Gen4D creates diverse and photorealistic synthetic sports videos from text and estimated motion, producing the SportPAL dataset for training human pose estimation models.
Seeing beyond the crop: Using language priors for out-of-bounding box key- point prediction.Advances in Neural Information Processing Systems, 37:102897–102918, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.GR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Gen4D: Synthesizing Humans and Scenes in the Wild
Gen4D creates diverse and photorealistic synthetic sports videos from text and estimated motion, producing the SportPAL dataset for training human pose estimation models.