Motion Captioning
4 papers with code • 2 benchmarks • 2 datasets
Generating textual description for human motion.
Most implemented papers
MotionGPT: Human Motion as a Foreign Language
Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language.
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts
Our approach is flexible, could be used for both text2motion and motion2text tasks.
Guided Attention for Interpretable Motion Captioning
While much effort has been invested in generating human motion from text, relatively few studies have been dedicated to the reverse direction, that is, generating text from motion.
Motion2Language, unsupervised learning of synchronized semantic motion segmentation
We find that both contributions to the attention mechanism and the encoder architecture additively improve the quality of generated text (BLEU and semantic equivalence), but also of synchronization.