Siamese Natural Language Tracker: Tracking by Natural Language Descriptions with Siamese Trackers
This work addresses the tracking by natural language task for computer vision applications, offering a new baseline with incremental improvements.
The paper tackled the problem of visual tracking using natural language descriptions by proposing a Siamese Natural Language Tracker (SNLT), which improved Siamese trackers by 3 to 7 percentage points on benchmarks and achieved competitive performance at 50 frames per second.
We propose a novel Siamese Natural Language Tracker (SNLT), which brings the advancements in visual tracking to the tracking by natural language (NL) descriptions task. The proposed SNLT is applicable to a wide range of Siamese trackers, providing a new class of baselines for the tracking by NL task and promising future improvements from the advancements of Siamese trackers. The carefully designed architecture of the Siamese Natural Language Region Proposal Network (SNL-RPN), together with the Dynamic Aggregation of vision and language modalities, is introduced to perform the tracking by NL task. Empirical results over tracking benchmarks with NL annotations show that the proposed SNLT improves Siamese trackers by 3 to 7 percentage points with a slight tradeoff of speed. The proposed SNLT outperforms all NL trackers to-date and is competitive among state-of-the-art real-time trackers on LaSOT benchmarks while running at 50 frames per second on a single GPU.