|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
There has been remarkable progress on object detection and re-identification (re-ID) in recent years which are the key components of multi-object tracking.
Ranked #1 on Multi-Object Tracking on MOT16 (using extra training data)
In this paper, we propose an MOT system that allows target detection and appearance embedding to be learned in a shared model.
Ranked #2 on Multi-Object Tracking on MOT16 (using extra training data)
This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video.
Ranked #5 on Pose Tracking on PoseTrack2017 (using extra training data)
Additionally, 3D MOT datasets such as KITTI evaluate MOT methods in the 2D space and standardized 3D MOT evaluation tools are missing for a fair comparison of 3D MOT methods.
Ranked #2 on 3D Multi-Object Tracking on KITTI
We then perform an analysis on the performance and failure cases of several state-of-the-art tracking methods in comparison to our Tracktor.
Ranked #1 on Online Multi-Object Tracking on MOT17
Online multi-object tracking is a fundamental problem in time-critical video analysis applications.
Ranked #2 on Online Multi-Object Tracking on MOT16
In this paper, we bridge this gap by proposing a differentiable proxy of MOTA and MOTP, which we combine in a loss function suitable for end-to-end training of deep multi-object trackers.
Ranked #3 on Multi-Object Tracking on 2D MOT 2015
We introduce associative embedding, a novel method for supervising convolutional neural networks for the task of detection and grouping.
Ranked #5 on Multi-Person Pose Estimation on COCO
We provide a large-scale drone captured dataset, VisDrone, which includes four tracks, i. e., (1) image object detection, (2) video object detection, (3) single object tracking, and (4) multi-object tracking.