Skip to search formSkip to main contentSkip to account menu

HOTA: A Higher Order Metric for Evaluating Multi-object Tracking

This work presents a novel MOT evaluation metric, higher order tracking accuracy (HOTA), which explicitly balances the effect of performing accurate detection, association and localization into a single unified metric for comparing trackers.
View on Springer (opens in a new tab)

MOTS: Multi-Object Tracking and Segmentation

This paper creates dense pixel-level annotations for two existing tracking datasets using a semi-automatic annotation procedure, and proposes a new baseline method which jointly addresses detection, tracking, and segmentation with a single convolutional network.
View on IEEE (opens in a new tab)

STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos

A novel approach that segments and tracks instances across space and time in a single stage and is trained end-to-end to learn spatio-temporal embeddings as well as parameters required to cluster pixels belonging to a specific objectinstance over an entire video clip is proposed.
View PDF on arXiv (opens in a new tab)

How to Train Your Deep Multi-Object Tracker

A differentiable proxy of MOTA and MOTP is proposed, which is combined in a loss function suitable for end-to-end training of deep multi-object trackers and establishes a new state of the art on the MOTChallenge benchmark.
View on IEEE (opens in a new tab)

MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking

This paper collects the first three releases of MOTChallenge and provides a categorization of state-of-the-art trackers and a broad error analysis, to help newcomers understand the related work and research trends in the MOT community, and hopefully shed some light into potential future research directions.
View on Springer (opens in a new tab)

Combined image- and world-space tracking in traffic scenes

This work presents its tracking pipeline as a 3D extension of image-based tracking, which uses world-space 3D information at every stage of processing by combining a novel coupled 2D-3D Kalman filter with a conceptually clean and extendable hypothesize-and-select framework.
View on IEEE (opens in a new tab)

EagerMOT: 3D Multi-Object Tracking via Sensor Fusion

This paper proposes EagerMOT, a simple tracking formulation that eagerly integrates all available object observations from both sensor modalities to obtain a well-informed interpretation of the scene dynamics and achieves state-of-the-art results across several MOT tasks on the KITTI and NuScenes datasets.
View on IEEE (opens in a new tab)

Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimation

Goal-GAN, an interpretable and end-to-end trainable model for human trajectory prediction, is presented, which establishes a new state-of-the-art on several benchmarks while being able to generate a realistic and diverse set of trajectories that conform to physical constraints.
View PDF on arXiv (opens in a new tab)

STEP: Segmenting and Tracking Every Pixel

This work presents a new benchmark: Segmenting and Tracking Every Pixel (STEP), encompassing two datasets, KITTI-STEP, and MOTChallenge-STEP together with a new evaluation metric Segmentation and Tracking Quality (STQ), that fairly balances semantic and tracking aspects of this task and is suitable for evaluating sequences of arbitrary length.
View PDF on arXiv (opens in a new tab)

MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?

MOTSynth, a large, highly diverse synthetic dataset for object detection and tracking using a rendering game engine, is generated and shows that MOTSynth can be used as a replacement for real data on tasks such as pedestrian detection, re-identification, segmentation, and tracking.
View on IEEE (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)