Related papers: MixFormer: End-to-End Tracking with Iterative Mixe…

We introduce MM-Mixing, a multi-modal mixing alignment framework for 3D understanding. MM-Mixing applies mixing-based methods to multi-modal data, preserving and optimizing cross-modal connections while enhancing diversity and improving…

Tracking multiple particles in noisy and cluttered scenes remains challenging due to a combinatorial explosion of trajectory hypotheses, which scales super-exponentially with the number of particles and frames. The transformer architecture…

Correlation acts as a critical role in the tracking field, especially in recent popular Siamese-based trackers. The correlation operation is a simple fusion manner to consider the similarity between the template and the search region.…

Modern multi-object tracking (MOT) system usually involves separated modules, such as motion model for location and appearance model for data association. However, the compatible problems within both motion and appearance models are always…

The Segment Anything Model (SAM) is a popular vision foundation model; however, its high computational and memory demands make deployment on resource-constrained devices challenging. While Post-Training Quantization (PTQ) is a practical…

Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods used a subset of combinations of component functions and weight matrices within the random feature paradigm. We…

Despite great progress in multimodal tracking, these trackers remain too heavy and expensive for resource-constrained devices. To alleviate this problem, we propose LightFC-X, a family of lightweight convolutional RGB-X trackers that…

We introduce Mixture-based Feature Space Learning (MixtFSL) for obtaining a rich and robust feature representation in the context of few-shot image classification. Previous works have proposed to model each base class either with a single…

Object detection has witnessed significant progress by relying on large, manually annotated datasets. Annotating such datasets is highly time consuming and expensive, which motivates the development of weakly supervised and few-shot object…

Recently, there has been a growing interest in Long-term Time Series Forecasting (LTSF), which involves predicting long-term future values by analyzing a large amount of historical time-series data to identify patterns and trends. There…

Long-term weather forecasting is critical for socioeconomic planning and disaster preparedness. While recent approaches employ finetuning to extend prediction horizons, they remain constrained by the issues of catastrophic forgetting, error…

The recently proposed Conformer model has become the de facto backbone model for various downstream speech tasks based on its hybrid attention-convolution architecture that captures both local and global features. However, through a series…

Window-based transformers excel in large-scale point cloud understanding by capturing context-aware representations with affordable attention computation in a more localized manner. However, the sparse nature of point clouds leads to a…

Classification-regression prediction networks have realized impressive success in several modern deep trackers. However, there is an inherent difference between classification and regression tasks, so they have diverse even opposite demands…

Mainstream visual object tracking frameworks predominantly rely on template matching paradigms. Their performance heavily depends on the quality of template features, which becomes increasingly challenging to maintain in complex scenarios…

Multi-object tracking (MOT) has profound applications in a variety of fields, including surveillance, sports analytics, self-driving, and cooperative robotics. Despite considerable advancements, existing MOT methodologies tend to falter…

The use of multimodal data in assisted diagnosis and segmentation has emerged as a prominent area of interest in current research. However, one of the primary challenges is how to effectively fuse multimodal features. Most of the current…

In the field of multi-organ medical image segmentation, recent methods frequently employ Transformers to capture long-range dependencies from image features. However, these methods overlook the high computational cost of Transformers and…

Leveraging information across diverse modalities is known to enhance performance on multimodal segmentation tasks. However, effectively fusing information from different modalities remains challenging due to the unique characteristics of…

Transformers have become the dominant architecture across a wide range of domains, largely due to the effectiveness of multi-head attention in capturing diverse representation subspaces. However, standard multi-head attention activates all…