Source Themes

Humble Teacher and Eager Student: Dual Network Learning for Semi-supervised 2D Human Pose Estimation

Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. The state-of-the-art methods are consistency-based which learn about unlabeled images by encouraging the model to give consistent predictions for images …

VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment

We present an approach to estimate 3D poses of multiple people from multiple camera views.

Locally Connected Network for Monocular 3D Human Pose Estimation

We propose a method for estimating 3D human poses from single images.

FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking

This is a real-time multi-object tracker that ranks first in many MOT evaluation datasets.

Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approach

We present a novel way of using IMUs for human pose estimation.

MetaFuse: A Pre-trained Fusion Model for Human Pose Estimation

We introduce MetaFuse, a pre-trained fusion model learned from a large number of cameras in the Panoptic dataset.

Semantic Image Segmentation by Scale-Adaptive Networks

Semantic image segmentation is an important yet unsolved problem. One of the major challenges is the large variability of the object scales. To tackle this scale problem, we propose a Scale-Adaptive network (SAN) which consists of multiple branches with each one taking charge of the segmentation of the objects of a certain range of scales. Given an image, SAN first computes a dense scale map indicating the scale of each pixel which is automatically determined by the size of the enclosing object. Then the features of different branches are fused according to the scale map to generate the final segmentation map. To ensure that each branch indeed learns the features for a certain scale, we propose a scale-induced ground-truth map and enforce a scale-aware segmentation loss for the corresponding branch in addition to the final loss. Extensive experiments over the PASCAL-Person-Part, the PASCAL VOC 2012, and the Look into Person datasets demonstrate that our SAN can handle the large variability of the object scales and outperforms the stateof-the-art semantic segmentation methods.

Cross View Fusion for 3D Human Pose Estimation

We address the problem of recovering absolute 3D human poses from multi-view images by incorporating multi-view geometric priors into our model.

Optimizing Network Structure for 3D Human Pose Estimation

We propose Locally Connected Network for 3D human pose estimation. It extracts and propagates features over the pose graph and can naturally deal with poses where only partial joints are visible.

Object detection in videos by high quality object linking

we focus on obtaining high quality object linking results for better classification. Unlike previous methods that link objects by checking boxes between neighboring frames, we propose to link in the same frame.