A Video-based End-to-end Pipeline for Non-nutritive Sucking Action Recognition and Segmentation in Young Infants.
Shaotong ZhuMichael WanElaheh HatamimajoumerdKashish JainSamuel ZlotaCholpady Vikram KamathCassandra B. RowanEmma C. GraceMatthew S. GoodwinMarie J. HayesRebecca A. Schwartz-MetteEmily ZimmermanSarah OstadabbasPublished in: CoRR (2023)
Keyphrases
- end to end
- action recognition
- bag of words
- activity recognition
- human actions
- human detection
- body parts
- computer vision
- action classification
- segmentation algorithm
- image segmentation
- bag of features
- recognition of human actions
- static images
- recognizing human actions
- segmentation method
- spatial temporal
- multiscale
- recognizing actions
- human activities
- depth sensors
- background subtraction
- view invariant action recognition
- image sequences
- view invariant
- action detection