State Space Models for Long-Term Temporal Context in 3D Single Object Tracking
- 31 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (4) , 4941-4955
Abstract
3D single object tracking (3D SOT) remains a challenging task due to the sparsity of point clouds, appearance variations caused by occlusions, and the difficulty of modeling long-term temporal context. Although recent Transformer-based approaches leverage memory mechanisms to propagate temporal information, their quadratic complexity and reliance on discrete historical snapshots limit both efficiency and temporal coherence. To address these limitations, we propose SSMTrack, a novel 3D SOT framework built upon state space models (SSMs), which efficiently models long-term temporal dependencies through a continuously evolving hidden state with linear complexity. Specifically, we introduce a serialization and bidirectional scanning (SBS) strategy to enhance intra-frame feature interactions and design a Target-Aware Encoder (TAE) to extract target cues while maintaining stable temporal representations. Furthermore, we propose a Temporal Causal Shape Learning (TCSL) mechanism that preserves critical historical information while adaptively integrating current inputs, progressively enriching target feature representations over time. Extensive experiments on three benchmark datasets demonstrate that SSMTrack achieves state-of-the-art performance with strong temporal coherence and high efficiency. The code will be released upon publication.Keywords
Funding Information
- National Natural Science Foundation of China (62394354)
- National Natural Science Foundation of China (62121002)
- Youth Innovation Promotion Association of the Chinese Academy of Sciences
- Graduate School Special Funding Program of the University of Science and Technology of China
This publication has 60 references indexed in Scilit:
- Boosting 3D Single Object Tracking with 2D Matching Distillation and 3D Pre-training2024
- 3D Single-Object Tracking in Point Clouds with High Temporal Variation2024
- Temporal-Aware Siamese Tracker: Integrate Temporal Context for 3D Object Tracking2023
- 3D Siamese Transformer Network for Single Object Tracking on Point Clouds2022
- CMT: Context-Matching-Guided Transformer for 3D Tracking in Point Clouds2022
- High Performance Visual Tracking with Siamese Region Proposal Network2018
- PU-Net: Point Cloud Upsampling Network2018
- Fully-Convolutional Siamese Networks for Object Tracking2016
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012
- Über die stetige Abbildung einer Linie auf ein Flächenstück1935