Table 2 Summary of the reviewed structured-template-based studies
From: Bilingual video captioning model for enhanced video retrieval
Ref. | Year | Extracted information | Method |
|---|---|---|---|
[17] | 2015 | Subject, verb, object | Stanford parser—DNN |
[28] | 2012 | Subject, verb, object | Stanford parser |
[29] | 2012 | Subject, verb, object, additional details (adverbs, adjectives, …) | Detectors—Kanade–Lucas–Tomas—HMMs—dynamic-programming algorithm |
[30] | 2014 | Subject, verb, object, place | Factor graph model |
[31] | 2013 | Subject, verb, object | Text-mining knowledge |