109/CVPR.2009.5206557 · DOI · Paper page
  3. 10.1109/CVPR.2014.102 · DOI · Paper page
  4. 10.1109/CVPR.2016.501 · DOI · Paper page
  5. ding, 2017, Tricornet A hybrid temporal convolutional and recurrent network for video action segmentation
  6. 10.1111/j.2517-6161.1977.tb01600.x · DOI · Paper page
  7. 10.1109/ICCV.2017.618 · DOI · Paper page
  8. 10.1109/ICCV.2017.83 · DOI · Paper page
  9. bojanowski, 2014, Weakly supervised action labeling in videos under ordering constraints, European Conference on Computer Vision, 628
  10. 10.1109/CVPR.2016.495 · DOI · Paper page
  11. 10.1109/WACV.2016.7477701 · DOI · Paper page
  12. 10.1109/CVPR.2015.7298839 · DOI
  13. yeung, 2015, Every moment counts: Dense detailed labeling of actions in complex videos, International Journal of Computer Vision, 1
  14. 10.1109/CVPR.2016.571 · DOI · Paper page
  15. zhou, 2018, Towards automatic learning of procedures from web instructional videos, AAAI Conference on Artificial Intelligence, 10.1007/978-981-13-2122-1 · DOI
  16. 10.1109/CVPR.2016.496 · DOI · Paper page

Cited by

See all 104

Metadata

Authors
Xu, C., & Ding, L.
Venue
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Publisher
IEEE
Published
2018-06
Pages
6508-6516
ISSN
1063-6919 (ISSN-L)
OpenAlex
W2964311439
Cited by
104
References
8
FWCI
5.00
Type
conference paper
Language
en
Open access
closed

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.