mlsanityData to 7 Oct 2026

A Twofold Siamese Network for Real-Time Object Tracking

arXiv 1802.08817 ↗First posted 24 Feb 2018cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

Observing that Semantic features learned in an image classification task and Appearance features learned in a similarity matching task complement each other, we build a twofold Siamese network, named SA-Siam, for real-time object tracking. SA-Siam is composed of a semantic branch and an appearance branch. Each branch is a similarity-learning Siamese network. An important design choice in SA-Siam is to separately train the two branches to keep the heterogeneity of the two types of features. In addition, we propose a channel attention mechanism for the semantic branch. Channel-wise weights are computed according to the channel activations around the target position. While the inherited architecture from SiamFC citeSiamFC allows our tracker to operate beyond real-time, the twofold design and the attention mechanism significantly improve the tracking performance. The proposed SA-Siam outperforms all other real-time trackers by a large margin on OTB-2013/50/100 benchmarks.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 23; 2022: 13; 2023: 9; 2024: 7; 2025: 5; 2026: 5.

62 papers.

Sort:

By area:

  1. 2021Transformer Trackingcited by 412
  2. 2024Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streamscited by 160
  3. 2025Flash-VStream: Efficient Real-Time Understanding for Long Video Streamscited by 78
  4. 2021SiamMOT: Siamese Multi-Object Trackingcited by 62
  5. 2024GuardT2I: Defending Text-to-Image Models from Adversarial Promptscited by 61
  6. 2022Accelerating DETR Convergence via Semantic-Aligned Matchingcited by 58
  7. 20213D Siamese Voxel-to-BEV Tracker for Sparse Point Cloudscited by 54
  8. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
  9. 2021Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlookcited by 45
  10. 2023Synchronize Feature Extracting and Matching: A Single Branch Framework for 3D Object Trackingcited by 16
  11. 2021Learning Tracking Representations via Dual-Branch Fully Transformer Networkscited by 15
  12. 2022High-Performance Transformer Trackingcited by 14
38 more
  1. 2024Generative AI for Unmanned Vehicle Swarms: Challenges, Applications and Opportunitiescited by 14
  2. 2022SiamMask: A Framework for Fast Online Object Tracking and Segmentationcited by 13
  3. 2023The Evolution of Distributed Systems for Graph Neural Networks and their Origin in Graph Processing and Deep Learning: A Surveycited by 13
  4. 2022Siamese Object Tracking for Unmanned Aerial Vehicle: A Review and Comprehensive Analysiscited by 11
  5. 2023T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learningcited by 11
  6. 2023Correlation Pyramid Network for 3D Single Object Trackingcited by 10
  7. 2022Learning Localization-aware Target Confidence for Siamese Visual Trackingcited by 7
  8. 2022Vision-based Human Fall Detection Systems using Deep Learning: A Reviewcited by 7
  9. 2022Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusioncited by 7
  10. 2026Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language Modelscited by 7
  11. 2021Multi-domain Collaborative Feature Representation for Robust Visual Object Trackingcited by 6
  12. 2021UHP-SOT: An Unsupervised High-Performance Single Object Trackercited by 6
  13. 2023FlakyFix: Using Large Language Models for Predicting Flaky Test Fix Categories and Test Code Repaircited by 6
  14. 2022Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV Trackingcited by 5
  15. 2023Adaptive Siamese Tracking with a Compact Latent Networkcited by 5
  16. 2024Distilling Channels for Efficient Deep Trackingcited by 5
  17. 2021SiamEvent: Event-based Object Tracking via Edge-aware Similarity Learning with Siamese Networkscited by 4
  18. 2021A Discriminative Single-Shot Segmentation Network for Visual Object Trackingcited by 4
  19. 2021Unsupervised Lightweight Single Object Tracking with UHP-SOT++cited by 3
  20. 2023SiamTHN: Siamese Target Highlight Network for Visual Trackingcited by 3
  21. 2023DFR-Net: Density Feature Refinement Network for Image Dehazing Utilizing Haze Density Differencecited by 3
  22. 2024SurgiTrack: Fine-Grained Multi-Class Multi-Tool Tracking in Surgical Videoscited by 3
  23. 2025A Simple Detector with Frame Dynamics is a Strong Trackercited by 3
  24. 2025Track-On2: Enhancing Online Point Tracking with Memorycited by 3
  25. 2021Classification of Long Noncoding RNA Elements Using Deep Convolutional Neural Networks and Siamese Networkscited by 2
  26. 2021Benchmarking Deep Trackers on Aerial Videoscited by 2
  27. 2021Object Tracking by Detection with Visual and Motion Cuescited by 1
  28. 2022SiamHAN: IPv6 Address Correlation Attacks on TLS Encrypted Traffic via Siamese Heterogeneous Graph Attention Networkcited by 1
  29. 2022SQ-Swin: a Pretrained Siamese Quadratic Swin Transformer for Lettuce Browning Predictioncited by 1
  30. 2022PhysiQ: Off-site Quality Assessment of Exercise in Physical Therapycited by 1
  31. 2024Multi-attention Associate Prediction Network for Visual Trackingcited by 1
  32. 2026DeTracker: Motion-decoupled Vehicle Detection and Tracking in Unstabilized Satellite Videoscited by 1
  33. 2021MFST: Multi-Features Siamese Trackercited by 0
  34. 2021Multiple Convolutional Features in Siamese Networks for Object Trackingcited by 0
  35. 2021Higher Performance Visual Tracking with Dual-Modal Localizationcited by 0
  36. 2021Matching Targets Across Domains with RADON, the Re-Identification Across Domain Networkcited by 0
  37. 2021DeepTracks: Geopositioning Maritime Vehicles in Video Acquired from a Moving Platformcited by 0
  38. 2021Improving Object Permanence using Agent Actions and Reasoningcited by 0

50 most cited of 62 All 62 (JSON)