Human-like Guidance by Generating Navigation Using Spatial-Temporal Scene Graph.
Hayato SuzukiKota ShimomuraTsubasa HirakawaTakayoshi YamashitaHironobu FujiyoshiShota OkuboNanri TakuyaWang SiyuanPublished in: IV (2024)
Keyphrases
- spatial temporal
- action recognition
- temporal information
- spatial and temporal
- video sequences
- video shots
- spatio temporal
- image sequences
- human actions
- computer vision
- spatial relations
- three dimensional
- spatial information
- context aware
- image features
- object recognition
- visual data
- e learning
- machine learning
- spatial and temporal information