AI SearchAction recognition in generalized zero-shot learning setting using the conditional generative adversarial network
Call Number: AIT RSPR no.CS-20-01 Material type:
Continuing resourceSeries: Asian Institute of Technology. Research studies project report ; no. Publication details: Pathum Thani, Thailand : Asian Institute of Technology, 2020Description: 37 leaves : illSubject(s): Online resources: Dissertation note: Research Studies Project Report (M. Eng.) - Asian Institute of Technology, 2020 Summary: Human action recognition is an interesting area of research which has found applications in security surveillance systems, robotics, human-computer interaction and so on. Human actions can be classified into usual (mundane) events and unusual (peculiar) events. The traditional supervised learning models that discriminate between classes are helpful in clas sifying mundane actions of which the data is available during training. But in case of unusual events, we do not generally possess the example data during training. This now becomes a problem of zero-shot learning. In this study, I explore generative models to produce in stances of peculiar action events with the help of semantic meaning related to the action classes. The data from different places at AIT has been combined with benchmark UCF101 dataset to carry out the experiment. I have achieved an accuracy of 96.7% on the usual event classification and 60.94% on unusual event classification tasks during test time.
| Cover image | Item type | Current library | Home library | Collection | Shelving location | Call number | Materials specified | Vol info | URL | Copy number | Status | Notes | Date due | Barcode | Item holds | Item hold queue priority | Course reserves | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
40-Archives
|
Asian Institute of Technology Library Archives | AIT RSPR no.CS-20-01 (Browse shelf(Opens below)) | 1 | Available | 3005012090005 | |||||||||||||
20-AIT Publication
|
Asian Institute of Technology Library AIT Publications | AIT RSPR no.CS-20-01 (Browse shelf(Opens below)) | 1 | Available | 30050120426258 | |||||||||||||
|
20-AIT Publication
|
Asian Institute of Technology Library AIT Publications | AIT RSPR no.CS-20-01 (Browse shelf(Opens below)) | 2 | Available | 30050120426241 |
A research study submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Computer Science, School of Engineering and Technology
Research Studies Project Report (M. Eng.) - Asian Institute of Technology, 2020
Human action recognition is an interesting area of research which has found applications in security surveillance systems, robotics, human-computer interaction and so on. Human actions can be classified into usual (mundane) events and unusual (peculiar) events. The traditional supervised learning models that discriminate between classes are helpful in clas sifying mundane actions of which the data is available during training. But in case of unusual events, we do not generally possess the example data during training. This now becomes a problem of zero-shot learning. In this study, I explore generative models to produce in stances of peculiar action events with the help of semantic meaning related to the action classes. The data from different places at AIT has been combined with benchmark UCF101 dataset to carry out the experiment. I have achieved an accuracy of 96.7% on the usual event classification and 60.94% on unusual event classification tasks during test time.
There are no comments on this title.