相关论文: X3D: Expanding Architectures for Efficient Video R…

In computer vision, an entity such as an image or video is often represented as a set of instance vectors, which can be SIFT, motion, or deep learning feature vectors extracted from different parts of that entity. Thus, it is essential to…

This paper introduces a fast and efficient segmentation technique for 2D images and 3D point clouds of building facades. Facades of buildings are highly structured and consequently most methods that have been proposed for this problem aim…

Understanding and reconstructing the complex geometry and motion of dynamic scenes from video remains a formidable challenge in computer vision. This paper introduces D4RT, a simple yet powerful feedforward model designed to efficiently…

Generative models for 2D images has recently seen tremendous progress in quality, resolution and speed as a result of the efficiency of 2D convolutional architectures. However it is difficult to extend this progress into the 3D domain since…

Recent advances in sparse voxel representations have significantly improved the quality of 3D content generation, enabling high-resolution modeling with fine-grained geometry. However, existing frameworks suffer from severe computational…

Convolutional neural networks (CNNs) have been extensively applied for image recognition problems giving state-of-the-art results on recognition, detection, segmentation and retrieval. In this work we propose and evaluate several deep…

Recent progress in deep learning-based models has improved photo-realistic (or perceptual) single-image super-resolution significantly. However, despite their powerful performance, many methods are difficult to apply to real-world…

Typical video classification methods often divide a video into short clips, do inference on each clip independently, then aggregate the clip-level predictions to generate the video-level results. However, processing visually similar clips…

Human activity recognition is one of the important research topics in computer vision and video understanding. It is often assumed that high quality video sequences are available for recognition. However, relaxing such a requirement and…

Accurate and computationally efficient 3D medical image segmentation remains a critical challenge in clinical workflows. Transformer-based architectures often demonstrate superior global contextual modeling but at the expense of excessive…

In videos, the human's actions are of three-dimensional (3D) signals. These videos investigate the spatiotemporal knowledge of human behavior. The promising ability is investigated using 3D convolution neural networks (CNNs). The 3D CNNs…

Current state-of-the-art models for video action recognition are mostly based on expensive 3D ConvNets. This results in a need for large GPU clusters to train and evaluate such architectures. To address this problem, we present a…

Extending state-of-the-art object detectors from image to video is challenging. The accuracy of detection suffers from degenerated object appearances in videos, e.g., motion blur, video defocus, rare poses, etc. Existing work attempts to…

In recent years, deep learning methods have been successfully applied to single-image super-resolution tasks. Despite their great performances, deep learning methods cannot be easily applied to real-world applications due to the requirement…

3D convolution is powerful for video classification but often computationally expensive, recent studies mainly focus on decomposing it on spatial-temporal and/or channel dimensions. Unfortunately, most approaches fail to achieve a…

Surface topography refers to the geometric micro-structure of a surface and defines its tactile characteristics (typically in the sub-millimeter range). High-resolution 3D scanning techniques developed recently enable the 3D reconstruction…

In recent years, 3D convolutional neural networks have become the dominant approach for volumetric medical image segmentation. However, compared to their 2D counterparts, 3D networks introduce substantially more training parameters and…

We introduce a lightweight and accurate architecture for resource-efficient visual correspondence. Our method, dubbed XFeat (Accelerated Features), revisits fundamental design choices in convolutional neural networks for detecting,…

Aggregating multi-level feature representation plays a critical role in achieving robust volumetric medical image segmentation, which is important for the auxiliary diagnosis and treatment. Unlike the recent neural architecture search (NAS)…

Deep neural networks have achieved remarkable success for video-based action recognition. However, most of existing approaches cannot be deployed in practice due to the high computational cost. To address this challenge, we propose a new…