NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object Tracking
Not on the map. Why?
Abstract (arXiv)
Many current visual object tracking benchmarks such as OTB100, NfS, UAV123, LaSOT, and GOT-10K, predominantly contain day-time scenarios while the challenges posed by the night-time has been less investigated. It is primarily because of the lack of a large-scale, well-annotated night-time benchmark for rigorously evaluating tracking algorithms. To this end, this paper presents NT-VOT211, a new benchmark tailored for evaluating visual object tracking algorithms in the challenging night-time conditions. NT-VOT211 consists of 211 diverse videos, offering 211,000 well-annotated frames with 8 attributes including camera motion, deformation, fast motion, motion blur, tiny target, distractors, occlusion and out-of-view. To the best of our knowledge, it is the largest night-time tracking benchmark to-date that is specifically designed to address unique challenges such as adverse visibility, image blur, and distractors inherent to night-time tracking scenarios. Through a comprehensive analysis of results obtained from 42 diverse tracking algorithms on NT-VOT211, we uncover the strengths and limitations of these algorithms, highlighting opportunities for enhancements in visual object tracking, particularly in environments with suboptimal lighting. Besides, a leaderboard for revealing performance rankings, annotation tools, comprehensive meta-information and all the necessary code for reproducibility of results is made publicly available. We believe that our NT-VOT211 benchmark will not only be instrumental in facilitating field deployment of VOT algorithms, but will also help VOT enhancements and it will unlock new real-world tracking applications. Our dataset and other assets can be found at: {https://github.com/LiuYuML/NV-VOT211.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 45 of its 61 references that are in the map. First posted on arXiv 27 Oct 2024.
Builds on
45 of 61 references.
References · 45
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
- 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 566
- 2018GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wildcited by 471
- 2018LaSOT: A High-quality Benchmark for Large-scale Single Object Trackingcited by 424
- 2021Transformer Trackingcited by 412
- 2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 348
- 2019Learning Discriminative Model Prediction for Trackingcited by 344
- 2018TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wildcited by 342
- 2022Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Frameworkcited by 328
- 2022MixFormer: End-to-End Tracking with Iterative Mixed Attentioncited by 278
- 2018Fast Online Object Tracking and Segmentation: A Unifying Approachcited by 272
33 more
- 2021Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Trackingcited by 220
- 2020Ocean: Object-aware Anchor-free Trackingcited by 212
- 2018Distractor-aware Siamese Networks for Visual Object Trackingcited by 187
- 2019Deeper and Wider Siamese Networks for Real-Time Visual Trackingcited by 156
- 2017Need for Speed: A Benchmark for Higher Frame Rate Object Trackingcited by 137
- 2022AiATrack: Attention in Attention for Transformer Visual Trackingcited by 137
- 2021Learning Target Candidate Association to Keep Track of What Not to Trackcited by 131
- 2021Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmarkcited by 124
- 2020Know Your Surroundings: Exploiting Scene Information for Object Trackingcited by 119
- 2022Transforming Model Prediction for Trackingcited by 117
- 2015A Novel Performance Evaluation Methodology for Single-Target Trackerscited by 113
- 2022Towards Grand Unification of Object Trackingcited by 93
- 2021STMTrack: Template-free Visual Tracking with Space-time Memory Networkscited by 91
- 2020Learning What to Learn for Video Object Segmentationcited by 89
- 2021LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Searchcited by 82
- 2016Learning Spatially Regularized Correlation Filters for Visual Trackingcited by 66
- 2017Learning Background-Aware Correlation Filters for Visual Trackingcited by 65
- 2018Learning Spatial-Temporal Regularized Correlation Filters for Visual Trackingcited by 63
- 2015Staple: Complementary Learners for Real-Time Trackingcited by 60
- 2022Unsupervised Domain Adaptation for Nighttime Aerial Trackingcited by 56
- 2021Efficient Visual Tracking with Exemplar Transformerscited by 48
- 2022Robust Visual Tracking by Segmentationcited by 38
- 2021All-Day Object Tracking for Unmanned Aerial Vehiclecited by 28
- 2023Target-Aware Tracking with Long-term Context Attentioncited by 27
- 2023Tracker Meets Night: A Transformer Enhancer for UAV Trackingcited by 23
- 2022AVisT: A Benchmark for Visual Object Tracking in Adverse Visibilitycited by 22
- 2020Learning to Fuse Asymmetric Feature Maps in Siamese Trackerscited by 18
- 2021ADTrack: Target-Aware Dual Filter Learning for Real-Time Anti-Dark UAV Trackingcited by 17
- 2022ProContEXT: Exploring Progressive Context Transformer for Trackingcited by 14
- 2022Towards Sequence-Level Training for Visual Trackingcited by 13
- 2017Robust Estimation of Similarity Transformation for Visual Object Trackingcited by 10
- 2018High-speed Tracking with Multi-kernel Correlation Filterscited by 6
- 2022How Well Do Vision Transformers (VTs) Transfer To The Non-Natural Image Domain? An Empirical Study Involving Art Classificationcited by 3
Built on by
Citing papers per year: 2025: 3.
3 papers.