HuM-Eval evaluates human motion videos with a coarse-to-fine approach using VLM global checks plus 2D pose and 3D motion analysis, reaching 58.2% average correlation with human judgments and introducing a 1000-prompt benchmark.
Vm- bench: A benchmark for perception-aligned video motion generation
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
Introduces a lightweight temporal module to extend pretrained DiT video models with time editing capabilities while preserving the original generative prior.
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
citing papers explorer
-
HuM-Eval: A Coarse-to-Fine Framework for Human-Centric Video Evaluation
HuM-Eval evaluates human motion videos with a coarse-to-fine approach using VLM global checks plus 2D pose and 3D motion analysis, reaching 58.2% average correlation with human judgments and introducing a 1000-prompt benchmark.
-
Making Time Editable in Video Diffusion Transformers
Introduces a lightweight temporal module to extend pretrained DiT video models with time editing capabilities while preserving the original generative prior.
-
Evolution of Video Generative Foundations
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
- ROBOSHACKLES: A Safety Dataset for Human-Injury Prevention in Embodied Foundation Models