Related papers: Exploiting Lightweight Hierarchical ViT and Dynami…
Gait recognition is a biometric technology that recognizes the identity of humans through their walking patterns. Compared with other biometric technologies, gait recognition is more difficult to disguise and can be applied to the condition…
Tracking multiple objects in videos relies on modeling the spatial-temporal interactions of the objects. In this paper, we propose a solution named TransMOT, which leverages powerful graph transformers to efficiently model the spatial and…
In autonomous driving, deep models have shown remarkable performance across various visual perception tasks with the demand of high-quality and huge-diversity training datasets. Such datasets are expected to cover various driving scenarios…
Accurate tracking is still a challenging task due to appearance variations, pose and view changes, and geometric deformations of target in videos. Recent anchor-free trackers provide an efficient regression mechanism but fail to produce…
3D single object tracking plays an essential role in many applications, such as autonomous driving. It remains a challenging problem due to the large appearance variation and the sparsity of points caused by occlusion and limited sensor…
In recent years, the integration of advanced imaging techniques and deep learning methods has significantly advanced computer-aided diagnosis (CAD) systems for breast cancer detection and classification. Transformers, which have shown great…
Diffusion Transformers (DiT) have attracted significant attention in research. However, they suffer from a slow convergence rate. In this paper, we aim to accelerate DiT training without any architectural modification. We identify the…
Tracking has traditionally been the art of following interest points through space and time. This changed with the rise of powerful deep networks. Nowadays, tracking is dominated by pipelines that perform object detection followed by…
Spiking Neural Networks (SNNs) promise energy-efficient vision, but applying them to RGB visual tracking remains difficult: Existing SNN tracking frameworks either do not fully align with spike-driven computation or do not fully leverage…
The main problem in RGB-T tracking is the correct and optimal merging of the cross-modal features of visible and thermal images. Some previous methods either do not fully exploit the potential of RGB and TIR information for channel and…
Video object removal and inpainting are critical tasks in the fields of computer vision and multimedia processing, aimed at restoring missing or corrupted regions in video sequences. Traditional methods predominantly rely on flow-based…
A practical long-term tracker typically contains three key properties, i.e. an efficient model design, an effective global re-detection strategy and a robust distractor awareness mechanism. However, most state-of-the-art long-term trackers…
Vision Transformer (ViT) has demonstrated promising performance in computer vision tasks, comparable to state-of-the-art neural networks. Yet, this new type of deep neural network architecture is vulnerable to adversarial attacks limiting…
Deep learning inference that needs to largely take place on the 'edge' is a highly computational and memory intensive workload, making it intractable for low-power, embedded platforms such as mobile nodes and remote security applications.…
Diffusion models have achieved remarkable progress in high-fidelity image, video, and audio generation, yet inference remains computationally expensive. Nevertheless, current diffusion acceleration methods based on distributed parallelism…
Data-hungry HSI classification methods require high-quality labeled HSIs, which are often costly to obtain. This characteristic limits the performance potential of data-driven methods when dealing with limited annotated samples. Bridging…
Tracking subjects in videos is one of the most widely used functions in camera-based IoT applications such as security surveillance, smart city traffic safety enhancement, vehicle to pedestrian communication and so on. In the computer…
Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an efficient DiT…
Due to the complex attention mechanisms and model design, most existing vision Transformers (ViTs) can not perform as efficiently as convolutional neural networks (CNNs) in realistic industrial deployment scenarios, e.g. TensorRT and…
Recently, masked image modeling (MIM) has offered a new methodology of self-supervised pre-training of vision transformers. A key idea of efficient implementation is to discard the masked image patches (or tokens) throughout the target…