Related papers: iFormer: Integrating ConvNet and Transformer for M…

We present a novel Transformer-based network architecture for instance-aware image-to-image translation, dubbed InstaFormer, to effectively integrate global- and instance-level information. By considering extracted content features from an…

Time series forecasting (TSF) faces challenges in modeling complex intra-channel temporal dependencies and inter-channel correlations. Although recent research has highlighted the efficiency of linear architectures in capturing global…

Person re-identification aims to retrieve persons in highly varying settings across different cameras and scenarios, in which robust and discriminative representation learning is crucial. Most research considers learning representations…

Amodal Instance Segmentation (AIS) aims to segment the region of both visible and possible occluded parts of an object instance. While Mask R-CNN-based AIS approaches have shown promising results, they are unable to model high-level…

Active research is currently underway to enhance the efficiency of vision transformers (ViTs). Most studies have focused solely on effective token mixers, overlooking the potential relationship with normalization. To boost diverse feature…

Recently, transformer-based models have demonstrated remarkable performance on audio-visual segmentation (AVS) tasks. However, their expensive computational cost makes real-time inference impractical. By characterizing attention maps of the…

Crowd counting, which is a key computer vision task, has emerged as a fundamental technology in crowd analysis and public safety management. However, challenges such as scale variations and complex backgrounds significantly impact the…

The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects. Through an examination of its adaptive behavior, we observe that while the spatial support for its neural…

Vision Transformer (ViT) has prevailed in computer vision tasks due to its strong long-range dependency modelling ability. \textcolor{blue}{However, its large model size and weak local feature modeling ability hinder its application in real…

Transformer models rely on self-attention to capture token dependencies but face challenges in effectively integrating positional information while allowing multi-head attention (MHA) flexibility. Prior methods often model semantic and…

Transformer models have recently garnered significant attention in image restoration due to their ability to capture long-range pixel dependencies. However, long-range attention often results in computational overhead without practical…

Hybrid Event-Based Vision Sensor (HybridEVS) is a novel sensor integrating traditional frame-based and event-based sensors, offering substantial benefits for applications requiring low-light, high dynamic range, and low-latency…

This paper proposes Omnidirectional Representations from Transformers (OmniNet). In OmniNet, instead of maintaining a strictly horizontal receptive field, each token is allowed to attend to all tokens in the entire network. This process can…

Recently, image restoration transformers have achieved comparable performance with previous state-of-the-art CNNs. However, how to efficiently leverage such architectures remains an open problem. In this work, we present Dual-former whose…

The Transformer architecture has become a cornerstone of modern artificial intelligence, but its core self-attention mechanism suffers from a complexity bottleneck that scales quadratically with sequence length, severely limiting its…

Object detection on visible (RGB) and infrared (IR) images, as an emerging solution to facilitate robust detection for around-the-clock applications, has received extensive attention in recent years. With the help of IR images, object…

Recent video recognition models utilize Transformer models for long-range spatio-temporal context modeling. Video transformer designs are based on self-attention that can model global context at a high computational cost. In comparison,…

There is a recent trend in the LiDAR perception field towards unifying multiple tasks in a single strong network with improved performance, as opposed to using separate networks for each task. In this paper, we introduce a new LiDAR…

This paper presents MOAT, a family of neural networks that build on top of MObile convolution (i.e., inverted residual blocks) and ATtention. Unlike the current works that stack separate mobile convolution and transformer blocks, we…

In accelerated MRI reconstruction, the anatomy of a patient is recovered from a set of under-sampled and noisy measurements. Deep learning approaches have been proven to be successful in solving this ill-posed inverse problem and are…