Transformer-based algorithms, such as LoRAT, have significantly enhanced objecttracking performance. However, these approaches rely on a standard attention mechanism, which incurs quadratic token complexity, making real-time inference computationally expensive. In this paper, we introduce LoRATv2, a novel tracking framework that addresses these limitations with three main contributions. First, LoRATv2 integrates frame-wise causal attention, which ensures full selfattention within each frame while enabling causal dependencies across frames, significantly reducing computational overhead. Moreover, key-value (KV) caching is employed to efficiently reuse past embeddings for further speedup.

Visual attention, derived from cognitive neuroscience, facilitates human perception on the most pertinent subset of the sensory data. Recently, significant efforts have been made to exploit attention schemes to advance computer vision systems. For visual tracking, it is often challenging to track target objects undergoing large appearance changes. Attention maps facilitate visual tracking by selectively paying attention to temporal robust features. Existing tracking-by-detection approaches mainly use additional attention modules to generate feature weights as the classifiers are not equipped with such mechanisms. In this paper, we propose a reciprocative learning algorithm to exploit visual attention for training deep classifiers. The proposed algorithm consists of feed-forward and backward operations to generate attention maps, which serve as regularization terms coupled with the original classification loss function for training. The deep classifier learns to attend to the regions of target objects robust to appearance changes. Extensive experiments on large-scale benchmark datasets show that the proposed attentive tracking method performs favorably against the state-of-the-art approaches.

V astTrack consists of a few attractive properties: (1) V ast Object Category . In particular, it covers targets from 2,115 categories, significantly surpassing object classes of existing popular benchmarks ( e.g ., GOT -10k with 563 classes and LaSOT with 70 categories). Through providing such vast object classes, we expect to learn more general object tracking.

F .1 Why is There A Sample Imbalance Between Underwater and Open-air Objects?

To bridge this gap, we take the first step and introduce WebUOT -1M, i.e., the largest public UOT benchmark to date, sourced from

Neural Information Processing Systems http://nips.cc/

WeexpectSwinTracktoserveasa solid baseline for Transformer tracking and facilitate future research.