16th June 2019, Long Beach, CA, USA
In Conjunction with the Conference on Computer Vision and Pattern Recognition, CVPR 2019
Workshops presentations

CVPR 2019 dataset and challenges: Download

Georgia Gkioxari - Facebook AI Research :
Beyond 2D Object Recognition: Understanding Objects in Space and Time: Download

Paul Voigtlaender - RWTH Aachen, Germany:
MOTS: Multi-Object Tracking and Segmentation: Download
Ground truth video:
TrackR-CNN results video:

Tracking and Detection Challenges 2019

For this 4th edition of our Benchmarking Multi-Target Tracking (MOTChallenge) Workshop, we want to push the limits of both detectors and trackers with the introduction of the MOT19 benchmark. Following the strict annotation protocols of MOT16 and MOT17, we will introduce 7 challenging extremely crowded scenes, with over 150 pedestrians per frame on average. The sequences are also much longer than previous editions, reaching up to 3500 frames.

The data will contain 3 splits in order to create a separate detection challenge as well as a tracking challenge. The MOTChallenge submission system will be updated to accept the new detector as input for the trackers. Our workshop has three major goals: (i) Analyzing the performance of state-of-the-art detectors and trackers on very crowded scenes, (ii) opening new detection and tracking challenges on 7 new crowded sequences, and (iii) discussing the limitation of current methods when the density of pedestrian increases. An important part of the workshop will also be dedicated to a discussion among participants on how to improve multi-target tracking evaluation and ideas on how to expand the current benchmark. These discussions in previous editions of the workshop have helped us tremendously in shaping MOTChallenge and significantly contributed to creating a widely used and perhaps the most popular multi-object tracking benchmark in the community.


We have 2 exciting challenges for the fourth edition of the BMTT MOTChallenge workshop!

  • Challenge 1: Detection in very crowded scenarios
  • Challenge 2: Tracking in very crowded scenarios
Call for Papers

This is the Call for Papers for the 4th BMTT MOTChallenge Workshop on Tracking and Surveillance, held in conjunction with the Conference on Computer Vision and Pattern Recognition (CVPR) 2019 in Long Beach, CA, USA.

We are looking forward to welcoming researchers and industry affiliates in computer vision, machine learning, image analysis and related fields, to present and discuss their work. A single-track program with keynote talks, oral and poster presentations shall provide ample opportunities for scientific exchange and discussion.

BMTT MOTChallenge 2019 invites submissions of high-quality research results as full papers.

Full-paper submissions will undergo a selective double-blind peer-review process, normally by three members of the international reviewing committee. Submitted papers will be refereed on their scientific originality and relevance, presentation and empirical results. For details on formatting, submission and paper policies please see the instructions for authors.

Topics include, but are not limited to:

  • Detection for tracking
  • Multi-target tracking
  • Video segmentation
  • Visual surveillance and tracking in crowded scenes
  • Motion prediction and social models
  • Abnormal activity recognition
  • Multi-class tracking and holistic scene understanding
  • Evaluation criteria and metrics for multi-target tracking
  • Action/pose recognition
  • Motion trajectory analysis
  • Human walking behavior
  • Maritime abnormal event detection
  • Activity analysis and monitoring
  • Multi-camera analysis
  • Interaction/sequential analysis
  • Event detection
  • Indexing and retrieval of human behaviors in video sequences
  • Visual feature extraction
  • Behaviour and ambient intelligence
  • Context analysis
  • Learning models and evaluation
  • Dataset proposals and bias analysis

Submission to the challenge is independent from the paper submission, but we encourage paper authors to submit to one of the challenges. For more details, please visit the website for each of the challenges.

As organizers of BMTT MOTChallenge 2019 we are looking forward to your contributions and to welcoming you in Long Beach.

Laura Leal-Taixé
Hamid Rezatofighi
Anton Milan
Javen Shi
Konrad Schindler
Patrick Dendorfer
Daniel Cremers
Stefan Roth
Ian Reid

Call for Participation

The BMTT MOTChallenge 2019 Detection and Tracking Challenges will be announced soon! Stay tuned.

This workshop is part of

Participating institutions