000 03004nas a2200409 a 4500
005 20260817161452.0
008 210308s2020 th a r m 000 eng d
035 _a.b12366134
099 9 _aAIT RSPR no.CS-20-01
100 1 _aTirumalasetty, Gayatri
245 1 0 _aAction recognition in generalized zero-shot learning setting using the conditional generative adversarial network
260 _aPathum Thani, Thailand :
_bAsian Institute of Technology,
_c2020
300 _a37 leaves :
_bill.
490 1 _aResearch studies project report ;
_vno.
500 _aA research study submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Computer Science, School of Engineering and Technology
502 _aResearch Studies Project Report (M. Eng.) - Asian Institute of Technology, 2020
520 _aHuman 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.
650 0 _aMachine learning
700 1 _aDailey, Mathew N.,
_eChairperson
700 1 _aPhan, Minh Dung,
_eExamination Committee
700 0 _aChutiporn Anutariya,
_eExamination Committee
710 2 _aAIT Fellowship,
_eScholarship Donor
810 2 _aAsian Institute of Technology.
_tResearch studies project report ;
_vno.
856 _3Full-Text
_uhttp://203.159.5.9/ait-thesis/detail.php?q=B11696
907 _a.b12366134
_bmnait
_cm
902 _a250428
998 _b0
_c210308
_dm
_ea
_fm
_g0
945 _lmnarc
945 _lmnait
945 _lmnait
942 _c40
942 _c20
909 _aBarcode : 3005012090005
_bCREATED : 2025-04-03
_cRECORD # : i13535717
_dLPATRON : 0
_eLCHKIN : -
_f# RENEWALS : 0
_g# OVERDUE : 0
_hIUSE3 : 0
_iTOT CHKOUT : 0
_jTOT RENEW : 0
909 _aBarcode : 30050120426258
_bCREATED : 2025-01-04
_cRECORD # : i13541523
_dLPATRON : 0
_eLCHKIN : -
_f# RENEWALS : 0
_g# OVERDUE : 0
_hIUSE3 : 0
_iTOT CHKOUT : 0
_jTOT RENEW : 0
909 _aBarcode : 30050120426241
_bCREATED : 2025-01-04
_cRECORD # : i13541535
_dLPATRON : 0
_eLCHKIN : -
_f# RENEWALS : 0
_g# OVERDUE : 0
_hIUSE3 : 0
_iTOT CHKOUT : 0
_jTOT RENEW : 0
999 _c1422
_d1422