Risky Action Recognition in Lane Change Video Clips using Deep Spatiotemporal Networks with Segmentation Mask Transfer.
Ekim YurtseverYongkang LiuJacob LambertChiyomi MiyajimaEijiro TakeuchiKazuya TakedaJohn H. L. HansenPublished in: CoRR (2019)
Keyphrases
- action recognition
- video clips
- video database
- video dataset
- human actions
- bag of words
- video data
- activity recognition
- action classification
- body parts
- video streams
- computer vision
- recognizing human actions
- video content
- video frames
- recognizing actions
- view invariant
- video scene
- object segmentation
- key frames
- video retrieval
- video segments
- spatial and temporal
- recognition of human actions
- action recognition in videos
- human pose
- video shots
- topic segmentation
- human activities
- feature vectors
- spatio temporal
- feature space