Video Captioning using a Hybrid Transformer and RNN-based Encoder-Decoder.
Alexandru-Cosmin MihaiMihai-Dan MasalaDan-Teodor PoncuTraian RebedeaPublished in: RoCHI (2022)
Keyphrases
- low complexity
- video codec
- bit budget
- video encoder
- video encoding
- distributed video coding
- pixel domain
- decoding process
- video transcoding
- temporal correlation
- video decoder
- mpeg avc
- recurrent neural networks
- video data
- bit rate
- rate distortion
- video sequences
- video coding
- motion estimation
- video coding scheme
- wyner ziv video coding
- compressed video
- nearest neighbor
- error control
- video streams
- video frames
- bitstream
- video content
- real time video
- noisy channel
- wyner ziv
- multimedia
- successive approximation
- motion vectors
- video conferencing
- video surveillance
- turbo codes
- low bit rate
- video quality
- neural network
- fuzzy logic
- distributed source coding
- coding scheme
- key frames
- motion compensation
- video transmission
- motion compensated
- rate control
- spatial correlation
- video objects
- error resilience
- rate allocation