Pith. sign in

REVIEW 6 cited by

Human Motion Modeling using DVGANs

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1804.10652 v2 pith:KU4H5FNA submitted 2018-04-27 cs.CV

Xiao Lin , Mohamed R. Amer This is my paper · ORCID
classification cs.CV
keywords motionhumandiscriminatorgenerationgenerativemodelmodelingactions
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We present a novel generative model for human motion modeling using Generative Adversarial Networks (GANs). We formulate the GAN discriminator using dense validation at each time-scale and perturb the discriminator input to make it translation invariant. Our model is capable of motion generation and completion. We show through our evaluations the resiliency to noise, generalization over actions, and generation of long diverse sequences. We evaluate our approach on Human 3.6M and CMU motion capture datasets using inception scores.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A 7B text-to-motion model trained on the new 2M-clip MotionMillion dataset is reported to generalize zero-shot to complex, out-of-domain prompts.

  2. Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristic

    cs.CV 2025-07 conditional novelty 6.0 of 10

    Adding a soft-transition action bank, an action characteristic bank, and adaptive attention fusion to the WAT baseline improves action-conditioned human motion prediction on four benchmarks.

  3. ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model

    cs.CV 2024-12 reject novelty 6.0 of 10

    The paper reports that normalized test loss in an autoregressive motion generation model follows a logarithmic law with compute budget, and that optimal model size, vocabulary size, and data tokens follow power laws.

  4. Learning Variations in Human Motion via Mix-and-Match Perturbation

    cs.LG 2019-08 conditional novelty 6.0 of 10

    Mix-and-Match perturbation randomly replaces a subset of the RNN hidden state with noise, preventing conditional VAEs from ignoring the latent code and yielding more diverse human motion predictions.

  5. Omni-Supervised Motion Editing: Balancing Change and Invariance through Positive-Negative Learning

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    OmniME integrates retrospective feature supervision, motion preservation, and triplet semantic alignment to achieve state-of-the-art text-motion editing alignment on MotionFix and STANCE datasets.

  6. Strong and Controllable 3D Motion Generation

    cs.CV 2025-01 unverdicted novelty 4.0 of 10

    A project proposal for efficient, joint-controllable text-to-motion generation, with no implemented method or experimental validation.

Pith tools