mlsanityData to 14 Oct 2026

ArrowGAN : Learning to Generate Videos by Learning Arrow of Time

arXiv 2101.03710 ↗First posted 11 Jan 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Training GANs on videos is even more sophisticated than on images because videos have a distinguished dimension: time. While recent methods designed a dedicated architecture considering time, generated videos are still far from indistinguishable from real videos. In this paper, we introduce ArrowGAN framework, where the discriminators learns to classify arrow of time as an auxiliary task and the generators tries to synthesize forward-running videos. We argue that the auxiliary task should be carefully chosen regarding the target domain. In addition, we explore categorical ArrowGAN with recent techniques in conditional image generation upon ArrowGAN framework, achieving the state-of-the-art performance on categorical video generation. Our extensive experiments validate the effectiveness of arrow of time as a self-supervisory task, and demonstrate that all our components of categorical ArrowGAN lead to the improvement regarding video inception score and Frechet video distance on three datasets: Weizmann, UCFsports, and UCF-101.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 37 of its 52 references that are in the map. First posted on arXiv 11 Jan 2021.

Builds on

37 of 52 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  5. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  6. 2016Improved Techniques for Training GANscited by 2,970
  7. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  8. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  9. 2014Conditional Generative Adversarial Netscited by 2,162
  10. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  11. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  12. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,234
25 more
  1. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,066
  2. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  3. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 524
  4. 2018Video-to-Video Synthesiscited by 390
  5. 2016Generating Videos with Scene Dynamicscited by 376
  6. 2016A Learned Representation For Artistic Stylecited by 341
  7. 2018Everybody Dance Nowcited by 315
  8. 2017Are GANs Created Equal? A Large-Scale Studycited by 267
  9. 2016Unsupervised Learning for Physical Interaction through Video Predictioncited by 260
  10. 2018cGANs with Projection Discriminatorcited by 254
  11. 2018Stochastic Video Generation with a Learned Priorcited by 245
  12. 2017Stochastic Variational Video Predictioncited by 234
  13. 2017Unsupervised Representation Learning by Sorting Sequencescited by 221
  14. 2016Temporal Generative Adversarial Nets with Singular Value Clippingcited by 198
  15. 2017Modulating early visual processing by languagecited by 167
  16. 2019Temporal Cycle-Consistency Learningcited by 154
  17. 2019Mode Seeking Generative Adversarial Networks for Diverse Image Synthesiscited by 138
  18. 2018Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GANcited by 120
  19. 2018Self-Supervised GANs via Auxiliary Rotation Losscited by 94
  20. 2014Video (language) modeling: a baseline for generative models of natural videoscited by 92
  21. 2019Diversity-Sensitive Conditional Generative Adversarial Networkscited by 77
  22. 2018Self-Supervised Spatiotemporal Feature Learning via Video Rotation Predictioncited by 71
  23. 2019Video Generation from Single Semantic Label Mapcited by 54
  24. 2018Probabilistic Video Generation using Holistic Attribute Controlcited by 24
  25. 2020Non-Adversarial Video Synthesis with Learned Priorscited by 13

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 1.

4 papers.

  1. 2021FitVid: Overfitting in Pixel-Level Video Predictioncited by 87
  2. 2021StyleVideoGAN: A Temporal Generative Model using a Pretrained StyleGANcited by 47
  3. 2022Long-horizon video prediction using a dynamic latent hierarchycited by 4
  4. 2021Continuous Face Aging Generative Adversarial Networkscited by 0