# TAPNext++: What's Next for Tracking Any Point (TAP)?

arXiv: https://arxiv.org/abs/2604.10582 · HTML: https://mlsanity.com/paper/2604.10582/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 29 references that are in the map.
- First posted on arXiv 12 Apr 2026.

## Builds on (most cited first, 23 of 23)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items](https://mlsanity.com/paper/2204.11918/) (2022)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [Kubric: A scalable dataset generator](https://mlsanity.com/paper/2203.03570/) (2022)
- [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)
- [TAP-Vid: A Benchmark for Tracking Any Point in a Video](https://mlsanity.com/paper/2211.03726/) (2022)
- [Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models](https://mlsanity.com/paper/2402.19427/) (2024)
- [MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos](https://mlsanity.com/paper/2412.04463/) (2024)
- [BootsTAP: Bootstrapped Training for Tracking-Any-Point](https://mlsanity.com/paper/2402.00847/) (2024)
- [RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation](https://mlsanity.com/paper/2308.15975/) (2023)
- [Local All-Pair Correspondence for Point Tracking](https://mlsanity.com/paper/2407.15420/) (2024)
- [AllTracker: Efficient Dense Point Tracking at High Resolution](https://mlsanity.com/paper/2506.07310/) (2025)
- [TAPTR: Tracking Any Point with Transformers as Detection](https://mlsanity.com/paper/2403.13042/) (2024)
- [TAPNext: Tracking Any Point (TAP) as Next Token Prediction](https://mlsanity.com/paper/2504.05579/) (2025)
- [Track-On: Transformer-based Online Point Tracking with Memory](https://mlsanity.com/paper/2501.18487/) (2025)
- [TAPTRv2: Attention-based Position Update Improves Tracking Any Point](https://mlsanity.com/paper/2407.16291/) (2024)
- [TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video](https://mlsanity.com/paper/2411.18671/) (2024)
- [Track-On2: Enhancing Online Point Tracking with Memory](https://mlsanity.com/paper/2509.19115/) (2025)

## Built on by (most cited first, 6 of 6)

- [Robustness without Wrinkles: Parallel Simulation and Robust MPC for Certified Deformable Manipulation](https://mlsanity.com/paper/2606.14188/) (2026)
- [Robo-Harness K1: Harnessing Robot-Use Agents via Perception Augmentation](https://mlsanity.com/paper/2609.29389/) (2026)
- [TrAction: Action Recognition with Sparse Trajectories](https://mlsanity.com/paper/2606.03490/) (2026)
- [TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views](https://mlsanity.com/paper/2609.01899/) (2026)
- [Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations](https://mlsanity.com/paper/2608.01628/) (2026)
- [Across Viewpoints and Time: Trajectory-Generalizable Physical Attacks on World Models and Video Understanding Models](https://mlsanity.com/paper/2610.15343/) (2026)

## Abstract (arXiv)

Tracking-Any-Point (TAP) models aim to track any point through a video which is a crucial task in AR/XR and robotics applications. The recently introduced TAPNext approach proposes an end-to-end, recurrent transformer architecture to track points frame-by-frame in a purely online fashion -- demonstrating competitive performance at minimal latency. However, we show that TAPNext struggles with longer video sequences and also frequently fails to re-detect query points that reappear after being occluded or leaving the frame. In this work, we present TAPNext++, a model that tracks points in sequences that are orders of magnitude longer while preserving the low memory and compute footprint of the architecture. We train the recurrent video transformer using several data-driven solutions, including training on long 1024-frame sequences enabled by sequence parallelism techniques. We highlight that re-detection performance is a blind spot in the current literature and introduce a new metric, Re-Detection Average Jaccard (AJRD), to explicitly evaluate tracking on re-appearing points. To improve re-detection of points, we introduce tailored geometric augmentations, such as periodic roll that simulates point re-entries, and supervising occluded points. We demonstrate that recurrent transformers can be substantially improved for point tracking and set a new state-of-the-art on multiple benchmarks. Model and code can be found at https://tap-next-plus-plus.github.io.