Related papers: An Adaptive Threshold for the Canny Edge Detection…
Modern one-stage video instance segmentation networks suffer from two limitations. First, convolutional features are neither aligned with anchor boxes nor with ground-truth bounding boxes, reducing the mask sensitivity to spatial location.…
In recent years, advances in Artificial Intelligence have significantly impacted computer science, particularly in the field of computer vision, enabling solutions to complex problems such as video frame prediction. Video frame prediction…
This paper investigates the principles of embedding learning to tackle the challenging semi-supervised video object segmentation. Different from previous practices that only explore the embedding learning using pixels from foreground object…
Existing tracking algorithms typically rely on low-frame-rate RGB cameras coupled with computationally intensive deep neural network architectures to achieve effective tracking. However, such frame-based methods inherently face challenges…
Detecting and extracting textual information from natural scene images needs Scene Text Detection (STD) algorithms. Fully Convolutional Neural Networks (FCNs) are usually utilized as the backbone model to extract features in these instance…
Remote sensor image object detection is an important technology for Earth observation, and is used in various tasks such as forest fire monitoring and ocean monitoring. Image object detection technology, despite the significant…
Challenges in remote sensing object detection(RSOD), such as high interclass similarity, imbalanced foreground-background distribution, and the small size of objects in remote sensing images, significantly hinder detection accuracy.…
We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…
It is well known that attention mechanisms can effectively improve the performance of many CNNs including object detectors. Instead of refining feature maps prevalently, we reduce the prohibitive computational complexity by a novel attempt…
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…
Unsupervised learning poses one of the most difficult challenges in computer vision today. The task has an immense practical value with many applications in artificial intelligence and emerging technologies, as large quantities of unlabeled…
Many real-world ubiquitous applications, such as parking recommendations and air pollution monitoring, benefit significantly from accurate long-term spatio-temporal forecasting (LSTF). LSTF makes use of long-term dependency between spatial…
Traffic object detection under variable illumination is challenging due to the information loss caused by the limited dynamic range of conventional frame-based cameras. To address this issue, we introduce bio-inspired event cameras and…
The detection of abnormal behaviours in crowded scenes has to deal with many challenges. This paper presents an efficient method for detection and localization of anomalies in videos. Using fully convolutional neural networks (FCNs) and…
Natural scene text detection is a significant challenge in computer vision, with tremendous potential applications in multilingual, diverse, and complex text scenarios. We propose a multilingual text detection model to address the issues of…
Few-shot object detection (FSOD) aims to detect objects with limited samples for novel classes, while relying on abundant data for base classes. Existing FSOD approaches, predominantly built on the Faster R-CNN detector, entangle objectness…
Automatic Modulation Recognition (AMR) is an essential part of Intelligent Transportation System (ITS) dynamic spectrum allocation. However, current deep learning-based AMR (DL-AMR) methods are challenged to extract discriminative and…
This paper investigates the principles of embedding learning to tackle the challenging semi-supervised video object segmentation. Unlike previous practices that focus on exploring the embedding learning of foreground object (s), we consider…
Real-time semantic segmentation plays a significant role in industry applications, such as autonomous driving, robotics and so on. It is a challenging task as both efficiency and performance need to be considered simultaneously. To address…
In the realm of multi-object tracking, the challenge of accurately capturing the spatial and temporal relationships between objects in video sequences remains a significant hurdle. This is further complicated by frequent occurrences of…