Video search reranking via information bottleneck principle
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Exploring social dynamics in online media sharing
Proceedings of the 16th international conference on World Wide Web
Practical elimination of near-duplicates from web video search
Proceedings of the 15th international conference on Multimedia
I tube, you tube, everybody tubes: analyzing the world's largest user generated content video system
Proceedings of the 7th ACM SIGCOMM conference on Internet measurement
UQLIPS: a real-time near-duplicate video clip detection system
VLDB '07 Proceedings of the 33rd international conference on Very large data bases
Content based video matching using spatiotemporal volumes
Computer Vision and Image Understanding
Identifying user behavior in online social networks
Proceedings of the 1st Workshop on Social Network Systems
Challenges and techniques for effective and efficient similarity search in large video databases
Proceedings of the VLDB Endowment
Understanding video interactions in youtube
MM '08 Proceedings of the 16th ACM international conference on Multimedia
Broadcast yourself on YouTube: really?
HCC '08 Proceedings of the 3rd ACM international workshop on Human-centered computing
Handbook of Parametric and Nonparametric Statistical Procedures
Handbook of Parametric and Nonparametric Statistical Procedures
Scalable clip-based near-duplicate video detection with ordinal measure
Proceedings of the ACM International Conference on Image and Video Retrieval
Mining near-duplicate graph for cluster-based reranking of web video search results
ACM Transactions on Information Systems (TOIS)
Correlation-based retrieval for heavily changed near-duplicate videos
ACM Transactions on Information Systems (TOIS)
Visual memes in social media: tracking real-world news in YouTube videos
MM '11 Proceedings of the 19th ACM international conference on Multimedia
Galaxy browser: exploratory search of web videos
MM '11 Proceedings of the 19th ACM international conference on Multimedia
Near-duplicate video retrieval: Current research and future trends
ACM Computing Surveys (CSUR)
Socially-aware video recommendation using users' profiles and crowdsourced annotations
Proceedings of the 2nd international workshop on Socially-aware multimedia
Hi-index | 0.00 |
Popular content in video sharing web sites (e.g., YouTube) is usually duplicated. Most scholars define near-duplicate video clips (NDVC) based on non-semantic features (e.g., different image/audio quality), while a few also include semantic features (different videos of similar content). However, it is unclear what features contribute to the human perception of similar videos. Findings of two large scale online surveys (N = 1003) confirm the relevance of both types of features. While some of our findings confirm the adopted definitions of NDVC, other findings are surprising. For example, videos that vary in visual content - by overlaying or inserting additional information - may not be perceived as near-duplicate versions of the original videos. Conversely, two different videos with distinct sounds, people, and scenarios were considered to be NDVC because they shared the same semantics (none of the pairs had additional information). Furthermore, the exact role played by semantics in relation to the features that make videos alike is still an open question. In most cases, participants preferred to see only one of the NDVC in the search results of a video search query and they were more tolerant to changes in the audio than in the video tracks. Finally, we propose a user-centric NDVC definition and present implications for how duplicate content should be dealt with by video sharing websites.