Related papers: Learning Correlation Structures for Vision Transfo…

Transformers have been successfully used in various fields and are becoming the standard tools in computer vision. However, self-attention, a core component of transformers, has a quadratic complexity problem, which limits the use of…

Vision transformer (ViT) expands the success of transformer models from sequential data to images. The model decomposes an image into many smaller patches and arranges them into a sequence. Multi-head self-attentions are then applied to the…

Video summarization is among challenging tasks in computer vision, which aims at identifying highlight frames or shots over a lengthy video input. In this paper, we propose an novel attention-based framework for video summarization with…

Transformers have been successfully applied to the visual tracking task and significantly promote tracking performance. The self-attention mechanism designed to model long-range dependencies is the key to the success of Transformers.…

The paradigm of Transformers using the self-attention mechanism has manifested its advantage in learning graph-structured data. Yet, Graph Transformers are capable of modeling full range dependencies but are often deficient in extracting…

For person re-identification (re-id), attention mechanisms have become attractive as they aim at strengthening discriminative features and suppressing irrelevant ones, which matches well the key of re-id, i.e., discriminative feature…

Correlation has a critical role in the tracking field, especially in recent popular Siamese-based trackers. The correlation operation is a simple fusion method that considers the similarity between the template and the search region.…

Advanced deep Convolutional Neural Networks (CNNs) have shown great success in video-based person Re-Identification (Re-ID). However, they usually focus on the most obvious regions of persons with a limited global representation ability.…

Recently, Vision Transformers (ViTs) have attracted a lot of attention in the field of computer vision. Generally, the powerful representative capacity of ViTs mainly benefits from the self-attention mechanism, which has a high computation…

Vision-Language Models (vLLMs) have emerged as powerful architectures for joint reasoning over visual and textual inputs, enabling breakthroughs in image captioning, cross modal retrieval, and multimodal dialogue. However, as these models…

Recently, substantial research effort has focused on how to apply CNNs or RNNs to better extract temporal patterns from videos, so as to improve the accuracy of video classification. In this paper, however, we show that temporal…

LiDAR-generated point clouds are crucial for perceiving outdoor environments. The segmentation of point clouds is also essential for many applications. Previous research has focused on using self-attention and convolution (local attention)…

Site-Net is a transformer architecture that models the periodic crystal structures of inorganic materials as a labelled point set of atoms and relies entirely on global self-attention and geometric information to guide learning. Site-Net…

Inspired by the human cognitive system, attention is a mechanism that imitates the human cognitive awareness about specific information, amplifying critical details to focus more on the essential aspects of data. Deep learning has employed…

We consider the problem of comparing the similarity of image sets with variable-quantity, quality and un-ordered heterogeneous images. We use feature restructuring to exploit the correlations of both inner$\&$inter-set images. Specifically,…

Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales quadratically w.r.t. the input patch number. Thus, existing solutions commonly…

Outdoor images often suffer from severe degradation due to rain, haze, and noise, impairing image quality and challenging high-level tasks. Current image restoration methods struggle to handle complex degradation while maintaining…

It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between video frames. The recent advances in this research have been…

Humans are very good at directing their visual attention toward relevant areas when they search for different types of objects. For instance, when we search for cars, we will look at the streets, not at the top of buildings. The motivation…

Over the past few years, vision transformers (ViTs) have consistently demonstrated remarkable performance across various visual recognition tasks. However, attempts to enhance their robustness have yielded limited success, mainly focusing…