TP-L.C1.4

TRANSFORMER BASED SELF-CONTEXT AWARE PREDICTION FOR FEW-SHOT ANOMALY DETECTION IN VIDEOS

Gargi V Pillai, Ashish Verma, Debashis Sen, Indian Institute of Technology Kharagpur, India
Session:
Image and Video Analysis
Lecture
Track:
Image and Video Analysis, Synthesis, and Retrieval
Location:
Room C1
Presentation Time:
Tue, 18 Oct, 23:15 - 23:30 China Standard Time (UTC +8)
Tue, 18 Oct, 17:15 - 17:30 Central European Time (UTC +1)
Tue, 18 Oct, 15:15 - 15:30 UTC
Tue, 18 Oct, 11:15 - 11:30 Eastern Time (UTC -4)
Session Chair:
James Fowler, MSU
Presentation
Discussion
Resources
No resources available.
Session TP-L.C1
TP-L.C1.1: ON MONOCULAR DEPTH ESTIMATION AND UNCERTAINTY QUANTIFICATION USING CLASSIFICATION APPROACHES FOR REGRESSION
Xuanlong Yu, Emanuel Aldea, Paris Saclay University, France; Gianni Franchi, École Nationale Supérieure de Techniques Avancées, France
TP-L.C1.2: PARALLEL PARTITIONING: PATH REDUCING AND UNION–FIND BASED WATERSHED FOR THE GPU
Yeva Gabrielyan, Varduhi Yeghiazaryan, American University of Armenia, Armenia; Irina Voiculescu, Oxford University, United Kingdom of Great Britain and Northern Ireland
TP-L.C1.3: TEMPORALLY PRECISE ACTION SPOTTING IN SOCCER VIDEOS USING DENSE DETECTION ANCHORS
João Soares, Avijit Shah, Yahoo, United States of America; Topojoy Biswas, Walmart, United States of America
TP-L.C1.4: TRANSFORMER BASED SELF-CONTEXT AWARE PREDICTION FOR FEW-SHOT ANOMALY DETECTION IN VIDEOS
Gargi V Pillai, Ashish Verma, Debashis Sen, Indian Institute of Technology Kharagpur, India
TP-L.C1.5: SEQUENTIAL CROSS ATTENTION BASED MULTI-TASK LEARNING
Sunkyung Kim, Hyesong Choi, Dongbo Min, Ewha Womans University, Korea, Republic of