Search

Similarity-based approaches have made significant progress in visual object tracking (VOT). Although these methods work well in simple scenes, they ignore the continuous spatio-temporal connection of the object in the video sequence. For this reason, tracking by spatial matching solely can lead to tracking failures because of distractors and occlusion. In this paper, we propose a spatio-temporal joint-modeling tracker named STTrack which implicitly builds continuous connections between the temporal and spatial aspects of the sequence. Specifically, we first design a time-sequence iteration strategy (TSIS) to concentrate on the temporal connection of the object in the video sequence. Then, we propose a novel spatial temporal interaction Transformer network (STIN) to capture the spatio-temporal correlation of the object between frames. The proposed STIN module is robust in object occlusion because it explores the dynamic state change dependencies of the object. Finally, we introduce a spatio-temporal query to suppress distractors by iteratively propagating the target prior. Extensive experiments on six tracking benchmark datasets demonstrate that the proposed STTrack achieves excellent performance while operating in real-time. The code is publicly available at https://github.com/nubsym/STTrack. [ABSTRACT FROM AUTHOR]

Landmark detection is a fundamental task aiming at identifying specific landmarks that serve as representations of distinct object features within an image. However, the present landmark detection algorithms often adopt complex architectures and are trained in a supervised manner using large datasets to achieve satisfactory performance. When faced with limited data, these algorithms tend to experience a notable decline in accuracy. To address these drawbacks, we propose a novel diffusion-based network (DBN) for unsupervised landmark detection, which leverages the generation ability of the diffusion models to detect the landmark locations. In particular, we introduce a dual-branch encoder (DualE) for extracting visual features and predicting landmarks. Additionally, we lighten the decoder structure for faster inference, referred to as LightD. By this means, we avoid relying on extensive data comparison and the necessity of designing complex architectures as in previous methods. Experiments on CelebA, AFLW, 300W and Deepfashion benchmarks have shown that DBN performs state-of-the-art compared to the existing methods. Furthermore, DBN shows robustness even when faced with limited data cases. [ABSTRACT FROM AUTHOR]