Marques, Guilherme de AP;
Busson, Antonio Jose G;
Guedes, Alan Livio;
Colcher, Sergio;
(2021)
A Cluster-Based Method for Action Segmentation Using Spatio-Temporal and Positional Encoded Embeddings.
In:
WebMedia '21: Proceedings of the Brazilian Symposium on Multimedia and the Web.
(pp. pp. 181-187).
ACM
Preview |
Text
216484.pdf - Other Download (2MB) | Preview |
Abstract
A crucial task to overall video understanding is the recognition and localisation in time of different actions or events that are present along the scenes. To address this problem, action segmentation must be achieved. Action segmentation consists of temporally segmenting a video by labeling each frame with a specific action. In this work, we propose a novel action segmentation method that requires no prior video analysis and no annotated data. Our method involves extracting spatio-Temporal features from videos in samples of 0.5s using a pre-Trained deep network. Data is then transformed using a positional encoder and finally a clustering algorithm is applied with the use of a silhouette score to find the optimal number of clusters where each cluster presumably corresponds to a different single and distinguishable action. In experiments, we show that our method produces competitive results on Breakfast and Inria Instructional Videos dataset benchmarks.
| Type: | Proceedings paper |
|---|---|
| Title: | A Cluster-Based Method for Action Segmentation Using Spatio-Temporal and Positional Encoded Embeddings |
| Event: | 27th Brazilian Symposium on Multimedia and the Web (WebMedia) |
| Location: | ELECTR NETWORK |
| Dates: | 5 Nov 2021 - 12 Nov 2021 |
| ISBN-13: | 9781450386098 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1145/3470482.3479632 |
| Publisher version: | https://doi.org/10.1145/3470482.3479632 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Action recognition, Action segmentation, Computer Science, Computer Science, Interdisciplinary Applications, Computer Science, Software Engineering, Computer Science, Theory & Methods, I3D, Positional encoding, Science & Technology, Technology |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10163974 |
Loading...
Loading...Loading...| 1. |  United States | 11 |
| 2. |  India | 11 |
| 3. |  China | 6 |
| 4. |  France | 3 |
| 5. |  Germany | 3 |
| 6. |  United Kingdom | 2 |
| 7. |  Australia | 2 |
| 8. |  South Africa | 2 |
| 9. |  Israel | 2 |
| 10. |  Sweden | 1 |
Archive Staff Only
 |
View Item |
