# Tracking Objects as Pixel-wise Distributions

arXiv: https://arxiv.org/abs/2207.05518 · HTML: https://mlsanity.com/paper/2207.05518/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 67 of its 82 references that are in the map.
- First posted on arXiv 12 Jul 2022.

## Builds on (most cited first, 30 of 67)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [TrackFormer: Multi-Object Tracking with Transformers](https://mlsanity.com/paper/2101.02702/) (2021)
- [FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking](https://mlsanity.com/paper/2004.01888/) (2020)
- [Tracking Objects as Points](https://mlsanity.com/paper/2004.01177/) (2020)
- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (2022)
- [PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1812.11788/) (2018)
- [Tracking without bells and whistles](https://mlsanity.com/paper/1903.05625/) (2019)
- [MOTR: End-to-End Multiple-Object Tracking with Transformer](https://mlsanity.com/paper/2105.03247/) (2021)

## Built on by (most cited first, 30 of 37)

- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception](https://mlsanity.com/paper/2303.07601/) (2023)
- [MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors](https://mlsanity.com/paper/2211.09791/) (2022)
- [AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing](https://mlsanity.com/paper/2207.13784/) (2022)
- [MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking](https://mlsanity.com/paper/2303.10404/) (2023)
- [Bridging the Domain Gap for Multi-Agent Perception](https://mlsanity.com/paper/2210.08451/) (2022)
- [SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth](https://mlsanity.com/paper/2306.05238/) (2023)
- [DiffusionTrack: Diffusion Model For Multi-Object Tracking](https://mlsanity.com/paper/2308.09905/) (2023)
- [Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization](https://mlsanity.com/paper/2211.10528/) (2022)
- [Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation](https://mlsanity.com/paper/2304.04694/) (2023)
- [NetTrack: Tracking Highly Dynamic Objects with a Net](https://mlsanity.com/paper/2403.11186/) (2024)
- [ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2303.15334/) (2023)
- [Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking](https://mlsanity.com/paper/2305.12724/) (2023)
- [DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions](https://mlsanity.com/paper/2309.04682/) (2023)
- [Collaborative Tracking Learning for Frame-Rate-Insensitive Multi-Object Tracking](https://mlsanity.com/paper/2308.05911/) (2023)
- [Beyond Visual Cues: Synchronously Exploring Target-Centric Semantics for Vision-Language Tracking](https://mlsanity.com/paper/2311.17085/) (2023)
- [MCTR: Multi Camera Tracking Transformer](https://mlsanity.com/paper/2408.13243/) (2024)
- [TrackSSM: A General Motion Predictor by State-Space Model](https://mlsanity.com/paper/2409.00487/) (2024)
- [End-to-end View Synthesis via NeRF Attention](https://mlsanity.com/paper/2207.14741/) (2022)
- [TQD-Track: Temporal Query Denoising for 3D Multi-Object Tracking](https://mlsanity.com/paper/2504.03258/) (2025)
- [PapMOT: Exploring Adversarial Patch Attack against Multiple Object Tracking](https://mlsanity.com/paper/2504.09361/) (2025)
- [NLOS Dies Twice: Challenges and Solutions of V2X for Cooperative Perception](https://mlsanity.com/paper/2307.06615/) (2023)
- [OccluTrack: Rethinking Awareness of Occlusion for Enhancing Multiple Pedestrian Tracking](https://mlsanity.com/paper/2309.10360/) (2023)
- [Multi-Granularity Language-Guided Training for Multi-Object Tracking](https://mlsanity.com/paper/2406.04844/) (2024)
- [When Trackers Date Fish: A Benchmark and Framework for Underwater Multiple Fish Tracking](https://mlsanity.com/paper/2507.06400/) (2025)
- [SVT: Supertoken Video Transformer for Efficient Video Understanding](https://mlsanity.com/paper/2304.00325/) (2023)
- [IP-MOT: Instance Prompt Learning for Cross-Domain Multi-Object Tracking](https://mlsanity.com/paper/2410.23907/) (2024)
- [To New Beginnings: A Survey of Unified Perception in Autonomous Vehicle Software](https://mlsanity.com/paper/2508.20892/) (2025)
- [Motion-Aware Transformer for Multi-Object Tracking](https://mlsanity.com/paper/2509.21715/) (2025)
- [S3Track: Self-supervised Tracking with Soft Assignment Flow](https://mlsanity.com/paper/2305.09981/) (2023)

## Abstract (arXiv)

Multi-object tracking (MOT) requires detecting and associating objects through frames. Unlike tracking via detected bounding boxes or tracking objects as points, we propose tracking objects as pixel-wise distributions. We instantiate this idea on a transformer-based architecture, P3AFormer, with pixel-wise propagation, prediction, and association. P3AFormer propagates pixel-wise features guided by flow information to pass messages between frames. Furthermore, P3AFormer adopts a meta-architecture to produce multi-scale object feature maps. During inference, a pixel-wise association procedure is proposed to recover object connections through frames based on the pixel-wise prediction. P3AFormer yields 81.2% in terms of MOTA on the MOT17 benchmark -- the first among all transformer networks to reach 80% MOTA in literature. P3AFormer also outperforms state-of-the-arts on the MOT20 and KITTI benchmarks.