Related papers: Efficient Attention-free Video Shift Transformers

While recent Transformer-based approaches have shown impressive performances on event-based object detection tasks, their high computational costs still diminish the low power consumption advantage of event cameras. Image-based works…

Transformers have sprung up in the field of computer vision. In this work, we explore whether the core self-attention module in Transformer is the key to achieving excellent performance in image recognition. To this end, we build an…

Vision transformers (ViTs) have found only limited practical use in processing images, in spite of their state-of-the-art accuracy on certain benchmarks. The reason for their limited use include their need for larger training datasets and…

This paper introduces EasyAnimate, an efficient and high quality video generation framework that leverages diffusion transformers to achieve high-quality video production, encompassing data processing, model training, and end-to-end…

Vision Transformers have achieved impressive performance in many vision tasks. While the token mixer or attention block has been studied in great detail, much less research has been devoted to the channel mixer or feature mixing block (FFN…

Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…

Vision Transformers are very popular nowadays due to their state-of-the-art performance in several computer vision tasks, such as image classification and action recognition. Although their performance has been greatly enhanced through…

Visual recognition has been dominated by convolutional neural networks (CNNs) for years. Though recently the prevailing vision transformers (ViTs) have shown great potential of self-attention based models in ImageNet classification, their…

While state-of-the-art vision transformer models achieve promising results in image classification, they are computationally expensive and require many GFLOPs. Although the GFLOPs of a vision transformer can be decreased by reducing the…

Vision Transformer (ViT) has demonstrated significant potential in various vision tasks due to its strong ability in modelling long-range dependencies. However, such success is largely fueled by training on massive samples. In real…

In this paper, we present a novel Motion-Attentive Transition Network (MATNet) for zero-shot video object segmentation, which provides a new way of leveraging motion information to reinforce spatio-temporal object representation. An…

The attention operator is arguably the key distinguishing factor of transformer architectures, which have demonstrated state-of-the-art performance on a variety of tasks. However, transformer attention operators often impose a significant…

Attention, as a core layer of the ubiquitous Transformer architecture, is the bottleneck for large language models and long-context applications. FlashAttention elaborated an approach to speed up attention on GPUs through minimizing memory…

Transformer-based video diffusion models (VDMs) deliver state-of-the-art video generation quality but are constrained by the quadratic cost of self-attention, making long sequences and high resolutions computationally expensive. While…

Vision Transformers have achieved impressive performance in video classification, while suffering from the quadratic complexity caused by the Softmax attention mechanism. Some studies alleviate the computational costs by reducing the number…

This research paper addresses the challenges associated with traffic sign detection in self-driving vehicles and driver assistance systems. The development of reliable and highly accurate algorithms is crucial for the widespread adoption of…

It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to…

The Transformer architecture has revolutionized deep learning, delivering the state-of-the-art performance in areas such as natural language processing, computer vision, and time series prediction. However, its core component,…

We propose a novel solution for the task of video panoptic segmentation, that simultaneously predicts pixel-level semantic and instance segmentation and generates clip-level instance tracks. Our network, named VPS-Transformer, with a hybrid…

Video restoration is a low-level vision task that seeks to restore clean, sharp videos from quality-degraded frames. One would use the temporal information from adjacent frames to make video restoration successful. Recently, the success of…