Using High-Level Semantic Features in Video Retrieval

Zheng, Wujie; Li, Jianmin; Si, Zhangzhang; Lin, Fang; Zhang, Bo

doi:10.1007/11788034_38

Cited by 25 publications

(28 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zheng et al [25] take a similar approach to ours. Starting from information theory they derive a formula which is supposed to rank shots in the same way as the probability of relevance.…”

Section: Related Workmentioning

confidence: 98%

“…Note, if we leave out the term marked with Ci is absent in Formula 10 and set P (R) = α, we have exactly the Formula 2 from Zheng et al [25], because the sum of logarithms is equal to the product. This suggests that Zheng's formula only considers the case P ( C|R) with C = (1, .., 1), in other words, the calculated quantity is the probability of relevance given the occurrence of all n concepts times the probability that all these n concepts occur.…”

Section: Ranking Functionmentioning

confidence: 99%

See 1 more Smart Citation

A probabilistic ranking framework using unobservable binary events for video search

Aly

Hiemstra

Vries

et al. 2008

Proceedings of the 2008 International Conference on Content-Based Image and Video Retrieval

View full text Add to dashboard Cite

Recent content-based video retrieval systems combine output of concept detectors (also known as high-level features) with text obtained through automatic speech recognition. This paper concerns the problem of search using the noisy concept detector output only. Unlike term occurrence in text documents, the event of the occurrence of an audiovisual concept is only indirectly observable. We develop a probabilistic ranking framework for unobservable binary events to search in videos, called PR-FUBE. The framework explicitly models the probability of relevance of a video shot through the presence and absence of concepts. From our framework, we derive a ranking formula and show its relationship to previously proposed formulas. We evaluate our framework against two other retrieval approaches using the TRECVID 2005 and 2007 datasets. Especially using large numbers of concepts in retrieval results in good performance. We attribute the observed robustness against the noise introduced by less related concepts to the effective combination of concept presence and absence in our method. The experiments show that an accurate estimate for the probability of occurrence of a particular concept in relevant shots is crucial to obtain effective retrieval results.

show abstract

“…Zheng et al [25] take a similar approach to ours. Starting from information theory they derive a formula which is supposed to rank shots in the same way as the probability of relevance.…”

Section: Related Workmentioning

confidence: 98%

Section: Ranking Functionmentioning

confidence: 99%

A probabilistic ranking framework using unobservable binary events for video search

Aly

Hiemstra

Vries

et al. 2008

Proceedings of the 2008 International Conference on Content-Based Image and Video Retrieval

View full text Add to dashboard Cite

show abstract

“…We use the following two concept combination methods to examine the influence of the concept selection method: Zheng et al propose in [19] a concept based retrieval method which uses the probability P (C|R). They estimate the probability that a concept occurs in relevant shots through the probability of concepts occurring in the positive examples which are provided with the query.…”

Section: Related Workmentioning

confidence: 99%

“…We name our estimation method "score-based". Now, a set of concepts can be selected and a Concept Based IR method, such as PRFUBE [1] or Entropy [19], can use these values to execute the third step of the retrieval procedure -to search on the actual search collection.…”

Section: Probability Of a Concept Given Relevancementioning

confidence: 99%

See 1 more Smart Citation

Reusing annotation labor for concept selection

Aly

Hiemstra

Vries

2009

Proceedings of the ACM International Conference on Image and Video Retrieval

View full text Add to dashboard Cite

Describing shots through the occurrence of semantic concepts is the first step towards modeling the content of a video semantically. An important challenge is to automatically select the right concepts for a given information need. For example, systems should be able to decide whether the concept "Outdoor" should be included into a search for "Street Basketball". In this paper we provide an innovative method to automatically select concepts for an information need. To achieve this, we provide an estimation for the occurrence probability of a concept in relevant shots, which helps us to quantify the helpfulness of a concept. Our method reuses existing training data which is annotated with concept occurrences to build a text collection. Searching in this collection with a text retrieval system and knowing about the concept occurrences allows us to come up with a good estimate for this probability. We evaluate our method against a concept selection benchmark and search runs on both the TRECVID 2005 and 2007 collections. These experiments show that the estimation consistently improves retrieval effectiveness.

show abstract

Video

Liu¹

2009

Encyclopedia of Database Systems

View full text Add to dashboard Cite

Using High-Level Semantic Features in Video Retrieval

Cited by 25 publications

References 7 publications

A probabilistic ranking framework using unobservable binary events for video search

A probabilistic ranking framework using unobservable binary events for video search

Reusing annotation labor for concept selection

Video

Contact Info

Product

Resources

About