Heatmap Distribution Matching for Human Pose Estimation
Nov 28, 2022
Speakers
Haoxuan Qu
Speaker · 0 followers
Lin Geng Foo
Speaker · 0 followers
About
For tackling the task of 2D human pose estimation, the great majority of the recent methods regard this task as a heatmap estimation problem, and optimize the heatmap prediction using the Gaussian-smoothed heatmap as the optimization objective. In this paper, we show that using the Gaussian-smoothed heatmap as the optimization objective, the model performance of body joint localization, which is the intrinsic objective of this task, may not be consistently improved during the optimization process of the heatmap prediction. To address this problem, from a novel perspective, we propose to formulate the optimization of the heatmap prediction as a distribution matching problem between the predicted heatmap and the dot annotation of the body joint directly. By doing so, our proposed method bypasses the step of constructing the Gaussian-smoothed heatmap and can achieve a more consistent model performance improvement during the optimization of the heatmap prediction. We show the effectiveness of our proposed method through extensive experiments on the COCO dataset and the MPII dataset.For tackling the task of 2D human pose estimation, the great majority of the recent methods regard this task as a heatmap estimation problem, and optimize the heatmap prediction using the Gaussian-smoothed heatmap as the optimization objective. In this paper, we show that using the Gaussian-smoothed heatmap as the optimization objective, the model performance of body joint localization, which is the intrinsic objective of this task, may not be consistently improved during the optimization proces…
Organizer
NeurIPS 2022
Account · 952 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Robust Model Selection and Nearly-Proper Learning for GMMs
Watch later
Allen Liu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning Counterfactually Invariant Predictors
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
The Lakota AI Code Camp
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Task-Free Continual Learning via Online Discrepancy Distance Learning
Watch later
Fei Ye, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Diffusion Curvature for Estimating Local Curvature in High Dimensional Data
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Bayesian Risk Markov Decision Processes
Watch later
Yifan Lin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%