Practical elimination of near-duplicates from web video search
Open accessAbstract
Current web video search results rely exclusively on text keywords or user-supplied tags. A search on typical popular video often returns many duplicate and near-duplicate videos in the top results. This paper outlines ways to cluster and filter out the near-duplicate video using a hierarchical approach. Initial triage is performed using fast signatures derived from color histograms. Only when a video cannot be clearly classified as novel or near-duplicate using global signatures, we apply a more expensive local feature based near-duplicate detection which provides very accurate duplicate analysis through more costly computation. The results of 24 queries in a data set of 12,790 videos retrieved from Google, Yahoo! and YouTube show that this hierarchical approach can dramatically reduce redundant video displayed to the user in the top result set, at relatively small computational cost.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
None of the existing definitions addresses the retrieval of same incident videos.
“However, there does not seem to be strong consensus among researchers about which videos are considered near-duplicate videos and none of the existing definitions addresses the retrieval of same incident videos ; in this paper, we attempt to address these issues and provide solid definitions for all types of associations between videos related to the FIVR problem.”
From FIVR: Fine-Grained Incident Video Retrieval (2019) · cites this paper as [49]
The labels in CC Web and UQ Video are only available on video-level, without timestamps of the copied segments.
“the labels in the datasets are only available on video-level, indicating whether or not two videos are copies of each other without the timestamps of the copied segments”
From VCDB: A Large-Scale Database for Partial Copy Detection in Videos (2014) · cites this paper as [3]
Many copies in the CC Web and UQ Video datasets are easy to be detected as the transformations among them are very limited.
“Many copies in the two datasets are easy to be detected as the transformations among them are very limited.”
From VCDB: A Large-Scale Database for Partial Copy Detection in Videos (2014) · cites this paper as [3]
There is no strong consensus among researchers about which videos are considered near-duplicate videos.
“However, there does not seem to be strong consensus among researchers about which videos are considered near-duplicate videos and none of the existing definitions addresses the retrieval of same incident videos ; in this paper, we attempt to address these issues and provide solid definitions for all types of associations between videos related to the FIVR problem.”
From FIVR: Fine-Grained Incident Video Retrieval (2019) · cites this paper as [49]
CC WEB VIDEO has a relatively small volume and query set (12,790 videos and 24 queries) and lacks challenging distractors because its queries are very different from each other.
“For instance, the volume and query set of CC WEB VIDEO are relatively small (12,790 videos and 24 queries), and the dataset lacks challenging distractors given that the queries are very different from each other.”
From FIVR: Fine-Grained Incident Video Retrieval (2019) · cites this paper as [49]
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · see citing works
A performance evaluation of local descriptors
Mikolajczyk, K., & Schmid, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.188 · Cited by 6,723 · see citing works
Scale & Affine Invariant Interest Point Detectors
Mikolajczyk, K., & Schmid, C. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000027790.02288.f2 · Cited by 3,436 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Multiple feature hashing for real-time large scale near-duplicate video retrieval
Song, J., Yang, Y., Huang, Z., Shen, H. T., & Hong, R. (2011) · Proceedings of the 19th ACM international conference on Multimedia · doi:10.1145/2072298.2072354 · Cited by 334 · see citing works
Event Retrieval in Large Video Collections with Circulant Temporal Encoding
Revaud, J., Douze, M., Schmid, C., & Jegou, H. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.318 · Cited by 133 · see citing works
Scalable detection of partial near-duplicate videos by visual-temporal consistency
Tan, H.-K., Ngo, C.-W., Hong, R., & Chua, T.-S. (2009) · Proceedings of the 17th ACM international conference on Multimedia · doi:10.1145/1631272.1631295 · Cited by 110 · see citing works
Self-citationVCDB: A Large-Scale Database for Partial Copy Detection in Videos
Jiang, Y.-G., Jiang, Y., & Wang, J. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10593-2_24 · Cited by 82 · see citing works
Near-Duplicate Video Retrieval by Aggregating Intermediate CNN Layers
Kordopatis-Zilos, G., Papadopoulos, S., Patras, I., & Kompatsiaris, Y. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-51811-4_21 · Cited by 83 · see citing works
FIVR: Fine-Grained Incident Video Retrieval
Kordopatis-Zilos, G., Papadopoulos, S., Patras, I., & Kompatsiaris, I. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2905741 · Cited by 78 · see citing works
“CC WEB VIDEO [49] 24 12,790 551 X Near-Duplicate Video Retrieval UQ VIDEO [42] 24 169,952 N/A X Near-Duplicate Video Retrieval MUSCLE-VCD [30] 18 101 100 7 Video Copy Detection TRECVID 2011 [29] 11,256 11,503 420 7 Video Copy Detection VCDB [20] 528 100,528 2,038 X Partial Video Copy Detection EVVE [35] 620 102,375 5,…”
BackgroundMethodInfluentialPartial Copy Detection in Videos: A Benchmark and an Evaluation of Popular Methods
Jiang, Y.-G., & Wang, J. (2016) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2016.2530714 · Cited by 72 · see citing works
Learning spatial-temporal features for video copy detection by the combination of CNN and RNN
Hu, Y., & Lu, X. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.05.013 · Cited by 57 · see citing works
Content-Based Video Copy Detection Benchmarking at TRECVID
Awad, G., Over, P., & Kraaij, W. (2014) · ACM Transactions on Information Systems · doi:10.1145/2629531 · Cited by 30 · see citing works
Attention-Based Deep Metric Learning for Near-Duplicate Video Retrieval
Wang, K.-H., Cheng, C.-C., Chen, Y.-L., Song, Y., & Lai, S.-H. (2021) · 2020 25th International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr48806.2021.9412710 · Cited by 19 · see citing works
- Authors
- Wu, X., Hauptmann, A. G., & Ngo, C.-W.
- Affiliations
- City University of Hong Kong (HK)
- Carnegie Mellon University (US)
- Venue
- Proceedings of the 15th ACM international conference on Multimedia
- Publisher
- ACM
- Published
- 2007-09-29
- Pages
- 218-227
- OpenAlex
- W2162659160
- Cited by
- 340
- References
- 3
- Citations by year
- 2026: 3 · 2025: 8 · 2024: 8 · 2023: 15 · 2022: 21 · 2021: 20 · 2020: 8 · 2019: 19 · 2018: 17 · 2017: 13 · 2016: 19 · 2015: 19 · 2014: 21 · 2013: 22 · 2012: 26
- FWCI
- 20.52
- Type
- conference paper
- Language
- en
- Open access
- Locations
- ACM International Conference on Multimedia (ACM MM) (publishedVersion)
- Singapore Management University Institutional Knowledge (InK) (Singapore Management University) (submittedVersion, other-oa)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Analysis and Summarization
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Keywords
- near-duplicate video detection, hierarchical clustering, color histogram, video signature, local feature matching
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
