mlsanityData to 7 Oct 2026

Video Pixel Networks

arXiv 1610.00527 ↗First posted 3 Oct 2016cs.CV cs.LGcited by 108

Not on the map. Why?

Abstract (arXiv)

We propose a probabilistic video model, the Video Pixel Network (VPN), that estimates the discrete joint distribution of the raw pixel values in a video. The model and the neural architecture reflect the time, space and color structure of video tensors and encode it as a four-dimensional dependency chain. The VPN approaches the best possible performance on the Moving MNIST benchmark, a leap over the previous state of the art, and the generated videos show only minor deviations from the ground truth. The VPN also produces detailed samples on the action-conditional Robotic Pushing benchmark and generalizes to the motion of novel objects.

Key facts. Cited by 108 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Oct 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 33; 2022: 24; 2023: 19; 2024: 13; 2025: 13; 2026: 6.

108 papers.

Sort:

By area:

  1. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  2. 2024Genie: Generative Interactive Environmentscited by 706
  3. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 651
  4. 2023GAIA-1: A Generative World Model for Autonomous Drivingcited by 618
  5. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Modelscited by 463
  6. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
  7. 2023DriveDreamer: Towards Real-world-driven World Models for Autonomous Drivingcited by 258
  8. 2023Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioningcited by 254
  9. 2022Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformercited by 244
  10. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  11. 2022Generating Videos with Dynamics-aware Implicit Generative Adversarial Networkscited by 186
  12. 2024DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generationcited by 186
38 more
  1. 2021PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learningcited by 181
  2. 2022SimVP: Simpler yet Better Video Predictioncited by 181
  3. 2023Video Probabilistic Diffusion Models in Projected Latent Spacecited by 171
  4. 2021DriveGAN: Towards a Controllable High-Quality Neural Simulationcited by 125
  5. 2022Generating Long Videos of Dynamic Scenescited by 113
  6. 2022Reinforcement Learning with Action-Free Pre-Training from Videoscited by 107
  7. 2023TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targetscited by 88
  8. 2021FitVid: Overfitting in Pixel-Level Video Predictioncited by 86
  9. 2022Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learningcited by 84
  10. 2021Greedy Hierarchical Variational Autoencoders for Large-Scale Video Predictioncited by 75
  11. 2023ARTboldsymbol·V: Auto-Regressive Text-to-Video Generation with Diffusion Modelscited by 74
  12. 2023Matryoshka Diffusion Modelscited by 70
  13. 2023Real-Time Radiance Fields for Single-Image Portrait View Synthesiscited by 64
  14. 2021Video Prediction Recalling Long-term Motion Context via Memory Alignment Learningcited by 62
  15. 2025Embodied AI Agents: Modeling the Worldcited by 57
  16. 2025Back to the Features: DINO as a Foundation for Video World Modelscited by 56
  17. 2021MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motionscited by 54
  18. 2026Context Forcing: Consistent Autoregressive Video Generation with Long Contextcited by 47
  19. 2022Temporally Consistent Transformers for Video Generationcited by 43
  20. 2024Efficient Video Diffusion Models via Content-Frame Motion-Latent Decompositioncited by 41
  21. 2021Clockwork Variational Autoencoderscited by 40
  22. 2024Autoregressive Models in Vision: A Surveycited by 39
  23. 2024A Survey on Generative AI and LLM for Video Generation, Understanding, and Streamingcited by 37
  24. 2023Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMscited by 35
  25. 2024VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecastingcited by 35
  26. 2021EarthNet2021: A large-scale dataset and challenge for Earth surface forecasting as a guided video prediction taskcited by 34
  27. 2025Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistencycited by 34
  28. 2022Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generationcited by 32
  29. 2023Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesiscited by 32
  30. 2023SwinLSTM:Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTMcited by 32
  31. 2021iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compressioncited by 27
  32. 2023Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material propertiescited by 23
  33. 2022HARP: Autoregressive Latent Video Prediction with High-Fidelity Image Generatorcited by 22
  34. 2023Vector Quantized Wasserstein Auto-Encodercited by 22
  35. 2022SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learningcited by 20
  36. 2025Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imagingcited by 20
  37. 2024ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Imagescited by 19
  38. 2023MMVP: Motion-Matrix-based Video Predictioncited by 18

50 most cited of 108 All 108 (JSON)