The DOI matches its Crossref record.
Learning from ambiguously labeled images
Open accessAbstract
In many image and video collections, we have access only to partially labeled data. For example, personal photo collections often contain several faces per image and a caption that only specifies who is in the picture, but not which name matches which face. Similarly, movie screenplays can tell us who is in the scene, but not when and where they are on the screen. We formulate the learning problem in this setting as partially-supervised multiclass classification where each instance is labeled ambiguously with more than one label. We show theoretically that effective learning is possible under reasonable assumptions even when all the data is weakly labeled. Motivated by the analysis, we propose a general convex learning formulation based on minimization of a surrogate loss appropriate for the ambiguous label setting. We apply our framework to identifying faces culled from Web news sources and to naming characters in TV series and movies. We experiment on a very large dataset consisting of 100 hours of video, and in particular achieve 6% error for character naming on 16 episodes of LOST.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Cited by
A data-driven approach to cleaning large face datasets
Ng, H.-W., & Winkler, S. (2014) · 2014 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2014.7025068 · Cited by 643
A dataset for Movie Description
Rohrbach, A., Rohrbach, M., Tandon, N., & Schiele, B. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298940 · Cited by 435
Selecting training sets for support vector machines: a review
Nalepa, J., & Kawulok, M. (2019) · Artificial Intelligence Review · doi:10.1007/s10462-017-9611-1 · Cited by 419
Acoustic classification of multiple simultaneous bird species: A multi-instance multi-label approach
Briggs, F., Lakshminarayanan, B., Neal, L., Fern, X. Z., Raich, R., Hadley, S. J. K., Hadley, A. S., & Betts, M. G. (2012) · The Journal of the Acoustical Society of America · doi:10.1121/1.4707424 · Cited by 305
Rohrbach, A., Torabi, A., Rohrbach, M., Tandon, N., Pal, C., Larochelle, H., Courville, A., & Schiele, B. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-016-0987-1 · Cited by 300
Metadata
- Authors
- Cour, T., Sapp, B., Jordan, C., & Taskar, B.
- Venue
- 2009 IEEE Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2009-06
- Pages
- 919-926
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2153603270
- Cited by
- 165
- References
- 0
- FWCI
- 9.87
- Type
- conference paper
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Learning from ambiguously labeled images. https://app.cochat.ai/papers/10.1109/cvpr.2009.5206667
- The paper
- Cour, T., Sapp, B., Jordan, C., & Taskar, B. (2009). Learning from ambiguously labeled images. 2009 IEEE Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/cvpr.2009.5206667
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.