SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.08534 · CVPR · 2022

Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video

Tyng-Luh Liu, Wen-Li Wei, Jen-Chun Lin, Hong-Yuan Liao, Mark Liao

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.

Abstract

Figure 1. By coupling motion continuity attention with hierarchical attentive feature integration, the proposed MPS-Net can achieve more accurate pose and shape estimations (bottom row), when dealing with in-the-wild videos. For comparison, the results (top row) obtained by TCMR [6], the state-of-the-art video-based 3D human pose and shape estimation method, are included.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.08534")
get_code_for_paper("2203.08534")
have("2203.08534")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.08534.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.08534.svg)](https://syntology.ai/paper/2203.08534)

Connect an agent — have() is free.