Concept-oriented video skimming and adaptation via semantic classification
Proceedings of the 6th ACM SIGMM international workshop on Multimedia information retrieval
Context-aware cooking navigation system using sensor based task model
ASM '07 The 16th IASTED International Conference on Applied Simulation and Modelling
Mining large-scale broadcast video archives towards inter-video structuring
PCM'04 Proceedings of the 5th Pacific Rim Conference on Advances in Multimedia Information Processing - Volume Part II
Learning cooking techniques from youtube
MMM'10 Proceedings of the 16th international conference on Advances in Multimedia Modeling
| Hi-index | 0.00 |
This paper presents a method to delineate visually important segments from cooking videos ,which is expectedto be a core technique for cooking video indexing. Visualinformation is exceptionally important in cooking videos, sinceit represents essential technical skills owing to properties of instruction type videos. Here, we reveal that ordinaryshot-based video indexing approach will not work for cooking videos, since visually important segments are absorbedin a shot. Based on the observation of cooking videos, themethod detects repetitious motion segments as visually important segments by using relatively simple and robusttechniques. The experimental evaluation shows that the methoddetects more than 80%of manually selected segments, while84%of detected segments were correct. We also developeda cooking video abstraction system as a sample applicationof our method and confirmed that the proposed method isuseful for a real application.