# Semi-TCL: Semi-Supervised Track Contrastive Representation Learning

arXiv: https://arxiv.org/abs/2107.02396 · HTML: https://mlsanity.com/paper/2107.02396/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 43 references that are in the map.
- First posted on arXiv 6 Jul 2021.

## Builds on (most cited first, 29 of 29)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [What Makes for Good Views for Contrastive Learning?](https://mlsanity.com/paper/2005.10243/) (2020)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [MOT16: A Benchmark for Multi-Object Tracking](https://mlsanity.com/paper/1603.00831/) (2016)
- [FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking](https://mlsanity.com/paper/2004.01888/) (2020)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [Tracking without bells and whistles](https://mlsanity.com/paper/1903.05625/) (2019)
- [Spatiotemporal Contrastive Video Representation Learning](https://mlsanity.com/paper/2008.03800/) (2020)
- [MOT20: A benchmark for multi object tracking in crowded scenes](https://mlsanity.com/paper/2003.09003/) (2020)
- [Towards Real-Time Multi-Object Tracking](https://mlsanity.com/paper/1909.12605/) (2019)
- [Large-Margin Softmax Loss for Convolutional Neural Networks](https://mlsanity.com/paper/1612.02295/) (2016)
- [CrowdHuman: A Benchmark for Detecting Human in a Crowd](https://mlsanity.com/paper/1805.00123/) (2018)
- [MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking](https://mlsanity.com/paper/1504.01942/) (2015)
- [Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking](https://mlsanity.com/paper/2007.14557/) (2020)
- [Large Margin Deep Networks for Classification](https://mlsanity.com/paper/1803.05598/) (2018)
- [Deep Affinity Network for Multiple Object Tracking](https://mlsanity.com/paper/1810.11780/) (2018)
- [The AVA-Kinetics Localized Human Actions Video Dataset](https://mlsanity.com/paper/2005.00214/) (2020)
- [TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model](https://mlsanity.com/paper/2006.05683/) (2020)
- [Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification](https://mlsanity.com/paper/1710.06555/) (2017)
- [MEVA: A Large-Scale Multiview, Multimodal Video Dataset for Activity Detection](https://mlsanity.com/paper/2012.00914/) (2020)
- [DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection](https://mlsanity.com/paper/1412.5661/) (2014)
- [Joint Person Segmentation and Identification in Synchronized First- and Third-person Videos](https://mlsanity.com/paper/1803.11217/) (2018)
- [Multi-Object Tracking with Siamese Track-RCNN](https://mlsanity.com/paper/2004.07786/) (2020)

## Built on by (most cited first, 23 of 23)

- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking](https://mlsanity.com/paper/2203.14360/) (2022)
- [BoT-SORT: Robust Associations Multi-Pedestrian Tracking](https://mlsanity.com/paper/2206.14651/) (2022)
- [Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification](https://mlsanity.com/paper/2302.11813/) (2023)
- [MeMOT: Multi-Object Tracking with Memory](https://mlsanity.com/paper/2203.16761/) (2022)
- [SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth](https://mlsanity.com/paper/2306.05238/) (2023)
- [GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021](https://mlsanity.com/paper/2202.11983/) (2022)
- [Tracking Objects as Pixel-wise Distributions](https://mlsanity.com/paper/2207.05518/) (2022)
- [Focus On Details: Online Multi-object Tracking with Diverse Fine-grained Representation](https://mlsanity.com/paper/2302.14589/) (2023)
- [TOPIC: A Parallel Association Paradigm for Multi-Object Tracking under Complex Motions and Diverse Scenes](https://mlsanity.com/paper/2308.11157/) (2023)
- [Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey](https://mlsanity.com/paper/2205.10766/) (2022)
- [Learning Data Association for Multi-Object Tracking using Only Coordinates](https://mlsanity.com/paper/2403.08018/) (2024)
- [Real-time End-to-End Video Text Spotter with Contrastive Representation Learning](https://mlsanity.com/paper/2207.08417/) (2022)
- [SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking](https://mlsanity.com/paper/2203.03985/) (2022)
- [PatchTrack: Multiple Object Tracking Using Frame Patches](https://mlsanity.com/paper/2201.00080/) (2022)
- [Single-Shot and Multi-Shot Feature Learning for Multi-Object Tracking](https://mlsanity.com/paper/2311.10382/) (2023)
- [CAMOT: Camera Angle-aware Multi-Object Tracking](https://mlsanity.com/paper/2409.17533/) (2024)
- [Learnable Graph Matching: A Practical Paradigm for Data Association](https://mlsanity.com/paper/2303.15414/) (2023)
- [SFSORT: Scene Features-based Simple Online Real-Time Tracker](https://mlsanity.com/paper/2404.07553/) (2024)
- [CRTrack: Low-Light Semi-Supervised Multi-object Tracking Based on Consistency Regularization](https://mlsanity.com/paper/2502.16809/) (2025)
- [VariabilityTrack:Multi-Object Tracking with Variable Speed Object Movement](https://mlsanity.com/paper/2203.06424/) (2022)
- [Mesh-SORT: Simple and effective location-wise tracker with lost management strategies](https://mlsanity.com/paper/2302.14415/) (2023)
- [Multi-Object Tracking by Hierarchical Visual Representations](https://mlsanity.com/paper/2402.15895/) (2024)

## Abstract (arXiv)

Online tracking of multiple objects in videos requires strong capacity of modeling and matching object appearances. Previous methods for learning appearance embedding mostly rely on instance-level matching without considering the temporal continuity provided by videos. We design a new instance-to-track matching objective to learn appearance embedding that compares a candidate detection to the embedding of the tracks persisted in the tracker. It enables us to learn not only from videos labeled with complete tracks, but also unlabeled or partially labeled videos. We implement this learning objective in a unified form following the spirit of constrastive loss. Experiments on multiple object tracking datasets demonstrate that our method can effectively learning discriminative appearance embeddings in a semi-supervised fashion and outperform state of the art methods on representative benchmarks.