Related papers: LiteTrack: Layer Pruning with Asynchronous Feature…

Hybrid vision transformers combine the elements of conventional neural networks (NN) and vision transformers (ViT) to enable lightweight and accurate detection. However, several challenges remain for their efficient deployment on…

3D single object tracking (SOT) in LiDAR point clouds is a critical task in computer vision and autonomous driving. Despite great success having been achieved, the inherent sparsity of point clouds introduces a dual-redundancy challenge…

Recently Transformer has been largely explored in tracking and shown state-of-the-art (SOTA) performance. However, existing efforts mainly focus on fusing and enhancing features generated by convolutional neural networks (CNNs). The…

The emergence of deep learning techniques has advanced the image segmentation task, especially for medical images. Many neural network models have been introduced in the last decade bringing the automated segmentation accuracy close to…

Vision transformers (ViTs) have emerged as a popular backbone for visual tracking. However, complete ViT architectures are too cumbersome to deploy for unmanned aerial vehicle (UAV) tracking which extremely emphasizes efficiency. In this…

Temporal information is crucial for visual tracking, but existing multi-frame trackers are vulnerable to model drift caused by naively aggregating noisy historical predictions. In this paper, we introduce DTPTrack, a lightweight and…

Vision Transformers (ViT) have shown rapid progress in computer vision tasks, achieving promising results on various benchmarks. However, due to the massive number of parameters and model design, \textit{e.g.}, attention mechanism,…

We present a novel method for efficiently producing semi-dense matches across images. Previous detector-free matcher LoFTR has shown remarkable matching capability in handling large-viewpoint change and texture-poor scenarios but suffers…

High-performance Transformer trackers have shown excellent results, yet they often bear a heavy computational load. Observing that a smaller input can immediately and conveniently reduce computations without changing the model, an easy…

Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos. Most methods obtain identities by associating detection boxes whose scores are higher than a threshold. The objects with low detection…

Visual object tracking is a fundamental and time-critical vision task. Recent years have seen many shallow tracking methods based on real-time pixel-based correlation filters, as well as deep methods that have top performance but need a…

Track materialization converts raw video into reusable object tracks that downstream queries can run against without rerunning tracking, but extracting those tracks efficiently and with high fidelity remains expensive. Prior systems reduce…

Simulating event streams from 3D scenes has become a common practice in event-based vision research, as it meets the demand for large-scale, high temporal frequency data without setting up expensive hardware devices or undertaking extensive…

Transformer-based models have improved visual tracking, but most still cannot run in real time on resource-limited devices, especially for unmanned aerial vehicle (UAV) tracking. To achieve a better balance between performance and…

Convolutional neural networks (CNN) based tracking approaches have shown favorable performance in recent benchmarks. Nonetheless, the chosen CNN features are always pre-trained in different task and individual components in tracking systems…

One-stream Transformer trackers have shown outstanding performance in challenging benchmark datasets over the last three years, as they enable interaction between the target template and search region tokens to extract target-oriented…

Recent DEtection TRansformer-based (DETR) models have obtained remarkable performance. Its success cannot be achieved without the re-introduction of multi-scale feature fusion in the encoder. However, the excessively increased tokens in…

We present DroTrack, a high-speed visual single-object tracking framework for drone-captured video sequences. Most of the existing object tracking methods are designed to tackle well-known challenges, such as occlusion and cluttered…

The rapid progress of generative AI has led to the emergence of new generative models, while existing detection methods struggle to keep pace, resulting in significant degradation in the detection performance. This highlights the urgent…

Visual tracking is challenging due to image variations caused by various factors, such as object deformation, scale change, illumination change and occlusion. Given the superior tracking performance of human visual system (HVS), an ideal…