Related papers: Siamese Transformer Pyramid Networks for Real-Time…

Spiking Neural Networks (SNNs) offer a biologically inspired alternative to conventional artificial neural networks, with potential advantages in power efficiency due to their event-driven computation. Despite their promise, SNNs have yet…

Siamese trackers turn tracking into similarity estimation between a template and the candidate regions in the frame. Mathematically, one of the key ingredients of success of the similarity function is translation equivariance.…

Existing image-to-image translation (I2IT) methods are either constrained to low-resolution images or long inference time due to their heavy computational burden on the convolution of high-resolution feature maps. In this paper, we focus on…

Percolation theory serves as a cornerstone for studying phase transitions and critical phenomena, with broad implications in statistical physics, materials science, and complex networks. However, most machine learning frameworks for…

Multi-object tracking systems often consist of a combination of a detector, a short term linker, a re-identification feature extractor and a solver that takes the output from these separate components and makes a final prediction.…

Though U-Net has achieved tremendous success in medical image segmentation tasks, it lacks the ability to explicitly model long-range dependencies. Therefore, Vision Transformers have emerged as alternative segmentation structures recently,…

The encoding of the target in object tracking moves from the coarse bounding-box to fine-grained segmentation map recently. Revisiting de facto real-time approaches that are capable of predicting mask during tracking, we observed that they…

A strong visual object tracker nowadays relies on its well-crafted modules, which typically consist of manually-designed network architectures to deliver high-quality tracking results. Not surprisingly, the manual design process becomes a…

Automated medical image segmentation can assist doctors to diagnose faster and more accurate. Deep learning based models for medical image segmentation have made great progress in recent years. However, the existing models fail to…

Learned image compression (LIC) methods have exhibited promising progress and superior rate-distortion performance compared with classical image compression standards. Most existing LIC methods are Convolutional Neural Networks-based…

We recently proposed a convolutional neural network (CNN) for remote sensing image pansharpening obtaining a significant performance gain over the state of the art. In this paper, we explore a number of architectural and training variations…

Robust object tracking requires knowledge of tracked objects' appearance, motion and their evolution over time. Although motion provides distinctive and complementary information especially for fast moving objects, most of the recent…

Event cameras provide superior temporal resolution, dynamic range, power efficiency, and pixel bandwidth. Spiking Neural Networks (SNNs) naturally complement event data through discrete spike signals, making them ideal for event-based…

We present in this paper a new architecture, the Pattern Attention Transformer (PAT), that is composed of the new doughnut kernel. Compared with tokens in the NLP field, Transformer in computer vision has the problem of handling the high…

The long-standing tension between Pre- and Post-Norm remains an open problem in Transformer architecture, reflecting a fundamental trade-off between training stability and representational capacity. Prior attempts to combine their strengths…

Trackers that follow Siamese paradigm utilize similarity matching between template and search region features for tracking. Many methods have been explored to enhance tracking performance by incorporating tracking history to better handle…

Efficient large-scale inference of transformer-based large language models (LLMs) remains a fundamental systems challenge, frequently requiring multi-GPU parallelism to meet stringent latency and throughput targets. Conventional tensor…

Transformer-based trackers have achieved strong accuracy on the standard benchmarks. However, their efficiency remains an obstacle to practical deployment on both GPU and CPU platforms. In this paper, to overcome this issue, we propose a…

Transformers achieve state-of-the-art results across many tasks, but their uniform application of quadratic self-attention to every token at every layer makes them computationally expensive. We introduce DTRNet (Dynamic Token Routing…

Self-similarity refers to the image prior widely used in image restoration algorithms that small but similar patterns tend to occur at different locations and scales. However, recent advanced deep convolutional neural network based methods…