A Siamese RNN trained with a trajectory-based contrastive loss produces a 3D human motion descriptor that outperforms prior retrieval and recognition embeddings on NTU RGB+D and HDM05.
”Deep signatures for indexing and retrieval in large motion databases.” Conference on Motion in Games, pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DeepHuMS: Deep Human Motion Signature for 3D Skeletal Sequences
A Siamese RNN trained with a trajectory-based contrastive loss produces a 3D human motion descriptor that outperforms prior retrieval and recognition embeddings on NTU RGB+D and HDM05.