Details
| Original language | English |
|---|---|
| Title of host publication | ICMR 2016 - Proceedings of the 2016 ACM International Conference on Multimedia Retrieval |
| Pages | 381-384 |
| Number of pages | 4 |
| ISBN (electronic) | 9781450343596 |
| Publication status | Published - 6 Jun 2016 |
| Event | 6th ACM International Conference on Multimedia Retrieval, ICMR 2016 - New York, United States Duration: 6 Jun 2016 → 9 Jun 2016 |
Publication series
| Name | ICMR 2016 - Proceedings of the 2016 ACM International Conference on Multimedia Retrieval |
|---|
Abstract
Some recent approaches for character identification in movies and TV broadcasts are realized in a semi-supervised manner by assigning transcripts and/or subtitles to the speakers. However, the labels obtained in this way achieve only an accuracy of 80%-90% and the number of training examples for the different actors is unevenly distributed. In this paper, we propose a novel approach for person identification in video by correcting and extending the training data with reliable predictions to reduce the number of annotation errors. Furthermore, the intra-class diversity of rarely speaking characters is enhanced. To address the imbalance of training data per person, we suggest two complementary prediction scores. These scores are also used to recognize whether or not a face track belongs to a (supporting) character whose identity does not appear in the transcript etc. Experimental results demonstrate the feasibility of the proposed approach, outperforming the current state of the art.
Keywords
- Face identification in video, Semi-supervised learning
ASJC Scopus subject areas
- Computer Science(all)
- Computer Graphics and Computer-Aided Design
- Computer Science(all)
- Human-Computer Interaction
- Computer Science(all)
- Software
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
ICMR 2016 - Proceedings of the 2016 ACM International Conference on Multimedia Retrieval. 2016. p. 381-384 (ICMR 2016 - Proceedings of the 2016 ACM International Conference on Multimedia Retrieval).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Semi-supervised identification of rarely appearing persons in video by correcting weak labels
AU - Müller, Eric
AU - Otto, Christian
AU - Ewerth, Ralph
PY - 2016/6/6
Y1 - 2016/6/6
N2 - Some recent approaches for character identification in movies and TV broadcasts are realized in a semi-supervised manner by assigning transcripts and/or subtitles to the speakers. However, the labels obtained in this way achieve only an accuracy of 80%-90% and the number of training examples for the different actors is unevenly distributed. In this paper, we propose a novel approach for person identification in video by correcting and extending the training data with reliable predictions to reduce the number of annotation errors. Furthermore, the intra-class diversity of rarely speaking characters is enhanced. To address the imbalance of training data per person, we suggest two complementary prediction scores. These scores are also used to recognize whether or not a face track belongs to a (supporting) character whose identity does not appear in the transcript etc. Experimental results demonstrate the feasibility of the proposed approach, outperforming the current state of the art.
AB - Some recent approaches for character identification in movies and TV broadcasts are realized in a semi-supervised manner by assigning transcripts and/or subtitles to the speakers. However, the labels obtained in this way achieve only an accuracy of 80%-90% and the number of training examples for the different actors is unevenly distributed. In this paper, we propose a novel approach for person identification in video by correcting and extending the training data with reliable predictions to reduce the number of annotation errors. Furthermore, the intra-class diversity of rarely speaking characters is enhanced. To address the imbalance of training data per person, we suggest two complementary prediction scores. These scores are also used to recognize whether or not a face track belongs to a (supporting) character whose identity does not appear in the transcript etc. Experimental results demonstrate the feasibility of the proposed approach, outperforming the current state of the art.
KW - Face identification in video
KW - Semi-supervised learning
UR - http://www.scopus.com/inward/record.url?scp=84978682976&partnerID=8YFLogxK
U2 - 10.1145/2911996.2912073
DO - 10.1145/2911996.2912073
M3 - Conference contribution
AN - SCOPUS:84978682976
T3 - ICMR 2016 - Proceedings of the 2016 ACM International Conference on Multimedia Retrieval
SP - 381
EP - 384
BT - ICMR 2016 - Proceedings of the 2016 ACM International Conference on Multimedia Retrieval
T2 - 6th ACM International Conference on Multimedia Retrieval, ICMR 2016
Y2 - 6 June 2016 through 9 June 2016
ER -