The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Automatic caption localization in compressed video
Abstract
We present a method to automatically localize captions in JPEG compressed images and the I-frames of MPEG compressed videos. Caption text regions are segmented from background images using their distinguishing texture characteristics. Unlike previously published methods which fully decompress the video sequence before extracting the text regions, this method locates candidate caption text regions directly in the DCT compressed domain using the intensity variation information encoded in the DCT domain. Therefore, only a very small amount of decoding is required. The proposed algorithm takes about 0.006 second to process a 240/spl times/350 image and achieves a recall rate of 99.17 percent while falsely accepting about 1.87 percent nontext DCT blocks on a variety of MPEG compressed videos containing more than 2,300 I-frames.
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
Cites
The JPEG still picture compression standard
Wallace, G. K. (1991) · Communications of the ACM · doi:10.1145/103085.103089 · Cited by 3,784
MPEG: a video compression standard for multimedia applications
Le Gall, D. (1991) · Communications of the ACM · doi:10.1145/103085.103090 · Cited by 2,013
Automatic text location in images and video frames
Jain, A. K., & Yu, B. (2002) · Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170) · doi:10.1109/icpr.1998.711990 · Cited by 450
Self-citationIntelligent access to digital video: Informedia project
Wactlar, H. D., Takeo Kanade, A., Smith, M. A., & Stevens, S. (1996) · Computer · doi:10.1109/2.493456 · Cited by 339
Text segmentation using gabor filters for automatic document processing
Jain, A. K., & Bhattacharjee, S. (1992) · Machine Vision and Applications · doi:10.1007/bf02626996 · Cited by 328
Self-citationSmith, M. A., & Kanade, T. (2002) · Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.1997.609414 · Cited by 311
Automatic text recognition in digital videos:
Lienhart, R. W., & Stuber, F. (1996) · SPIE Proceedings · doi:10.1117/12.234741 · Cited by 160
Cited by
Text information extraction in images and video: a survey
Jung, K., In Kim, K., & K. Jain, A. (2004) · Pattern Recognition · doi:10.1016/j.patcog.2003.10.012 · Cited by 846
Text Detection and Recognition in Imagery: A Survey
Ye, Q., & Doermann, D. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2366765 · Cited by 780
Robust Text Detection in Natural Scene Images
Yin, X.-C., Yin, X., Huang, K., & Hao, H.-W. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.182 · Cited by 633
Multimodal Video Indexing: A Review of the State-of-the-art
Snoek, C. G. M., & Worring, M. (2005) · Multimedia Tools and Applications · doi:10.1023/b:mtap.0000046380.27575.a5 · Cited by 486
Kim, K. I., Jung, K., & Kim, J. H. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1251157 · Cited by 449
Metadata
- Authors
- Zhong, Y., Zhang, H., & Jain, A. K.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2000-04
- Volume
- 22
- Issue
- 4
- Pages
- 385-392
- ISSN
- 0162-8828 (ISSN-L)
- OpenAlex
- W2165401735
- Cited by
- 333
- References
- 7
- FWCI
- 22.36
- Type
- journal article
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Automatic caption localization in compressed video. https://app.cochat.ai/papers/10.1109/34.845381
- The paper
- Zhong, Y., Zhang, H., & Jain, A. K. (2000). Automatic caption localization in compressed video. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/34.845381
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.