3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification
IEEE Transactions on Neural Networks and Learning Systems, Volume abs/1812.10222, Issue 11, 2019, Pages 1-13.
Feature extractionSpatiotemporal phenomenaNeural networksStreaming mediaSolid modelingMore(2+)
We present the global deep video representation learning to video-based person reidentification (re-ID) that aggregates local 3-D features across the entire video extent. Existing methods typically extract frame-wise deep features from 2-D convolutional networks (ConvNets) which are pooled temporally to produce the video-level representat...More
PPT (Upload PPT)