Related papers: Dynamic Mobile-Former: Strengthening Dynamic Convo…

Video diffusion models have achieved impressive realism and controllability but are limited by high computational demands, restricting their use on mobile devices. This paper introduces the first mobile-optimized video diffusion model.…

The research on recognizing the most discriminative regions provides referential information for weakly supervised object localization with only image-level annotations. However, the most discriminative regions usually conceal the other…

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…

This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features. By comparing the design principles of the recent…

Existing stereo matching networks typically rely on either cost-volume construction based on 3D convolutions or deformation methods based on iterative optimization. The former incurs significant computational overhead during cost…

To accommodate the explosive wireless traffics, massive multiple-input multiple-output (MIMO) is regarded as one of the key enabling technologies for next-generation communication systems. In massive MIMO cellular networks, coordinated…

Transfer learning paradigm has driven substantial advancements in various vision tasks. However, as state-of-the-art models continue to grow, classical full fine-tuning often becomes computationally impractical, particularly in multi-task…

Driver drowsiness increases crash risk, leading to substantial road trauma each year. Drowsiness detection methods have received considerable attention, but few studies have investigated the implementation of a detection approach on a…

Light-weight convolutional neural networks (CNNs) are specially designed for applications on mobile devices with faster inference speed. The convolutional operation can only capture local information in a window region, which prevents…

This study proposes a lightweight method for building image super-resolution using a Dilated Contextual Feature Modulation Network (DCFMN). The process includes obtaining high-resolution images, down-sampling them to low-resolution,…

This paper presents DFR (Decompose, Fuse and Reconstruct), a novel framework that addresses the fundamental challenge of effectively utilizing multi-modal guidance in few-shot segmentation (FSS). While existing approaches primarily rely on…

Transformer has shown great successes in natural language processing, computer vision, and audio processing. As one of its core components, the softmax attention helps to capture long-range dependencies yet prohibits its scale-up due to the…

Deep neural networks face several challenges in hyperspectral image classification, including insufficient utilization of joint spatial-spectral information, gradient vanishing with increasing depth, and overfitting. To enhance feature…

Multi-head-self-attention (MHSA)-equipped models have achieved notable performance in computer vision. Their computational complexity is proportional to quadratic numbers of pixels in input feature maps, resulting in slow processing,…

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…

Diffusion Transformers (DiTs) have emerged as a leading architecture for text-to-image synthesis, producing high-quality and photorealistic images. However, the quadratic scaling properties of the attention in DiTs hinder image generation…

Convolution is one of the basic building blocks of CNN architectures. Despite its common use, standard convolution has two main shortcomings: Content-agnostic and Computation-heavy. Dynamic filters are content-adaptive, while further…

Recent advancements in neural network-based optical flow estimation often come with prohibitively high computational and memory requirements, presenting challenges in their model adaptation for mobile and low-power use cases. In this paper,…

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…

Neural networks for visual content understanding have recently evolved from convolutional ones (CNNs) to transformers. The prior (CNN) relies on small-windowed kernels to capture the regional clues, demonstrating solid local expressiveness.…