LaSOT: A High-quality Large-scale Single Object Tracking Benchmark

By Heng Fan, Hexin Bai, Liting Lin, Fan Yang, Peng Chu, Ge Deng, Sijia Yu, Harshit, Mingzhen Huang, Juehuan Liu and 4 more. International Journal of Computer Vision, 2020

396 citations recorded by the source corpus.

Despite great recent advances in visual tracking, its further development, including both algorithm design and evaluation, is limited due to lack of dedicated large-scale benchmarks. To address this problem, we present LaSOT, a high-quality Large-scale Single Object Tracking benchmark. LaSOT contains a diverse selection of 85 object classes, and offers 1550 totaling more than 3.87 million frames. Each video frame is carefully and manually annotated with a bounding box. This makes LaSOT, to our knowledge, the largest densely annotated tracking benchmark. Our goal in releasing LaSOT is to provide a dedicated high quality platform for both training and evaluation of trackers. The average video length of LaSOT is around 2500 frames, where each video contains various challenge factors that exist in real world video footage,such as the targets disappearing and re-appearing. These longer video lengths allow for the assessment of long-term trackers. To take advantage of the close connection between visual appearance and natural language, we provide language specification for each video in LaSOT. We believe such additions will allow for future research to use linguistic features to improve tracking. Two protocols, full-overlap and one-shot, are designated for flexible assessment of trackers. We extensively evaluate 48 baseline trackers on LaSOT with in-depth analysis, and results reveal that there still exists significant room for improvement. The complete benchmark, tracking results as well as analysis are available at http://vision.cs.stonybrook.edu/~lasot/.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e284bc13c2b76d0d0c7ad61d976f8a9d3eef8461

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

AiATrack: Attention in Attention for Transformer Visual Tracking (2022, methodology): “To validate the importance of the proposed components in our tracker, we conduct ablation studies on LaSOT testing set and its new extension set [16], totaling 430 diverse videos.”
Learning Target Candidate Association to Keep Track of What Not to Track (2021, methodology): “All results, except ours and SuperDiMP, are obtained from [20], e.”
Perception Test: A Diagnostic Benchmark for Multimodal Video Models (2023, background): “SiamFC was chosen due to its high-performance on a number of single-object tracking benchmarks when running in zero-shot setting [21].”
Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework (2022, methodology): “Method Source LaSOT [14] LaSOText [13] TrackingNet [35] GOT-10k ∗ [20] AUC PNorm P AUC PNorm P AUC PNorm P AO SR0.”
SwinTrack: A Simple and Strong Baseline for Transformer Tracking (2021, methodology): “The recently proposed LaSOText [14] is an extension of LaSOT by adding 150 extra videos from 15 new categories.”
SeqTrack: Sequence to Sequence Learning for Visual Object Tracking (2023, background): “LaSOT ext [15] is a recently released dataset with 150 video sequences and 15 object classes.”
Transforming Model Prediction for Tracking (2022, methodology): “11 the LaSOTExtSub [19] test set in Fig.”