mlsanityData to 7 Oct 2026

PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search

arXiv 2403.15712 ↗First posted 23 Mar 2024cs.CV cs.ROcited by 9

Not on the map. Why?

Abstract (arXiv)

Multiple object tracking is a critical task in autonomous driving. Existing works primarily focus on the heuristic design of neural networks to obtain high accuracy. As tracking accuracy improves, however, neural networks become increasingly complex, posing challenges for their practical application in real driving scenarios due to the high level of latency. In this paper, we explore the use of the neural architecture search (NAS) methods to search for efficient architectures for tracking, aiming for low real-time latency while maintaining relatively high accuracy. Another challenge for object tracking is the unreliability of a single sensor, therefore, we propose a multi-modal framework to improve the robustness. Experiments demonstrate that our algorithm can run on edge devices within lower latency constraints, thus greatly reducing the computational requirements for multi-modal object tracking while keeping lower latency.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 23 Mar 2024.

Builds on

31 of 45 references.

References · 31

  1. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  2. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  3. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  4. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  5. 2019Tracking without bells and whistlescited by 382
  6. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 345
  7. 2019MOTS: Multi-Object Tracking and Segmentationcited by 222
  8. 2022StrongSORT: Make DeepSORT Great Againcited by 213
  9. 2017Detect to Track and Track to Detectcited by 131
  10. 2020GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learningcited by 113
  11. 2021FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detectioncited by 92
  12. 2021EagerMOT: 3D Multi-Object Tracking via Sensor Fusioncited by 83
19 more
  1. 2023SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detectioncited by 83
  2. 2018Deep Affinity Network for Multiple Object Trackingcited by 82
  3. 2019Robust Multi-Modality Multi-Object Trackingcited by 56
  4. 2019Track to Reconstruct and Reconstruct to Trackcited by 49
  5. 2017Deep Network Flow for Multi-Object Trackingcited by 45
  6. 2018Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Trackingcited by 40
  7. 2023RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registrationcited by 37
  8. 2018Mono-Camera 3D Multi-Object Tracking Using Deep Learning Detections and PMBM Filteringcited by 32
  9. 2022PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?cited by 29
  10. 2019FANTrack: 3D Multi-Object Tracking with Feature Association Networkcited by 28
  11. 2017Accurate Single Stage Detector Using Recurrent Rolling Convolutioncited by 27
  12. 2018End-to-end Learning of Multi-sensor 3D Tracking by Detectioncited by 25
  13. 2021HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Searchcited by 20
  14. 2022Exploiting More Information in Sparse Point Cloud for 3D Single Object Trackingcited by 14
  15. 2023DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Cloudscited by 14
  16. 2021Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillationcited by 9
  17. 2014FollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory and Computationcited by 8
  18. 2018Vehicle Tracking Using Surveillance with Multimodal Data Fusioncited by 7
  19. 2022Implicit and Efficient Point Cloud Completion for 3D Single Object Trackingcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 2; 2026: 1.

9 papers.

  1. 2024DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenescited by 45
  2. 2024MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Drivingcited by 17
  3. 2024Joint Pedestrian Trajectory Prediction through Posterior Samplingcited by 10
  4. 2024A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervisioncited by 9
  5. 2025HybridTrack: A Hybrid Approach for Robust Multi-Object Trackingcited by 3
  6. 2024CrossTracker: Robust Multi-modal 3D Multi-Object Tracking via Cross Correctioncited by 2
  7. 2025OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedbackcited by 2
  8. 2026Polycepta: Object-Centric Appearance Estimation for Multi-Object Trackingcited by 1
  9. 2024RegTrack: Simplicity Beneath Complexity in Robust Multi-Modal 3D Multi-Object Trackingcited by 0