# Unsupervised Deep Tracking

arXiv: https://arxiv.org/abs/1904.01828 · HTML: https://mlsanity.com/paper/1904.01828/

## Key facts

- Cited by 74 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2019.

## Built on by (most cited first, 30 of 74)

- [Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking](https://mlsanity.com/paper/2103.11681/) (2021)
- [VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples](https://mlsanity.com/paper/2103.05905/) (2021)
- [Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos](https://mlsanity.com/paper/2205.14065/) (2022)
- [VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows](https://mlsanity.com/paper/2108.05015/) (2021)
- [Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark](https://mlsanity.com/paper/2103.16746/) (2021)
- [Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective](https://mlsanity.com/paper/2103.17263/) (2021)
- [HiFT: Hierarchical Feature Transformer for Aerial Tracking](https://mlsanity.com/paper/2108.00202/) (2021)
- [TCTrack: Temporal Contexts for Aerial Tracking](https://mlsanity.com/paper/2203.01885/) (2022)
- [Disentangled Cycle Consistency for Highly-realistic Virtual Try-On](https://mlsanity.com/paper/2103.09479/) (2021)
- [Do Different Tracking Tasks Require Different Appearance Models?](https://mlsanity.com/paper/2107.02156/) (2021)
- [Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation](https://mlsanity.com/paper/2203.16586/) (2022)
- [Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook](https://mlsanity.com/paper/2112.02838/) (2021)
- [SiamAPN++: Siamese Attentional Aggregation Network for Real-Time UAV Tracking](https://mlsanity.com/paper/2106.08816/) (2021)
- [Learning Pixel Trajectories with Multiscale Contrastive Random Walks](https://mlsanity.com/paper/2201.08379/) (2022)
- [Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/2110.05340/) (2021)
- [Temporally Consistent Object-Centric Learning by Contrasting Slots](https://mlsanity.com/paper/2412.14295/) (2024)
- [All-Day Object Tracking for Unmanned Aerial Vehicle](https://mlsanity.com/paper/2101.08446/) (2021)
- [WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking](https://mlsanity.com/paper/2201.07425/) (2022)
- [Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning](https://mlsanity.com/paper/2203.14333/) (2022)
- [IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking](https://mlsanity.com/paper/2103.14938/) (2021)
- [Learning to Associate Every Segment for Video Panoptic Segmentation](https://mlsanity.com/paper/2106.09453/) (2021)
- [Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackers](https://mlsanity.com/paper/2407.08394/) (2024)
- [Learning to Track Objects from Unlabeled Videos](https://mlsanity.com/paper/2108.12711/) (2021)
- [Boosting Video Object Segmentation via Space-time Correspondence Learning](https://mlsanity.com/paper/2304.06211/) (2023)
- [Unsupervised Visual Representation Learning by Tracking Patches in Video](https://mlsanity.com/paper/2105.02545/) (2021)
- [SGDViT: Saliency-Guided Dynamic Vision Transformer for UAV Tracking](https://mlsanity.com/paper/2303.04378/) (2023)
- [Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency](https://mlsanity.com/paper/2105.06463/) (2021)
- [Active Learning for Deep Visual Tracking](https://mlsanity.com/paper/2110.13259/) (2021)
- [Object Permanence Emerges in a Random Walk along Memory](https://mlsanity.com/paper/2204.01784/) (2022)
- [ADTrack: Target-Aware Dual Filter Learning for Real-Time Anti-Dark UAV Tracking](https://mlsanity.com/paper/2106.02495/) (2021)

## Abstract (arXiv)

We propose an unsupervised visual tracking method in this paper. Different from existing approaches using extensive annotated data for supervised learning, our CNN model is trained on large-scale unlabeled videos in an unsupervised manner. Our motivation is that a robust tracker should be effective in both the forward and backward predictions (i.e., the tracker can forward localize the target object in successive frames and backtrace to its initial position in the first frame). We build our framework on a Siamese correlation filter network, which is trained using unlabeled raw videos. Meanwhile, we propose a multiple-frame validation method and a cost-sensitive loss to facilitate unsupervised learning. Without bells and whistles, the proposed unsupervised tracker achieves the baseline accuracy of fully supervised trackers, which require complete and accurate labels during training. Furthermore, unsupervised framework exhibits a potential in leveraging unlabeled or weakly labeled data to further improve the tracking accuracy.