Overview of the H.264/AVC video coding standard

By Thomas Wiegand, Gary J. Sullivan, Gisle Bjøntegaard, Ajay Luthra. 2003

9,164 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

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

In Signal Processing

Citations in the corpus

The latest open-source video codec VP9 - An overview and preliminary results (2013, background): “For each segment it is possible to specify: (1) a quantizer (Q) - absolute value or delta, (2) a loop filter strength (3) a prediction reference frame, and (4) a block skip mode that implies both the use of a (0, 0) motion vector and that no residual is coded.”
3D High-Efficiency Video Coding for Multi-View Video and Depth Data (2013, neutral): “As a result, multi-view video coding (MVC) was standardized as an extension of H.264/MPEG-4 Advanced Video Coding (AVC) [6], [20], [47], [52], [53].”
3-D Video Representation Using Depth Maps (2011, methodology): “MVC is based on the single-view video compression standard H.264/AVC [14], [ 48 ].”
The H.264 Advanced Video Compression Standard (2010, background): “601-6, ‘Studio encoding parameters of digital television for standard 4:3 and widescreen 16:9 aspect ratios’, ITU-R, 2007. ii. ‘High Definition Image Formats for Television Broadcasting’, European Broadcasting Union (EBU) Technical Report 3299, Geneva, 2004. iii. J. Findlay and I. Gilchrist, Active ”
Multi-frame Quality Enhancement for Compressed Video (2018, methodology): “[31], H.264/AVC [39] and HEVC [33].”
Weakly Supervised Semantic Segmentation Using Web-Crawled Videos (2017, methodology): “We utilize reference frames used to compress the video [38] as keyframes for computational efficiency.”
Measuring energy consumption for short code paths using RAPL (2012, background): “[18] suggests splitting video frames into so called slices and decoding slices on the available CPUs.”
Introduction to Data Compression (2005, methodology): “In terms of performance, it claims a 50% reduction in bit rate over previous standards for equivalent perceptual quality [255].”
Analysis and architecture design of an HDTV720p 30 frames/s H.264/AVC encoder (2006, background): “For more details, interested readers can refer to [11]–[13] for a quick and thorough study.”
Algorithm and Architecture Design of Power-Oriented H.264/AVC Baseline Profile Encoder for Portable Devices (2009, positive): “264/AVC can save approximately 50% of bit rate with equivalent visual quality [7] and thus is practical for bandwidth-limited mobile applications.”
Deep learning tools for the measurement of animal behavior in neuroscience (2019, background): “…pipelines should be robust to a myriad of perturbations: such as changes in setups (backgrounds, light sources, cameras, etc.), subject appearance (due to different animal strains), and compression algorithms (which allow storage of perceptually good videos with little memory demands (64)).”
Deep Probabilistic Video Compression (2018, background): “We also provide the performance H.264, H.265, and VP9 codecs (Wiegand et al., 2003; Sullivan et al., 2012; Mukherjee et al., 2015).”
H.264/AVC over IP (2003, methodology): “Calling parameter sets an error-resilience tool is not entirely appropriate—they are generally used in all H.264 bit streams and hence described elsewhere in this special issue [1].”
Intra Coding of the HEVC Standard (2012, methodology): “264/AVC, intra coding is based on spatial extrapolation of samples from previously decoded image blocks, followed by discrete cosine transform (DCT)-based transform coding [2].”
Multi-View Video Plus Depth Representation and Coding (2007, background): “Regarding single view video coding, where prediction is limited to reference pictures in temporal dimension, the concept of hierarchical B pictures (see [11] for a detailed description) has proven to provide high compression efficiency.”