# Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking

arXiv: https://arxiv.org/abs/2108.06029 · HTML: https://mlsanity.com/paper/2108.06029/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 70 references that are in the map.
- First posted on arXiv 13 Aug 2021.

## Builds on (most cited first, 30 of 37)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [Language Modeling with Gated Convolutional Networks](https://mlsanity.com/paper/1612.08083/) (2016)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [MOT16: A Benchmark for Multi-Object Tracking](https://mlsanity.com/paper/1603.00831/) (2016)
- [TrackFormer: Multi-Object Tracking with Transformers](https://mlsanity.com/paper/2101.02702/) (2021)
- [Tracking Objects as Points](https://mlsanity.com/paper/2004.01177/) (2020)
- [Tracking without bells and whistles](https://mlsanity.com/paper/1903.05625/) (2019)
- [TransTrack: Multiple Object Tracking with Transformer](https://mlsanity.com/paper/2012.15460/) (2020)
- [Learning a Neural Solver for Multiple Object Tracking](https://mlsanity.com/paper/1912.07515/) (2019)
- [CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification](https://mlsanity.com/paper/1903.09254/) (2019)
- [Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking](https://mlsanity.com/paper/2007.14557/) (2020)
- [GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning](https://mlsanity.com/paper/2006.07327/) (2020)
- [UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking](https://mlsanity.com/paper/1511.04136/) (2015)
- [Joint Monocular 3D Vehicle Detection and Tracking](https://mlsanity.com/paper/1811.10742/) (2018)
- [How To Train Your Deep Multi-Object Tracker](https://mlsanity.com/paper/1906.06618/) (2019)
- [TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model](https://mlsanity.com/paper/2006.05683/) (2020)
- [FAMNet: Joint Learning of Feature, Affinity and Multi-dimensional Assignment for Online Multiple Object Tracking](https://mlsanity.com/paper/1904.04989/) (2019)
- [Lifted Disjoint Paths with Application in Multiple Object Tracking](https://mlsanity.com/paper/2006.14550/) (2020)
- [Track to Reconstruct and Reconstruct to Track](https://mlsanity.com/paper/1910.00130/) (2019)
- [Recurrent Autoregressive Networks for Online Multi-Object Tracking](https://mlsanity.com/paper/1711.02741/) (2017)
- [Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor](https://mlsanity.com/paper/1504.02340/) (2015)
- [JRMOT: A Real-Time 3D Multi-Object Tracker and a New Large-Scale Dataset](https://mlsanity.com/paper/2002.08397/) (2020)
- [Exploit the Connectivity: Multi-Object Tracking with TrackletNet](https://mlsanity.com/paper/1811.07258/) (2018)
- [Learning Complexity-Aware Cascades for Deep Pedestrian Detection](https://mlsanity.com/paper/1507.05348/) (2015)

## Built on by (most cited first, 26 of 26)

- [Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking](https://mlsanity.com/paper/2203.14360/) (2022)
- [StrongSORT: Make DeepSORT Great Again](https://mlsanity.com/paper/2202.13514/) (2022)
- [CAMO-MOT: Combined Appearance-Motion Optimization for 3D Multi-Object Tracking with Camera-LiDAR Fusion](https://mlsanity.com/paper/2209.02540/) (2022)
- [DeepFusionMOT: A 3D Multi-Object Tracking Framework Based on Camera-LiDAR Fusion with Deep Association](https://mlsanity.com/paper/2202.12100/) (2022)
- [TripletTrack: 3D Object Tracking using Triplet Embeddings and LSTM](https://mlsanity.com/paper/2210.16204/) (2022)
- [EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Driving](https://mlsanity.com/paper/2402.18302/) (2024)
- [DIVOTrack: A Novel Dataset and Baseline Method for Cross-View Multi-Object Tracking in DIVerse Open Scenes](https://mlsanity.com/paper/2302.07676/) (2023)
- [Self-Supervised Multi-Object Tracking with Path Consistency](https://mlsanity.com/paper/2404.05136/) (2024)
- [In Pursuit of Many: A Review of Modern Multiple Object Tracking Systems](https://mlsanity.com/paper/2209.04796/) (2022)
- [CenterRadarNet: Joint 3D Object Detection and Tracking Framework using 4D FMCW Radar](https://mlsanity.com/paper/2311.01423/) (2023)
- [Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey](https://mlsanity.com/paper/2205.10766/) (2022)
- [Ego-Vehicle Action Recognition based on Semi-Supervised Contrastive Learning](https://mlsanity.com/paper/2303.00977/) (2023)
- [You Only Need Two Detectors to Achieve Multi-Modal 3D Multi-Object Tracking](https://mlsanity.com/paper/2304.08709/) (2023)
- [Learning Data Association for Multi-Object Tracking using Only Coordinates](https://mlsanity.com/paper/2403.08018/) (2024)
- [Ego3DT: Tracking Every 3D Object in Ego-centric Videos](https://mlsanity.com/paper/2410.08530/) (2024)
- [Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection](https://mlsanity.com/paper/2207.11789/) (2022)
- [Single-Shot and Multi-Shot Feature Learning for Multi-Object Tracking](https://mlsanity.com/paper/2311.10382/) (2023)
- [Tracking Objects with 3D Representation from Videos](https://mlsanity.com/paper/2306.05416/) (2023)
- [CrossTracker: Robust Multi-modal 3D Multi-Object Tracking via Cross Correction](https://mlsanity.com/paper/2411.18850/) (2024)
- [Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers](https://mlsanity.com/paper/2111.08954/) (2021)
- [Towards Effective Multi-Moving-Camera Tracking: A New Dataset and Lightweight Link Model](https://mlsanity.com/paper/2312.11035/) (2023)
- [AM-SORT: Adaptable Motion Predictor with Historical Trajectory Embedding for Multi-Object Tracking](https://mlsanity.com/paper/2401.13950/) (2024)
- [Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos](https://mlsanity.com/paper/2412.10861/) (2024)
- [S3Track: Self-supervised Tracking with Soft Assignment Flow](https://mlsanity.com/paper/2305.09981/) (2023)
- [Hierarchical IoU Tracking based on Interval](https://mlsanity.com/paper/2406.13271/) (2024)
- [RegTrack: Simplicity Beneath Complexity in Robust Multi-Modal 3D Multi-Object Tracking](https://mlsanity.com/paper/2409.00618/) (2024)

## Abstract (arXiv)

Vehicle tracking is an essential task in the multi-object tracking (MOT) field. A distinct characteristic in vehicle tracking is that the trajectories of vehicles are fairly smooth in both the world coordinate and the image coordinate. Hence, models that capture motion consistencies are of high necessity. However, tracking with the standalone motion-based trackers is quite challenging because targets could get lost easily due to limited information, detection error and occlusion. Leveraging appearance information to assist object re-identification could resolve this challenge to some extent. However, doing so requires extra computation while appearance information is sensitive to occlusion as well. In this paper, we try to explore the significance of motion patterns for vehicle tracking without appearance information. We propose a novel approach that tackles the association issue for long-term tracking with the exclusive fully-exploited motion information. We address the tracklet embedding issue with the proposed reconstruct-to-embed strategy based on deep graph convolutional neural networks (GCN). Comprehensive experiments on the KITTI-car tracking dataset and UA-Detrac dataset show that the proposed method, though without appearance information, could achieve competitive performance with the state-of-the-art (SOTA) trackers. The source code will be available at https://github.com/GaoangW/LGMTracker.