LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking
This provides a high-quality, large-scale benchmark for the computer vision community to advance single object tracking, though it is incremental as it builds on existing benchmark efforts.
The authors introduced LaSOT, a large-scale benchmark for single object tracking with 1,400 sequences and over 3.5 million frames, providing dense annotations and language specifications to facilitate training and evaluation of tracking algorithms, with experimental results showing significant room for improvement in current methods.
In this paper, we present LaSOT, a high-quality benchmark for Large-scale Single Object Tracking. LaSOT consists of 1,400 sequences with more than 3.5M frames in total. Each frame in these sequences is carefully and manually annotated with a bounding box, making LaSOT the largest, to the best of our knowledge, densely annotated tracking benchmark. The average video length of LaSOT is more than 2,500 frames, and each sequence comprises various challenges deriving from the wild where target objects may disappear and re-appear again in the view. By releasing LaSOT, we expect to provide the community with a large-scale dedicated benchmark with high quality for both the training of deep trackers and the veritable evaluation of tracking algorithms. Moreover, considering the close connections of visual appearance and natural language, we enrich LaSOT by providing additional language specification, aiming at encouraging the exploration of natural linguistic feature for tracking. A thorough experimental evaluation of 35 tracking algorithms on LaSOT is presented with detailed analysis, and the results demonstrate that there is still a big room for improvements.