# DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video

arXiv: https://arxiv.org/abs/2403.14548 · HTML: https://mlsanity.com/paper/2403.14548/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 64 references that are in the map.
- First posted on arXiv 21 Mar 2024.

## Builds on (most cited first, 30 of 45)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence](https://mlsanity.com/paper/2305.15347/) (2023)
- [TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement](https://mlsanity.com/paper/2306.08637/) (2023)
- [PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking](https://mlsanity.com/paper/2307.15055/) (2023)
- [FlowFormer: A Transformer Architecture for Optical Flow](https://mlsanity.com/paper/2203.16194/) (2022)
- [Learning Correspondence from the Cycle-Consistency of Time](https://mlsanity.com/paper/1903.07593/) (2019)
- [TAP-Vid: A Benchmark for Tracking Any Point in a Video](https://mlsanity.com/paper/2211.03726/) (2022)
- [Unsupervised Semantic Segmentation by Distilling Feature Correspondences](https://mlsanity.com/paper/2203.08414/) (2022)
- [Space-Time Correspondence as a Contrastive Random Walk](https://mlsanity.com/paper/2006.14613/) (2020)
- [Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories](https://mlsanity.com/paper/2204.04153/) (2022)
- [Splicing ViT Features for Semantic Appearance Transfer](https://mlsanity.com/paper/2201.00424/) (2022)
- [Tracking Everything Everywhere All at Once](https://mlsanity.com/paper/2306.05422/) (2023)
- [Tracking Emerges by Colorizing Videos](https://mlsanity.com/paper/1806.09594/) (2018)
- [Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization](https://mlsanity.com/paper/2205.07839/) (2022)

## Built on by (most cited first, 30 of 64)

- [MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds](https://mlsanity.com/paper/2405.17421/) (2024)
- [DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment](https://mlsanity.com/paper/2412.16334/) (2024)
- [DELTA: Dense Efficient Long-range 3D Tracking for any video](https://mlsanity.com/paper/2410.24211/) (2024)
- [Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation](https://mlsanity.com/paper/2412.06016/) (2024)
- [TAPNext: Tracking Any Point (TAP) as Next Token Prediction](https://mlsanity.com/paper/2504.05579/) (2025)
- [Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph](https://mlsanity.com/paper/2406.07113/) (2024)
- [Feat2GS: Probing Visual Foundation Models with Gaussian Splatting](https://mlsanity.com/paper/2412.09606/) (2024)
- [LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models](https://mlsanity.com/paper/2504.14032/) (2025)
- [JAFAR: Jack up Any Feature at Any Resolution](https://mlsanity.com/paper/2506.11136/) (2025)
- [Retrieval-augmented Few-shot Medical Image Segmentation with Foundation Models](https://mlsanity.com/paper/2408.08813/) (2024)
- [Zero-Shot Object-Centric Representation Learning](https://mlsanity.com/paper/2408.09162/) (2024)
- [When Does Perceptual Alignment Benefit Vision Representations?](https://mlsanity.com/paper/2410.10817/) (2024)
- [Cluster and Predict Latent Patches for Improved Masked Image Modeling](https://mlsanity.com/paper/2502.08769/) (2025)
- [Exploring Temporally-Aware Features for Point Tracking](https://mlsanity.com/paper/2501.12218/) (2025)
- [Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning](https://mlsanity.com/paper/2411.19458/) (2024)
- [Seurat: From Moving Points to Depth](https://mlsanity.com/paper/2504.14687/) (2025)
- [Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising](https://mlsanity.com/paper/2511.08633/) (2025)
- [EgoPoints: Advancing Point Tracking for Egocentric Videos](https://mlsanity.com/paper/2412.04592/) (2024)
- [Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects](https://mlsanity.com/paper/2502.07005/) (2025)
- [DELTAv2: Accelerating Dense 3D Tracking](https://mlsanity.com/paper/2508.01170/) (2025)
- [Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Tracking](https://mlsanity.com/paper/2507.07483/) (2025)
- [LookOut: Real-World Humanoid Egocentric Navigation](https://mlsanity.com/paper/2508.14466/) (2025)
- [Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter](https://mlsanity.com/paper/2511.08334/) (2025)
- [TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video](https://mlsanity.com/paper/2411.18671/) (2024)
- [Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognition](https://mlsanity.com/paper/2508.03695/) (2025)
- [Tracking Any Point with Frame-Event Fusion Network at High Frame Rate](https://mlsanity.com/paper/2409.11953/) (2024)
- [TieBot: Learning to Knot a Tie from Visual Demonstration through a Real-to-Sim-to-Real Approach](https://mlsanity.com/paper/2407.03245/) (2024)
- [3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation](https://mlsanity.com/paper/2506.09883/) (2025)
- [DINO-VO: A Feature-based Visual Odometry Leveraging a Visual Foundation Model](https://mlsanity.com/paper/2507.13145/) (2025)
- [Video Understanding: From Geometry and Semantics to Unified Models](https://mlsanity.com/paper/2603.17840/) (2026)

## Abstract (arXiv)

We present DINO-Tracker -- a new framework for long-term dense tracking in video. The pillar of our approach is combining test-time training on a single video, with the powerful localized semantic features learned by a pre-trained DINO-ViT model. Specifically, our framework simultaneously adopts DINO's features to fit to the motion observations of the test video, while training a tracker that directly leverages the refined features. The entire framework is trained end-to-end using a combination of self-supervised losses, and regularization that allows us to retain and benefit from DINO's semantic prior. Extensive evaluation demonstrates that our method achieves state-of-the-art results on known benchmarks. DINO-tracker significantly outperforms self-supervised methods and is competitive with state-of-the-art supervised trackers, while outperforming them in challenging cases of tracking under long-term occlusions.