Language-Driven 3D Human Pose Estimation in Multi-Person Scenarios: A New Dataset and Approach
Open Access
- 27 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 12761-12768
Abstract
No abstract availableThis publication has 30 references indexed in Scilit:
- ChatPose: Chatting about 3D Human Pose2024
- End-to-End Referring Video Object Segmentation with Multimodal Transformers2022
- Putting People in their Place: Monocular Regression of 3D People in Depth2022
- Video Swin Transformer2022
- Action Transformer: A self-attention model for short-time pose-based human action recognitionPattern Recognition, 2022
- One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing2021
- SMAP: Single-Shot Multi-person Absolute 3D Pose Estimation2020
- Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition2020
- 3D Human Pose Estimation in Video With Temporal Convolutions and Semi-Supervised Training2019
- Deep Residual Learning for Image Recognition2016