mlsanityData to 7 Oct 2026

Temporal Context Mining for Learned Video Compression

arXiv 2111.13850 ↗First posted 27 Nov 2021cs.CV cs.LG eess.IVcited by 112

Not on the map. Why?

Abstract (arXiv)

We address end-to-end learned video compression with a special focus on better learning and utilizing temporal contexts. For temporal context mining, we propose to store not only the previously reconstructed frames, but also the propagated features into the generalized decoded picture buffer. From the stored propagated features, we propose to learn multi-scale temporal contexts, and re-fill the learned temporal contexts into the modules of our compression scheme, including the contextual encoder-decoder, the frame generator, and the temporal context encoder. Our scheme discards the parallelization-unfriendly auto-regressive entropy model to pursue a more practical decoding time. We compare our scheme with x264 and x265 (representing industrial software for H.264 and H.265, respectively) as well as the official reference software for H.264, H.265, and H.266 (JM, HM, and VTM, respectively). When intra period is 32 and oriented to PSNR, our scheme outperforms H.265--HM by 14.4% bit rate saving; when oriented to MS-SSIM, our scheme outperforms H.266--VTM by 21.1% bit rate saving.

Key facts. Cited by 112 papers in the map (data through 7 Oct 2026). Builds on 32 of its 62 references that are in the map. First posted on arXiv 27 Nov 2021.

Builds on

32 of 62 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  3. 2018Variational image compression with a scale hyperpriorcited by 910
  4. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  5. 2017Video Enhancement with Task-Oriented Flowcited by 612
  6. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  7. 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 421
  8. 2020CompressAI: a PyTorch library and evaluation platform for end-to-end compression researchcited by 271
  9. 2021Deep Contextual Video Compressioncited by 216
  10. 2021FVC: A New Framework towards Deep Video Compression in Feature Spacecited by 149
  11. 2018Video Compression through Image Interpolationcited by 143
  12. 2020M-LVC: Multiple Frames Prediction for Learned Video Compressioncited by 106
20 more
  1. 2019Video Compression With Rate-Distortion Autoencoderscited by 97
  2. 2020Learning for Video Compression with Hierarchical Quality and Recurrent Enhancementcited by 90
  3. 2018Learned Video Compressioncited by 89
  4. 2019Image and Video Compression with Neural Networks: A Reviewcited by 82
  5. 2020Content Adaptive and Error Propagation Aware Deep Video Compressioncited by 72
  6. 2020Causal Contextual Prediction for Learned Image Compressioncited by 70
  7. 2021ELF-VC: Efficient Learned Flexible-Rate Video Codingcited by 68
  8. 2020Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Modelcited by 67
  9. 2020Improving Deep Video Compression by Resolution-adaptive Flow Codingcited by 58
  10. 2020BVI-DVC: A Training Database for Deep Video Compressioncited by 47
  11. 2020Conditional Entropy Coding for Efficient Video Compressioncited by 42
  12. 2020Neural Video Coding using Multiscale Motion Compensation and Spatiotemporal Context Modelcited by 38
  13. 2021Perceptual Learned Video Compression with Recurrent Conditional GANcited by 38
  14. 2021Neural Video Compression using GANs for Detail Synthesis and Propagationcited by 35
  15. 2019Learned Video Compression via Joint Spatial-Temporal Correlation Explorationcited by 28
  16. 2020Hierarchical Autoregressive Modeling for Neural Video Compressioncited by 28
  17. 2018Learning for Video Compressioncited by 26
  18. 2019Learning Image and Video Compression through Spatial-Temporal Energy Compactioncited by 26
  19. 2020Multi-level Wavelet-based Generative Adversarial Network for Perceptual Quality Enhancement of Compressed Videocited by 26
  20. 2020Learned Video Compression with Feature-level Residualscited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 5; 2023: 15; 2024: 35; 2025: 31; 2026: 24.

112 papers.

Sort:

By area:

  1. 2024HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compressioncited by 202
  2. 2023Neural Video Compression with Diverse Contextscited by 155
  3. 2022Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compressioncited by 123
  4. 2024Neural Video Compression with Feature Modulationcited by 115
  5. 2025Improving the Diffusability of Autoencoderscited by 74
  6. 2025Towards Practical Real-Time Neural Video Compressioncited by 72
  7. 2023HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representationcited by 70
  8. 2023C3: High-performance and low-complexity neural compression from a single image or videocited by 54
  9. 2023DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videoscited by 42
  10. 2024USTC-TD: A Test Dataset and Benchmark for Image and Video Coding in 2020scited by 37
  11. 2024How Far Can We Compress Instant-NGP-Based NeRF?cited by 30
  12. 2024Boosting Neural Representations for Videos with a Conditional Decodercited by 29
38 more
  1. 2022AlphaVC: High-Performance and Efficient Learned Video Compressioncited by 28
  2. 20254DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Videocited by 26
  3. 2025Linear Attention Modeling for Learned Image Compressioncited by 22
  4. 2024Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compressioncited by 21
  5. 2025Generative Latent Coding for Ultra-Low Bitrate Image Compressioncited by 21
  6. 2024Bi-Directional Deep Contextual Video Compressioncited by 20
  7. 2022B-CANF: Adaptive B-frame Coding with Conditional Augmented Normalizing Flowscited by 18
  8. 2023Offline and Online Optical Flow Enhancement for Deep Video Compressioncited by 17
  9. 2025Neural Video Compression with Context Modulationcited by 15
  10. 2023VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Visioncited by 13
  11. 2021Learning Cross-Scale Weighted Prediction for Efficient Neural Video Compressioncited by 12
  12. 2022Neighbor Correspondence Matching for Flow-based Video Frame Synthesiscited by 12
  13. 2023IBVC: Interpolation-driven B-frame Video Compressioncited by 12
  14. 2024Group-aware Parameter-efficient Updating for Content-Adaptive Neural Video Compressioncited by 12
  15. 2025Conditional Latent Coding with Learnable Synthesized Reference for Deep Image Compressioncited by 10
  16. 2022Bit Allocation using Optimizationcited by 9
  17. 2023Towards Real-Time Neural Video Codec for Cross-Platform Application Using Calibration Informationcited by 9
  18. 2025DiffVC-OSD: One-Step Diffusion-based Perceptual Neural Video Compression Frameworkcited by 9
  19. 2025Augmented Deep Contexts for Spatially Embedded Video Codingcited by 8
  20. 2025Single-step Diffusion-based Video Coding with Semantic-Temporal Guidancecited by 8
  21. 2023High Visual-Fidelity Learned Video Compressioncited by 7
  22. 2024UCVC: A Unified Contextual Video Compression Framework with Joint P-frame and B-frame Codingcited by 6
  23. 2024Task-Aware Encoder Control for Deep Video Compressioncited by 6
  24. 2024CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesiscited by 6
  25. 2024Benchmarking Conventional and Learned Video Codecs with a Low-Delay Configurationcited by 6
  26. 2025EHVC: Efficient Hierarchical Reference and Quality Structure for Neural Video Codingcited by 6
  27. 2023Learned Scalable Video Coding For Humans and Machinescited by 5
  28. 2024Generative Human Video Compression with Multi-granularity Temporal Trajectory Factorizationcited by 5
  29. 2025An Efficient Adaptive Compression Method for Human Perception and Machine Vision Taskscited by 5
  30. 2025Neural B-frame Video Compression with Bi-directional Reference Harmonizationcited by 5
  31. 2021Learning-Based Video Coding with Joint Deep Compression and Enhancementcited by 4
  32. 2023Accelerating Learnt Video Codecs with Gradient Decay and Layer-wise Distillationcited by 4
  33. 2024STanH : Parametric Quantization for Variable Rate Learned Image Compressioncited by 4
  34. 2024Rendering-Oriented 3D Point Cloud Attribute Compression using Sparse Tensor-based Transformercited by 4
  35. 2024Hybrid Local-Global Context Learning for Neural Video Compressioncited by 4
  36. 2023Butterfly: Multiple Reference Frames Feature Propagation Mechanism for Neural Video Compressioncited by 3
  37. 2024Prediction and Reference Quality Adaptation for Learned Video Compressioncited by 3
  38. 2024Hierarchical B-frame Video Coding for Long Group of Picturescited by 3

50 most cited of 112 All 112 (JSON)