paper-with-me

Papers

Compositional Human Pose Regression

2017-04-01 · ICCV 2017 10 · Xiao Sun, Jiaxiang Shang, Shuang Liang, Yichen Wei

Regression based methods are not performing as well as detection based methods for human pose estimation. A central problem is that the structural information in the pose is not well exploited in the previous regression methods. In this work, we propose a structure-aware regression approach. It adopts a reparameterized pose representation using bones instead of joints. It exploits the joint connection structure to define a compositional loss function that encodes the long range interactions in the pose. It is simple, effective, and general for both 2D and 3D pose estimation in a unified setting. Comprehensive evaluation validates the effectiveness of our approach. It significantly advances the state-of-the-art on Human3.6M and is competitive with state-of-the-art results on MPII.

📄 PDF Abstract BibTeX arXiv:1704.00159

Code (1)

anibali/h36m-fetch

Tasks

3D Human Pose Estimation3D Pose EstimationPose Estimationregression

Similar Papers 제목 키워드 기반

Probing the Compositionality of Intuitive Functions

2016-12-01 · NeurIPS 2016 12 · Eric Schulz, Josh Tenenbaum, David K. Duvenaud, Maarten Speekenbrink 외

How do people learn about complex functional structure? Taking inspiration from other areas of cognitive science, we propose that this is accomplished by harnessing compositionality: complex structure is decomposed into …

regression

Primal path algorithm for compositional data analysis

2018-12-21 · Jong-June Jeon, Yongdai Kim, Sungho Won, Hosik Choi

Compositional data have two unique characteristics compared to typical multivariate data: the observed values are nonnegative and their summand is exactly one. To reflect these characteristics, a specific regularized reg…

General Classificationregression

On the inability of Gaussian process regression to optimally learn compositional functions

2022-05-16 · Matteo Giordano, Kolyan Ray, Johannes Schmidt-Hieber

We rigorously prove that deep Gaussian process priors can outperform Gaussian process priors if the target function has a compositional structure. To this end, we study information-theoretic lower bounds for posterior co…

regression

Multi-Step Regression Learning for Compositional Distributional Semantics

2013-03-01 · WS 2013 3 · E. Grefenstette, G. Dinu, Y. Zhang, M. Sadrzadeh 외
regression

Resolving Lexical Ambiguity in Tensor Regression Models of Meaning

2014-08-26 · ACL 2014 6 · Dimitri Kartsaklis, Nal Kalchbrenner, Mehrnoosh Sadrzadeh

This paper provides a method for improving tensor-based compositional distributional models of meaning by the addition of an explicit disambiguation step prior to composition. In contrast with previous research where thi…

regression