Incomplete phase encoding with few phases is an effective under-sampling manner of fast Magnetic Resonance (MR) scan. The key is how to choose important slice-specific phases. Reinforcement Learning (RL) is powerful for sequential decision-making ...

Many feature extraction components have been proposed for image deraining tasks, aiming to improve feature learning. However, few models have addressed the integration of multi-scale features from derain images. The fusion of multiple features at ...

• Introduce detail scaling module to extract generalized features from rainfall image.
• Improved Transform block was introduced to enhance the model’s generalized ability.
• Scale-mixing strategy is proposed for capturing more multi-...

Learning-based correspondence matching methods have become the mainstream techniques in many computer vision and robotics applications due to their robustness to large illumination and viewpoint changes. However, it is difficult for conventional ...

The efficiency of deep neural networks is increasing, and so is the amount of annotated data required for training them. We propose a solution improving the learning process of a classification network with less labeled data. Our approach is to ...

• We propose a solution to learn a classification network with less labeled data.
• The principle is to provide the classifier a binary mask as a simple shape prior.
• We resort to a Siamese architecture and feed it with images and shape ...

Data augmentation is a crucial and challenging task for improving defect detection with limited data. Many generative models have been proposed and shown promising performance on this task. However, existing models are unable to capture the fine ...

Knowledge distillation (KD) is a method that transfers information from a larger network (teacher) to a smaller network (student) to obtain stronger performance without extra computational load. It has made great success in image classification, ...

Autonomous driving requires information such as the velocity of other vehicles to prevent potential hazards. This work proposes a real-time deep learning-based framework to estimate vehicle speeds from image captures through an onboard camera. ...

• Use object detection and linear regression to estimate moving vehicle speeds.
• Comparison of the methodology with LIDAR-based speed estimation techniques.
• Evaluation of the methodology on the Prevention dataset.

Deep learning techniques have led to remarkable breakthroughs in the field of object detection and have spawned a lot of scene-understanding tasks in recent years. Scene graph has been the focus of research because of its powerful semantic ...

Display Omitted

• A comprehensive review of 138 papers on scene graph generation is presented.
• We analyze 2D scene graph generation, focusing on feature representation.
• A review of typical datasets for 2D, spatio-temporal and 3D scene graph ...

Recent deep learning models have exhibited impressive performance in the area of 3D skull landmark detection, but most of them aimed to detect a fixed number of landmarks. This paper focuses on automatically detecting an arbitrary number of ...

Camouflaged object detection (COD) aims to search and identify disguised objects that are hidden in their surrounding environment, thereby deceiving the human visual system. As an interesting and challenging task, COD has received increasing ...

Vehicle re-identification (re-ID) has received increasing attention due to its tremendous potential in practical intelligent transportation scenarios. The main difficulties of vehicle re-ID are generally induced by insufficient annotations, ...

In this work, we present a new semi-supervised learning framework to cope with satellite image time series (SITS) classification in a data paucity scenario, considering extreme low levels of supervision. The proposed methodology, referred as S 3 ...

Recurrent neural networks (RNNs) are a popular family of models widely used when facing sequential data such as videos. However, RNNs make assumptions about state transitions that could be damageable. This paper presents two theoretical ...

• Sign language tokenization is a challenging task involving complex transitions.
• The limitations of RNNs highlighted in theory can be observed in practice.
• Extensions have a positive impact, but there is still room for improvement.

Tremendous progress has been made in facial Micro-Expression (ME) spotting and recognition; however, most works have focused on either spotting or recognition tasks on the 2D videos. Until recently, the estimation of the 3D motion field (a.k.a ...

• First study to spot and recognize micro-expressions on the multi-modal dataset.
• A scene flow attention-based end-to-end multi-stream multi-task network is proposed.
• Scene flow is extracted to estimate the 3D motion using color and ...

Vertebral fractures are a common problem and the most prevalent of thoracolumbar compression and burst fractures. However, vertebral fractures are difficult to diagnose: an experienced orthopedist or radiologist is required to detect and ...

• Proposed AI model for vertebral fracture detection using YOLOv4 and ResUNet.
• Achieved high precision (99%, 74%, 94%) in identifying healthy, compression, and burst fractures.
• First literature mention of detecting compression and ...

With the enhancement of people’s security awareness, transmitting secret information securely has gradually become a demand for the public. Steganography is a technology of representing secret information within another carrier, aiming at ...

Quantization methods for convolutional neural network models can be broadly categorized into post-training quantization (PTQ) and quantization aware training (QAT). While PTQ offers the advantage of requiring only a small portion of the data for ...

• Attention Round quantization function expands the quantization optimization space.
• Mixed precision allocation method improves mixed precision quantization efficiency.
• Enriched lightweight CNNs contribute to applications in resource-...

Bio-inspired neuromorphic cameras asynchronously record pixel brightness changes and generate sparse event streams. They can capture dynamic scenes with little motion blur and more details in extreme illumination conditions. Due to the ...

• Asynchronous event streams of neuromorphic cameras shape synchronous graph representations.
• Graph Transformer effectively learns informative features from event-based graphs.
• Temporal-wise connectivity and learning suffer less from ...

Vision Transformer (ViT) has demonstrated promising performance in computer vision tasks, comparable to state-of-the-art neural networks. Yet, this new type of deep neural network architecture is vulnerable to adversarial attacks limiting its ...

When recovering the sharp image from a blurry observation, moving objects, e.g., people and vehicles, usually attract more perceptual attention. However, existing motion deblurring methods primarily focus on removing the global camera motion blur,...