Tracking Without Bells and Whistles

@article{Bergmann2019TrackingWB,
  title={Tracking Without Bells and Whistles},
  author={Philipp Bergmann and Tim Meinhardt and Laura Leal-Taix{\'e}},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={941-951}
}
The problem of tracking multiple objects in a video sequence poses several challenging tasks. [...] Key Method To this end, we exploit the bounding box regression of an object detector to predict the position of an object in the next frame, thereby converting a detector into a Tracktor. We demonstrate the potential of Tracktor and provide a new state-of-the-art on three multi-object tracking benchmarks by extending it with a straightforward re-identification and camera motion compensation. We then perform an…Expand

Paper Mentions

News Article
Multi-Object Tracking with Siamese Track-RCNN
TLDR
Siamese Track-RCNN is proposed, a two stage detect-and-track framework which consists of three functional branches: the detection branch localizes object instances; the Siamese-based track branch estimates the object motion and the object re-identification branch re-activates the previously terminated tracks when they re-emerge. Expand
Localization-Based Tracking
TLDR
This work presents Localization-based Tracking (LBT), an extension to any tracker that follows the tracking by detection or joint detection and tracking paradigms, which outperform all other reported algorithms in terms of PRMOTA, PR-MOTP, and mostly tracked objects on the UADETRAC benchmark, establishing a new state-of-the art. Expand
Compact and discriminative multi-object tracking with siamese CNNs
TLDR
This work proposes a fast, lightweight tracker able to predict targets position and reidentify them at once, when it is usually done with two sequential steps, and proposes a tracks management strategy able to balance efficiently between detection and tracking outputs and their associated likelihoods. Expand
Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking
TLDR
A probabilistic autoregressive motion model is introduced to score tracklet proposals by directly measuring their likelihood, achieved by training the model to learn the underlying distribution of natural tracklets. Expand
Multi-object Tracking with Tracked Object Bounding Box Association
  • Nanyang Yang, Yi Wang, Lap-Pui Chau
  • Computer Science
  • 2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)
  • 2021
TLDR
This paper proposes to incorporate a simple tracked object bounding box and overlapping prediction based on the current frame onto the CenterTrack algorithm and proposes an Intersection over Union (IOU) distance cost matrix in the association step instead of simple point displacement distance. Expand
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
  • Yifu Zhang, Peize Sun, +5 authors Xinggang Wang
  • Computer Science
  • ArXiv
  • 2021
TLDR
A simple, effective and generic association method, tracking by associating every detection box instead of only the high score ones, for the low score detection boxes, to recover true objects and filter out the background detections. Expand
SiamMT: Real-Time Arbitrary Multi-Object Tracking
TLDR
This work presents the architecture of SiamMT, a system capable of efficiently applying individual visual tracking techniques to multiple objects in real-time, and makes it the first deep-learning-based arbitrary multi-object tracker. Expand
Faster object tracking pipeline for real time tracking
TLDR
This paper finds that the tracking by detection paradigm can be made faster by performing localization and association tasks parallely with model prediction, and other computational optimizations such as using mixed precision model and performing batchwise detection result in a speed-up of the tracking pipeline by 57.8%. Expand
Learning to Track with Object Permanence
TLDR
This work introduces an end-to-end trainable approach for joint object detection and tracking that outperforms the state of the art on KITTI, and MOT17 datasets thanks to its robustness to occlusions. Expand
Two is a crowd: tracking relations in videos
TLDR
This paper proposes a plug-in Relation Encoding Module (REM), which allows for tracking severely or even fully occluded objects by utilizing relational cues and aims to employ heavy and persistent overlap with the partner rather than rejecting that information. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 79 REFERENCES
Joint tracking and segmentation of multiple targets
TLDR
This work proposes a multi-target tracker that exploits low level image information and associates every (super)-pixel to a specific target or classifies it as background and obtains a video segmentation in addition to the classical bounding-box representation in unconstrained, real-world videos. Expand
Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking
TLDR
The current trends and weaknesses of multiple people tracking methods are shown, and pointers of what researchers should be focusing on to push the field forward are provided. Expand
Detect to Track and Track to Detect
TLDR
This paper sets up a ConvNet architecture for simultaneous detection and tracking, using a multi-task objective for frame-based object detection and across-frame track regression, and introduces correlation features that represent object co-occurrences across time to aid the ConvNet during tracking. Expand
Improvements to Frank-Wolfe optimization for multi-detector multi-object tracking
TLDR
This paper proposes a novel formulation for the multiobject tracking-by-detection paradigm for two (or more) input detectors, using full-body and heads detections, and approximate the solution using the Frank-Wolfe algorithm. Expand
MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
TLDR
With MOTChallenge, the work toward a novel multiple object tracking benchmark aimed to address issues of standardization, and the way toward a unified evaluation framework for a more meaningful quantification of multi-target tracking is described. Expand
Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering
TLDR
This work states this joint problem as a co-clustering problem that is principled and tractable by existing algorithms, and demonstrates the effectiveness of this approach by combining bottom-up motion segmentation by grouping of point trajectories with high-level multiple object tracking by clustering of bounding boxes. Expand
Multiple Object Tracking Using K-Shortest Paths Optimization
TLDR
This paper shows that reformulating that step as a constrained flow optimization results in a convex problem and takes advantage of its particular structure to solve it using the k-shortest paths algorithm, which is very fast. Expand
Multiple Hypothesis Tracking Revisited
TLDR
It is demonstrated that a classical MHT implementation from the 90's can come surprisingly close to the performance of state-of-the-art methods on standard benchmark datasets, and it is shown that appearance models can be learned efficiently via a regularized least squares framework. Expand
Real-Time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification
TLDR
This paper proposes to handle unreliable detection by collecting candidates from outputs of both detection and tracking, and adopts a deeply learned appearance representation, which is trained on large-scale person re-identification datasets, to improve the identification ability of the tracker. Expand
Multiple Target Tracking in World Coordinate with Single, Minimally Calibrated Camera
TLDR
A novel algorithm for multi-object tracking that is capable of working under very challenging conditions such as minimal hardware equipment, uncalibrated monocular camera, occlusions and severe background clutter is proposed. Expand
...
1
2
3
4
5
...