Adversarial Video Generation on Complex Datasets

By Aidan Clark, Jeff Donahue, Karen Simonyan. 2019

282 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Generative Models

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 Generative Models

Citations in the corpus

VideoGPT: Video Generation using VQ-VAE and Transformers (2021, neutral): “, 2018), TGAN-F (Kahembwe & Ramamoorthy, 2020), TGANv2 (Saito & Saito, 2018), DVD-GAN (Clark et al., 2019) are our baselines for IS on UCF-101.”
High Fidelity Speech Synthesis with Adversarial Networks (2019, positive): “…GANs have achieved state-of-the-art results in image (Zhang et al., 2019; Brock et al., 2019; Karras et al., 2019) and video generation (Clark et al., 2019), and have been successfully applied for unsupervised feature learning (Donahue et al., 2017; Dumoulin et al., 2017a; Donahue &…”
LOGAN: Latent Optimisation for Generative Adversarial Networks (2019, background): “…including representation learning and inference (Donahue et al., 2017; Dumoulin et al., 2017), text generation (Zhang et al., 2019), style learning (Zhu et al., 2017; Karras et al., 2019), audio generation (Donahue et al., 2018) and video generation (Vondrick et al., 2016; Clark et al., 2019).”
Video Diffusion Models (2022, background): “Method FVD ↓ DVD-GAN [14] 109.8 VideoGPT [62] 103.3 TrIVD-GAN-FP [33] 103.3 Transframer [35] 100 CCVS [31] 99 VideoTransformer [59] 94 FitVid [4] 93.6 NUWA [61] 86.9 Video Diffusion (ours) ancestral sampler, 512 steps 68.19 Langevin sampler, 256 steps 66.92 Table 3: Video prediction on Kinetics-600.”
Motion Representations for Articulated Animation (2021, methodology): “Video-generation-based animation methods predict future frames of a video, given the first frame and an animation class label, such as “make a happy face”, “do jumping jack”, or “play golf” [33, 26, 7].”
Stochastic Image-to-Video Synthesis using cINNs (2021, methodology): “Similar to previous work [15, 79], we use a discriminator DS applied”
Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer (2022, methodology): “, 16 frames, like the previous methods [71,55,67,12,56,65].”
SimVP: Simpler yet Better Video Prediction (2022, methodology): “These methods achieve impressive performance gain by introducing novel neural operators like various RNNs [65–69,71] or transformers [48,70], delicate architectures like autoregressive [21,28,49,55,71] or normalizing flow [73], and applying distinct training strategies such as adversarial training [”
StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2 (2021, unknown): “1 In this work, we argue that this design choice is not optimal and propose to treat videos in their natural form: as continuous signals x ( t ) , that map any time coordinate 1 E.g., DVD-GAN [13] requires ≈ $30 k to train on 256 2 Figure 2.”
CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers (2022, methodology): “Previous works followed this basic framework [35, 9], e.g. VideoGPT [36], verifying its superiority over GAN-based methods [4, 26], but are still far from satisfactory.”
A Review on Deep Learning Techniques for Video Prediction (2020, methodology): “Relying on kernel-based transformations and improving [163], Luc et al.”
Predicting Video with VQVAE (2021, methodology): “We ﬁnd performance exceeds [7] but not necessarily [27].”
Transframer: Arbitrary Frame Prediction with Generative Models (2022, methodology): “We use the same experimental set-up as DVD-GAN [10], operating at 64×64 resolution, and generate 11 frames given 5 context frames.”
LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models (2023, unknown): “The Bund, Shanghai, with the ship moving on the river, oil painting.”
A Survey on Generative Adversarial Networks: Variants, Applications, and Training (2020, methodology): “Dual Video Discriminator GAN (DVD-GAN) [165] framework generates high-resolution videos of comparatively high reliability.”