# MissFormer: (In-)attention-based handling of missing observations for trajectory filtering and prediction

arXiv: https://arxiv.org/abs/2106.16009 · HTML: https://mlsanity.com/paper/2106.16009/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 30 Jun 2021.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks](https://mlsanity.com/paper/1803.10892/) (2018)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [A Recurrent Latent Variable Model for Sequential Data](https://mlsanity.com/paper/1506.02216/) (2015)
- [Human Motion Trajectory Prediction: A Survey](https://mlsanity.com/paper/1905.06113/) (2019)
- [Social Attention: Modeling Attention in Human Crowds](https://mlsanity.com/paper/1710.04689/) (2017)
- [Transformer Networks for Trajectory Forecasting](https://mlsanity.com/paper/2003.08111/) (2020)
- [Human Trajectory Forecasting in Crowds: A Deep Learning Perspective](https://mlsanity.com/paper/2007.03639/) (2020)
- [Deep Learning for Vision-based Prediction: A Survey](https://mlsanity.com/paper/2007.00095/) (2020)
- [Convolutional Neural Network for Trajectory Prediction](https://mlsanity.com/paper/1809.00696/) (2018)
- [Quantifying the Complexity of Standard Benchmarking Datasets for Long-Term Human Trajectory Prediction](https://mlsanity.com/paper/2005.13934/) (2020)
- [Pedestrian Trajectory Prediction using Context-Augmented Transformer Networks](https://mlsanity.com/paper/2012.01757/) (2020)
- [Microscopic Pedestrian Flow Characteristics: Development of an Image Processing Data Collection and Simulation Model](https://mlsanity.com/paper/1610.00029/) (2016)
- [Handling Missing Observations with an RNN-based Prediction-Update Cycle](https://mlsanity.com/paper/2103.11747/) (2021)

## Built on by (most cited first, 2 of 2)

- [An Analysis of Temporal Dropout in Earth Observation Time Series for Regression Tasks](https://mlsanity.com/paper/2504.06915/) (2025)
- [ViFiT: Reconstructing Vision Trajectories from IMU and Wi-Fi Fine Time Measurements](https://mlsanity.com/paper/2310.03140/) (2023)

## Abstract (arXiv)

In applications such as object tracking, time-series data inevitably carry missing observations. Following the success of deep learning-based models for various sequence learning tasks, these models increasingly replace classic approaches in object tracking applications for inferring the objects' motion states. While traditional tracking approaches can deal with missing observations, most of their deep counterparts are, by default, not suited for this. Towards this end, this paper introduces a transformer-based approach for handling missing observations in variable input length trajectory data. The model is formed indirectly by successively increasing the complexity of the demanded inference tasks. Starting from reproducing noise-free trajectories, the model then learns to infer trajectories from noisy inputs. By providing missing tokens, binary-encoded missing events, the model learns to in-attend to missing data and infers a complete trajectory conditioned on the remaining inputs. In the case of a sequence of successive missing events, the model then acts as a pure prediction model. The abilities of the approach are demonstrated on synthetic data and real-world data reflecting prototypical object tracking scenarios.