Detect-and-Track: Efficient Pose Estimation in Videos

CVPR 2018 Rohit GirdharGeorgia GkioxariLorenzo TorresaniManohar PaluriDu Tran

This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video. We propose an extremely lightweight yet highly effective approach that builds upon the latest advancements in human detection and video understanding... (read more)

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Results from the Paper


Ranked #5 on Pose Tracking on PoseTrack2017 (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Keypoint Detection COCO test-challenge Girdhar et al. AR 70.2 # 6
ARM 60.7 # 7
Pose Tracking PoseTrack2017 ProTracker MOTA 51.82 # 5

Methods used in the Paper