The DOI matches its Crossref record; 56 of the 59 references it cites were found in a registry or an index.
LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search
Open accessAbstract
Object tracking has achieved significant progress over the past few years. However, state-of-the-art trackers become increasingly heavy and expensive, which limits their deployments in resource-constrained applications. In this work, we present LightTrack, which uses neural architecture search (NAS) to design more lightweight and efficient object trackers. Comprehensive experiments show that our LightTrack is effective. It can find trackers that achieve superior performance compared to handcrafted SOTA trackers, such as SiamRPN++ [30] and Ocean [56], while using much fewer model Flops and parameters. Moreover, when deployed on resource-constrained mobile chipsets, the discovered trackers run much faster. For example, on Snapdragon 845 Adreno GPU, LightTrack runs 12× faster than Ocean, while using 13× fewer parameters and 38× fewer Flops. Such improvements might narrow the gap between academic models and industrial deployments in object tracking task. LightTrack is released at here.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Xception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.195 · Cited by 20,380
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Tan, M., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1905.11946 · Cited by 17,072
Howard, A., Sandler, M., Chen, B., Wang, W., Chen, L.-C., Tan, M., Chu, G., Vasudevan, V., Zhu, Y., Pang, R., et al. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00140 · Cited by 9,708
Research works printed but not linked: 2
- liu, 2019, DARTS: differentiable architecture searc, ICLRE
- 10.1109/CVPR42600.2020.00661 · DOI · Paper page
Cited by
Sorted by citations
Items 201–277 of 277
Cross-Correlation Fusion Graph Convolution-Based Object Tracking
Fan, L., Jiang, X., Chen, W., & Fujita, H. (2023) · Symmetry · doi:10.3390/sym15030771 · Cited by 1
Performance Benchmarking of Visual Human Tracking Algorithms for UAVs
Kalampokas, Τ., Papakostas, G. A., Chatzis, V., & Krinidis, S. (2022) · Panhellenic Conference on Informatics · doi:10.1145/3575879.3575880 · Cited by 1
Reliable interconnected channels for dynamic DCF based visual tracking
Gopal, G. Y., & Amer, M. A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15235-x · Cited by 1
Efficient and Lightweight Visual Tracking with Differentiable Neural Architecture Search
Gao, P., Liu, X., Sang, H.-C., Wang, Y., & Wang, F. (2023) · Electronics · doi:10.3390/electronics12173623 · Cited by 2
Target-Aware Feature Bottleneck for Real-Time Visual Tracking
Choi, J. (2023) · Applied Sciences · doi:10.3390/app131810198 · Cited by 1
Siamese Dense Pixel-Level Fusion Network for Real-Time UAV Tracking
Huang, Z., Li, G., Sun, X., Chen, Y., Sun, J., Ni, Z., & Yang, Y. (2023) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.039489 · Cited by 1
A Lightweight and Real-Time Network for Unmanned Aerial Vehicle Object Tracking
Jin, Q., Wang, W., Wang, B., Wang, X., Sun, Z., & Sun, H. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-9021-4_26 · Cited by 1
Mao, T., Zheng, H., Zhai, X., & Zhu, J. (2024) · International Symposium on Autonomous Systems (ISAS) · doi:10.1109/isas61044.2024.10552592 · Cited by 1
Masked Autoencoders as Single Object Tracking Learners
Bo, C., Chen, X., & Zhang, J. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.052329 · Cited by 1
A framework of specialized knowledge distillation for Siamese tracker on challenging attributes
Li, Y., Shimada, A., Minematsu, T., & Tang, C. C. (2024) · Machine Vision and Applications · doi:10.1007/s00138-024-01578-4 · Cited by 1
A lightweight target tracking algorithm based on online correction for meta-learning
Qi, Y., Yin, G., Li, Y., Liu, L., & Jiang, Z. (2024) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2024.104228 · Cited by 1
HCV: Lightweight Hybrid CNN-Vision Transformer for Visual Object Tracking
Chen, L.-C., & Chu, W.-T. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-2061-6_4 · Cited by 1
CaphandAuth: Robust and Anti-spoofing Hand Authentication via COTS Capacitive Touchscreens
Zhu, X., Zhou, M., Qiao, X., Ling, Z., Liu, Q., Wang, H., Ma, X., & Li, Z. (2025) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3715014.3722046 · Cited by 1
Cheng, F., Peng, G., Li, H., Zhao, B., & Li, R. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3619160 · Cited by 1
On Designing Light-Weight Object Trackers Through Network Pruning: Use CNNS or Transformers?
Aggarwal, S., Gupta, T., Sahu, P. K., Chavan, A., Tiwari, R., Prasad, D. K., & Gupta, D. K. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10094920 · Cited by 1
Single target tracking algorithm for lightweight Siamese networks based on global attention
Wang, Z., He, X., & Cheng, R. (2022) · Bulletin of the Polish Academy of Sciences Technical Sciences · doi:10.24425/bpasts.2021.139961 · Cited by 1
Robust Probabilistic Discriminative Model Prediction Tracker via Improved Model Update StrategyPreprint
Chen, S., Qiu, C., Huang, Y., & Zhang, Z. (2021) · Research Square · doi:10.21203/rs.3.rs-1138271/v1 · Cited by 1
Learning Dynamic Compact Memory Embedding for Deformable Visual Object TrackingPreprint
Zhu, P., Yu, H., Zhang, K., Wang, Y., Zhao, S., Wang, L., Zhang, T., & Hu, Q. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.11625
Rank-Based Filter Pruning for Real-Time Deep Uav TrackersPreprint
Wang, X., Zeng, D., Zhao, Q., & Li, S. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4159540
Algorithm Research of Siamese Neural Network in Target Tracking
李, 铭. (2022) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2022.113029
Application of Target Recognition and Tracking in Agricultural Picking Robots
Li, T., & Zhang, K. (2023) · Advances in Engineering Technology Research · doi:10.56028/aetr.5.1.203.2023
Edge-Aware and Relation Mining Network for RGBT TrackingPreprint
Xiao, X., Chen, Z., Meng, F., Liu, J., & Xiong, X. (2023) · Research Square · doi:10.21203/rs.3.rs-3488582/v1
Molecular-Clump Detection Based on an Improved YOLOv5 Joint Density Peak Clustering
Hu, J., Huang, Y., Zheng, S., Chen, Z., Zeng, X., Luo, X., & Chen, L. (2023) · Universe · doi:10.3390/universe9110480
Multi-granularity Feature Fusion for Transformer-Based Single Object Tracking
Wang, Z., & Miao, D. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-50959-9_22
A Lightweight Target Tracking Algorithm Based on 1 Online Correction for Meta-learningPreprint
Qi, Y., Yin, G., Li, Y., Liu, L., & Jiang, Z. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4673176
Sun, L., Li, X., Gao, D., & Fan, B. (2024) · Journal of Electronic Imaging · doi:10.1117/1.jei.33.1.013012
Central Attention with Sliding Window for Efficient Visual TrackingPreprint
Chen, Z., Xiao, X., Xiong, X., Meng, F., & Liu, J. (2024) · Research Square · doi:10.21203/rs.3.rs-3912795/v1
A Correlation-Filtered Target Tracking Method Incorporating Hybrid Saliency TechniquesPreprint
Liao, Z., & Ismail, A. B. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4873806
Real-Time UAV Tracking Through Disentangled Representation With Mutual Information Maximization
Ye, H., Yang, X., Wu, Y., Wang, X., Li, Y., & Li, S. (2024) · IEEE Access · doi:10.1109/access.2024.3439432
A Stochastic Model for Video Object Tracking
Leo, M., Ubul, K., Aysa, A., Cheng, S., Eli, E., & Xu, X. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-8858-3_5
Robust Object Tracking with Gradient Activation Siamese Network
Yan, Z., Lu, X., Pang, T., & Xu, J. (2024) · International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC) · doi:10.1109/cyberc62439.2024.00027
Augment One With Others: Generalizing to Unforeseen Variations for Visual Tracking
Zhang, J., Li, Z., Wei, R., & Wang, Y. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3521842 · Cited by 1
Multi-Attention Fusion Lightweight Single Object Tracking Algorithm
Bao, J., Zhao, J., Liu, B., & Zhang, D. (2024) · International Conference on Robotics, Control and Automation Engineering (RCAE) · doi:10.1109/rcae62637.2024.10834246
Efficient Transformer-Based Visual Tracking for Edge Computing Devices
Xu, Y., Xu, T., Zhang, W., Wu, J., Cheng, Z., & Yang, W. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2914-5_21
Rethinking Correlation Filter Trackers for Small Unmanned Aircraft Systems
Liu, W., Wu, S., Yun, X., & Liu, Y. (2025) · Computational Intelligence · doi:10.1111/coin.70053
PEBTrack: A Performance-Efficiency Balance Tracker for Aerial Scenario
Ma, X., Yu, X., & Peng, X. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-6596-9_14
Efficient local–global feature fusion transformer for siamese object tracking
Pan, F., Zhao, L., Wang, C., Wang, X., & Ren, G. (2025) · Multimedia Systems · doi:10.1007/s00530-025-01875-6
SP-HRNet: single-path neural architecture search for human pose estimation
Sun, M., Wang, Y., Wang, P., Gao, W., Li, Q., Li, X., & Di, R. (2025) · Discover Applied Sciences · doi:10.1007/s42452-025-06846-0
ESTrack: Towards Efficient Sequence-Based Visual Tracking with Hierarchical Features
Wang, Y., Wang, Y., Qu, T., & Fang, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9891-2_21
SiamSCT: Spatial-Channel Saliency and Temporal Fusion Network for Real-Time Aerial Tracking
Wang, B., Liu, C., Chen, Q., & Liu, J. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3596119
Response Feedback for Task Semantic Space Consistent Siamese Tracking
Cao, M., & Tan, H. (2024) · International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE) · doi:10.1109/icbaie63306.2024.11116881
Liu, Z., Li, Z., & Hu, W. (2025) · Multimedia Systems · doi:10.1007/s00530-025-01913-3
Flying Through Moving Gates without Full State Estimation
Römer, R., Emmert, T., & Schoellig, A. P. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127465 · Cited by 1
Object Tracking: A Comprehensive Survey of Deep and Traditional Methods
Ghazali, S. M., & Baleghi, Y. (2025) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-025-10314-8 · Cited by 1
Automated Feature Extraction Model Design Based on Neural Architecture Search
Ding, J. (2025) · International Conference on Intelligent Computing and Robotics (ICICR) · doi:10.1109/icicr65456.2025.00124
Inference-Time Optimization for Fast and Accurate Visual Object Tracking
Borsuk, V., & Yakovyna, V. S. (2025) · Mathematical Modeling and Computing · doi:10.23939/mmc2025.04.1211
Exploring Pruning-Based Efficient Object Tracking via Hybrid Knowledge Distillation
Song, Y., Wang, S., Zeng, Z., Zheng, J., Wang, Z., & Ning, J. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3609410
Exploring a Hierarchical Cross-Attention Transformer for High-Speed Tracking
Chen, X. Y., Kang, B., Zhu, J., Li, D., Bo, C., & Wang, D. (2025) · Computational Visual Media · doi:10.26599/cvm.2025.9450418
Self-citationOcclusion-Resistant Visual Tracking for UAVs
Bai, Q., Xu, Z., Wang, Y., & Zhu, Y. (2025) · IEEE International Conference on Unmanned Systems (ICUS) · doi:10.1109/icus66297.2025.11294590
A Comprehensive Benchmark for Evaluating Night-time Visual Object Tracking
Liu, Y., Mahmood, A., & Khan, M. H. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02661-7
USBTrack: Efficient Underwater Single-Branch Tracker via Template Prompt Learning
Xu, X.-H., Jing, T., & Meng, Q. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3647019
Boosting Nighttime UAV Tracking via Self-prompting Autoregressive Learning and a New Benchmark
Zhang, C., Liu, L., Wen, H., Zhou, X., & Wang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5755-4_1
Liu, T., Zhang, M., Wang, Z., & Piao, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5693-9_6
WmLSTM: A Plug-and-Play Window-Level mLSTM-Based Temporal Encoder for Robust Visual Tracking
Chen, Y., Jia, G., Ma, D., Zha, Y., & Zhang, P. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3662479
Dual-Attention Interaction and Adaptive Features for Lightweight Visual Tracking
Li, Z., Lü, T., Wang, J., Zhou, H., & Hu, R. (2025) · International Conference on Robot Systems and Applications (ICRSA) · doi:10.1109/icrsa66467.2025.11383825
Asymmetric IR Tracking with Cross-Scale Attention Interaction
Yuan, Z., Ma, J., & Feng, Y. (2025) · International Conference on Intelligent Control, Measurement and Signal Processing (ICMSP) · doi:10.1109/icmsp68723.2025.11407807
Efficient Plug-and-Play Mamba-Based Selective Target State Modeling for Lightweight Visual Tracking
Chen, Y., Jia, G., Zha, Y., & Zhang, P. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3678806
A Multi-Objective RL-Driven Architecture Search Framework for Lightweight Visual Object Tracking
Zhang, H., Wu, C., & Bai, F. (2025) · International Conference on Signal Processing and Intelligent Computing (SPIC) · doi:10.1109/spic68204.2025.11470684
HARMONY: Adapting Segment Anything Model for Hyperspectral Video Tracking With Motion-Aware Memory
Chen, Y., Yuan, Q., Su, X., & Zhang, L. (2025) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers69515.2025.11501565
Underwater Object Tracking Method Based on Acousto - Optic Multi - Sensor Fusion
He, N., Wei, J., Feng, X., Wang, X., He, W., & Xu, S. (2026) · International Conference on Robot Perception and Intelligent Control (RPIC) · doi:10.1109/rpic68328.2026.11518491
Chen, Y., Jia, G., Ma, D., Zha, Y., & Zhang, P. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114033
Wei, X., Li, J., & Lu, M. (2026) · Electronics · doi:10.3390/electronics15112276
Qiu, Z., Liu, S., & Wan, Z. (2026) · International Conference on Image, Signal Processing and Pattern Recognition (ISPP) · doi:10.1109/ispp69262.2026.11542990
Learning Shallow-Robust Vision Transformers With Selective Distillation for Real-Time UAV Tracking
Zeng, F., Liang, Q., Zhong, B., Xue, C., Tan, Y., Mo, Z., & Song, S. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3706810
LTFTrack: Lightweight Temporal Fusion with Self-Distillation for Efficient Object Tracking
Yan, J., Li, W., & Hu, W. (2026) · International Conference on Artificial Intelligence and Industrial Technology Applications (AIITA) · doi:10.1109/aiita69518.2026.11567120
SiamVTRS: enhanced Siamese vehicle tracking for road surveillance
Guo, S., Yu, X., Liu, Y., Ma, D., & Xu, C. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02551-z
Wei, Y., Liu, J., Xue, K., & Wang, E. (2026) · Defence Technology · doi:10.1016/j.dt.2026.07.026
Adaptive token division-based transformer for visual object tracking
Tian, D., Liu, D., & Wang, X. (2026) · PLoS ONE · doi:10.1371/journal.pone.0351112
Lv, Y., Zhang, J., Yang, W., Li, G., Zhang, X., Wang, F., & Zhu, J. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104913
Wang, R., Gao, Z., & Gao, X. (2026) · IET Image Processing · doi:10.1049/ipr2.70453
Yin, M., Huang, S., 郭小藤, Wen, X., Qian, Y., & Li, H. (2026) · Vehicles · doi:10.3390/vehicles8090200
Efficient UAV Object Tracking via Visual Contrastive Attention and Hybrid Adaptive Computation
Jia, D., Pang, J., Zhang, Z., Li, Y., & Xue, W. (2026) · International Conference on Unmanned Systems and Technology (UST) · doi:10.1109/ust70584.2026.11663823
A novel lightweight Siamese-like tracker based on transformers with unidirectional mixed attention
Liang, W., Shen, B., Ding, D., & Yu, H. L. (2026) · Pattern Analysis and Applications · doi:10.1007/s10044-026-01771-3
Motion-Aware Sparse Pipeline for Lightweight Object Tracking
Wei, Q., Liu, F., Zhang, D. H., He, Q., & Tang, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37255-0_13
Boosting Real-Time Edge MOT Via Content-Aware Adaptive Keyframe Sampling
Liu, X., Xu, T., Qin, S., & Ji, D. (2026) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case69030.2026.11704345
Tkaczyk, K., & Sitnik, R. (2026) · Sensors · doi:10.3390/s26206653
Hyperspectral video object tracking: A review and benchmark
Chen, Y., Yuan, Q., Yokoya, N., Wang, J., Xuan, W., Chen, H., Zheng, Z., Li, Z., Tang, Y., Zhou, J. W., et al. (2026) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2026.10.014
Metadata
- Authors
- Yan, B., Peng, H., Wu, K., Wang, D., Fu, J., & Lu, H.
- Affiliations
- Dalian University of Technology (CN)
- Microsoft Research Asia (China) (CN)
- Sun Yat-sen University (CN)
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 15175-15184
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3173344965
- Cited by
- 277
- References
- 59
- Citations by year
- 2026: 32 · 2025: 72 · 2024: 77 · 2023: 50 · 2022: 40 · 2021: 6
- FWCI
- 14.15
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- object tracking, lightweight neural networks, neural architecture search, resource-constrained deployment, mobile devices, model compression
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
