About

Object tracking is the task of taking an initial set of object detections, creating a unique ID for each of the initial detections, and then tracking each of the objects as they move around frames in a video, maintaining the ID assignment.

( Image credit: Towards-Realtime-MOT )

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Subtasks

Datasets

Greatest papers with code

Unsupervised Learning of Object Structure and Dynamics from Videos

NeurIPS 2019 google-research/google-research

Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning.

ACTION RECOGNITION CONTINUOUS CONTROL OBJECT TRACKING VIDEO PREDICTION

SMOT: Single-Shot Multi Object Tracking

30 Oct 2020dmlc/gluon-cv

We combine this scheme with SSD detectors by proposing a novel tracking anchor assignment module.

MULTI-OBJECT TRACKING

Fast Online Object Tracking and Segmentation: A Unifying Approach

CVPR 2019 foolwood/SiamMask

In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach.

REAL-TIME VISUAL TRACKING SEMI-SUPERVISED SEMANTIC SEGMENTATION SEMI-SUPERVISED VIDEO OBJECT SEGMENTATION VISUAL OBJECT TRACKING

Simple Online and Realtime Tracking with a Deep Association Metric

21 Mar 2017nwojke/deep_sort

Simple Online and Realtime Tracking (SORT) is a pragmatic approach to multiple object tracking with a focus on simple, effective algorithms.

LARGE-SCALE PERSON RE-IDENTIFICATION MULTIPLE OBJECT TRACKING VIDEO INSTANCE SEGMENTATION

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

4 Apr 2020ifzhang/FairMOT

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)

FAIRNESS MULTI-OBJECT TRACKING MULTIPLE OBJECT TRACKING OBJECT DETECTION

Simple Online and Realtime Tracking

2 Feb 2016abewley/sort

This paper explores a pragmatic approach to multiple object tracking where the main focus is to associate objects efficiently for online and realtime applications.

MULTIPLE OBJECT TRACKING

Towards Real-Time Multi-Object Tracking

ECCV 2020 Zhongdao/Towards-Realtime-MOT

In this paper, we propose an MOT system that allows target detection and appearance embedding to be learned in a shared model.

Ranked #5 on Multi-Object Tracking on MOT16 (using extra training data)

MULTIPLE OBJECT TRACKING MULTI-TASK LEARNING REAL-TIME MULTI-OBJECT TRACKING

Know Your Surroundings: Exploiting Scene Information for Object Tracking

ECCV 2020 visionml/pytracking

Such approaches are however prone to fail in case of e. g. fast appearance changes or presence of distractor objects, where a target appearance model alone is insufficient for robust tracking.

OBJECT TRACKING

Distractor-aware Siamese Networks for Visual Object Tracking

ECCV 2018 foolwood/DaSiamRPN

During the off-line training phase, an effective sampling strategy is introduced to control this distribution and make the model focus on the semantic distractors.

INCREMENTAL LEARNING VISUAL OBJECT TRACKING VISUAL TRACKING