http://repo.lib.jfn.ac.lk/ujrr/handle/123456789/128 2026-08-24T11:23:13Z 2026-08-24T11:23:13Z Kugarajeevan, J. Kokul, T. Ramanan, A. Fernando, S. http://repo.lib.jfn.ac.lk/ujrr/handle/123456789/12904 2026-08-24T05:34:09Z 2023-01-01T00:00:00Z

Title: Transformers in Single Object Tracking: An Experimental Survey Authors: Kugarajeevan, J.; Kokul, T.; Ramanan, A.; Fernando, S. Abstract: Single-object tracking is a well-known and challenging research topic in computer vision. Over the last two decades, numerous researchers have proposed various algorithms to solve this problem and achieved promising results. Recently, Transformer-based tracking approaches have ushered in a new era in single-object tracking by introducing new perspectives and achieving superior tracking robustness. In this paper, we conduct an in-depth literature analysis of Transformer tracking approaches by categorizing them into CNN-Transformer based trackers, Two-stream Two-stage fully-Transformer based trackers, and One-stream One-stage fully-Transformer based trackers. In addition, we conduct experimental evaluations to assess their tracking robustness and computational efficiency using publicly available benchmark datasets. Furthermore, we measure their performances on different tracking scenarios to identify their strengths and weaknesses in particular situations. Our survey provides insights into the underlying principles of Transformer tracking approaches, the challenges they encounter, and the future directions they may take.

2023-01-01T00:00:00Z Kugarajeevan, J. Kokul, T. Ramanan, A. Fernando, S. http://repo.lib.jfn.ac.lk/ujrr/handle/123456789/12903 2026-08-24T05:26:55Z 2024-01-01T00:00:00Z

Title: Transformer Tracking Using Spatiotemporal Features Authors: Kugarajeevan, J.; Kokul, T.; Ramanan, A.; Fernando, S. Abstract: Recent approaches in single-object tracking leverage Transformer-based architectures to achieve state-of-the-art performance by utilizing the attention mechanism between target templates and search region patches. However, most existing trackers fail to capture the temporal information of the target object present in the sequences of frames, making them unsuitable for capturing changes in the target’s appearance over time. This leads to suboptimal performance in real-world scenarios where the target’s appearance can change significantly due to variations such as occlusions, deformations, and abrupt movements. To overcome this limitation, a Transformer-based tracking framework is introduced that simultaneously captures the spatial and temporal features of the target object and utilizes that knowledge to accurately locate the target. This is achieved by adapting the standard Transformer encoder architecture, enabling the direct extraction of spatiotemporal features of the target object from a sequence of frames. As the first step, the sequences of template frames and search region are partitioned into non-overlapping spatiotemporal patches, which are then tokenized and processed by the Transformer encoder to capture spatiotemporal features. Additionally, the Transformer encoder is initialized with spatiotemporal masked autoencoders, which are trained to capture the relationship between patches through self-supervised learning. Extensive experiments on the GOT-10k benchmark dataset demonstrate that our tracker surpasses current state-of-the-art methods, achieving an average overlap of 70.9%, a success rate of 82.4% at a 0.5 threshold, and a success rate of 66.3% at a 0.75 threshold on test data, while maintaining real-time processing speed of 47 frames per second on an NVIDIA P100 GPU.

2024-01-01T00:00:00Z Kugarajeevan, J. Kokul, T. Ramanan, A. Fernando, S. http://repo.lib.jfn.ac.lk/ujrr/handle/123456789/12902 2026-08-24T05:17:58Z 2025-01-01T00:00:00Z

Title: Selective Information Flow for Transformer Tracking Authors: Kugarajeevan, J.; Kokul, T.; Ramanan, A.; Fernando, S. Abstract: Fully transformer-based one-stream trackers have demonstrated outstanding performance on challenging benchmark datasets over the past three years. These trackers enable bidirectional information flow between all target template and search region tokens to compute attention features without assessing its impact on the tracker’s discriminative capability. Our study found that the information flow from a large portion of background tokens in the search region diminishes the importance of the target-specific features of the template. Moreover, previous transformer-based trackers fail to consider cues from the dynamic background region, even though it contains information about distracting similar objects. To address the identified limitations in transformer tracking, we propose a novel Selective Information Flow Tracking (SIFTrack) framework to enhance the tracker’s discriminative capability by selectively allowing information flow between different types of token groups. In the early encoder layers of the proposed SIFTrack, interactions from all search tokens to target template tokens are blocked to enrich target-specific feature extraction. In the deeper encoder layers, search tokens are partitioned into target and non-target tokens based on their attention scores. Then, bidirectional flow from target search tokens to template tokens is allowed to capture the appearance changes of the target. In addition, by including tokens from the dynamic background, SIFTrack effectively avoids distractor objects by capturing cues from the area surrounding the target. The proposed SIFTrack demonstrated outstanding performance in challenging benchmarks, particularly excelling in the one-shot tracking benchmark GOT-10k, achieving an average overlap of 74.6%. The code, models, and results of this work are available at https://github.com/JananiKugaa/SIFTrack.

2025-01-01T00:00:00Z Kugarajeevan, J. Kokul, T. Ramanan, A. Fernando, S. http://repo.lib.jfn.ac.lk/ujrr/handle/123456789/12901 2026-08-24T05:17:24Z 2026-01-01T00:00:00Z

Title: Context-Aware Token Pruning and Discriminative Selective Attention for Transformer Tracking Authors: Kugarajeevan, J.; Kokul, T.; Ramanan, A.; Fernando, S. Abstract: One-stream Transformer-based trackers have demonstrated remarkable performance by concatenating template and search region tokens, thereby enabling joint attention across all tokens. However, enabling a large number of background search tokens to attend to the target template tokens weakens the tracker’s discriminative capability. Several token pruning methods have been proposed to mitigate background interference; however, they often remove tokens near the target, leading to the loss of essential contextual information and degraded tracking performance. Moreover, the presence of distractors within the search tokens further reduces the tracker’s ability to accurately identify the target. To address these limitations, we propose CPDATrack, a novel tracking framework designed to suppress interference from background and distractor tokens while enhancing computational efficiency. First, a learnable module is integrated between two designated encoder layers to estimate the probability of each search token being associated with the target. Based on these estimates, less-informative background tokens are pruned from the search region while preserving the contextual cues surrounding the target. To further suppress background interference, a discriminative selective attention mechanism is employed that fully blocks search-to-template attention in the early layers. In the subsequent encoder layers, high-probability target tokens are selectively extracted from a localized region to attend to the template tokens, thereby reducing the influence of background and distractor tokens. The proposed CPDATrack achieves state-of-the-art performance on multiple benchmarks, particularly excelling in one-shot tracking on GOT-10k with an average overlap of 75.1%. The code, models, and results of this work are available at https://github.com/JananiKugaa/CPDATrack.git.

2026-01-01T00:00:00Z