Video coding with H.264/AVC: tools, performance, and complexity

By Jörn Ostermann, Jan Bormans, P. List, Detlev Marpe, Matthias Narroschke, Fernando Manuel Bernardo Pereira, Thomas Stockhammer, T. Wedi. IEEE Circuits and Systems Magazine, 2004

1,002 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/5a1bb801c0c8aaa37668202b732598acf3f278c4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Tien-Ju Yang
2. Vivienne Sze
3. Joel S. Emer
4. Yu-hsin Chen
5. Fernando Manuel Bernardo Pereira
6. João Ascenso
7. Catarina Brites
8. Yingyan Lin

In Signal Processing

1. Fernando Manuel Bernardo Pereira
2. Vivienne Sze
3. Joel S. Emer
4. Tien-Ju Yang
5. Yu-hsin Chen

Citations in the corpus

• IMPROVING FRAME INTERPOLATION WITH SPATIAL MOTION SMOOTHING FOR PIXEL DOMAIN DISTRIBUTED VIDEO CODING (2005, background): “In this framework, the encoder has a higher computational complexity than the decoder, typically 5 to 10 times more complex [1], specially related to the very computationally consuming motion estimation operations.”
• Efficient Processing of Deep Neural Networks: A Tutorial and Survey (2017, methodology): “sion. Previously, video standards were mostly focused on algorithm development. Going from MPEG-2 to H.264/AVC gave a 2 improvement in coding efficiency at the cost of 4 increase in decoder complexity [110]. More recently, the latest video coding standard H.265/HEVC [111] used co-design of algorithms”