Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting.
Pongpisit ThanasutivesKen-ichi FukuiMasayuki NumaoBoonserm KijsirikulPublished in: CoRR (2020)
Keyphrases
- convolutional neural networks
- multiscale
- video codec
- decoding process
- distributed video coding
- error control
- low complexity
- wyner ziv
- noisy channel
- successive approximation
- convolutional network
- wyner ziv video coding
- video coding
- rate distortion
- video coding scheme
- mpeg avc
- distributed source coding
- coarse to fine
- motion estimation
- motion compensated prediction
- video quality
- inter frame
- transform domain
- scale space
- motion compensation
- video encoder
- error resilience
- turbo codes
- rate allocation
- edge detection
- error concealment
- video coding standard
- wavelet transform
- bit rate
- video compression
- low bit rate
- image segmentation
- compressive sensing
- packet loss
- error correction
- bit budget
- vector quantization
- video coder
- temporal correlation
- base layer
- rate control
- compressed video
- motion compensated
- local binary pattern
- bitstream