Related papers: Weaving Multi-scale Context for Single Shot Detect…

Recently, scene text detection has been a challenging task. Texts with arbitrary shape or large aspect ratio are usually hard to detect. Previous segmentation-based methods can describe curve text more accurately but suffer from over…

In this paper, we propose an effective method for fast and accurate scene parsing called Bidirectional Alignment Network (BiAlignNet). Previously, one representative work BiSeNet~\cite{bisenet} uses two different paths (Context Path and…

The multitude of data generated by sensors available on users' mobile devices, combined with advances in machine learning techniques, support context-aware services in recognizing the current situation of a user (i.e., physical context) and…

3D object recognition has attracted wide research attention in the field of multimedia and computer vision. With the recent proliferation of deep learning, various deep models with different representations have achieved the…

Salient object detection plays an important role in many downstream tasks. However, complex real-world scenes with varying scales and numbers of salient objects still pose a challenge. In this paper, we directly address the problem of…

In this paper, we present an efficient pedestrian detection system, designed by fusion of multiple deep neural network (DNN) systems. Pedestrian candidates are first generated by a single shot convolutional multi-box detector at different…

Successful visual recognition networks benefit from aggregating information spanning from a wide range of scales. Previous research has investigated information fusion of connected layers or multiple branches in a block, seeking to…

Deep region-based object detector consists of a region proposal step and a deep object recognition step. In this paper, we make significant improvements on both of the two steps. For region proposal we propose a novel lightweight cascade…

Modern deep learning architectures produce highly accurate results on many challenging semantic segmentation datasets. State-of-the-art methods are, however, not directly transferable to real-time applications or embedded devices, since…

Salient object detection (SOD) in remote sensing images faces significant challenges due to large variations in object sizes, the computational cost of self-attention mechanisms, and the limitations of CNN-based extractors in capturing…

Visual intelligence at the edge is becoming a growing necessity for low latency applications and situations where real-time decision is vital. Object detection, the first step in visual data analytics, has enjoyed significant improvements…

Existing salient object detection methods often adopt deeper and wider networks for better performance, resulting in heavy computational burden and slow inference speed. This inspires us to rethink saliency detection to achieve a favorable…

Salient object detection models often demand a considerable amount of computation cost to make precise prediction for each pixel, making them hardly applicable on low-power devices. In this paper, we aim to relieve the contradiction between…

Convolutional Neural Networks (CNNs) were recently shown to provide state-of-the-art results for object category viewpoint estimation. However different ways of formulating this problem have been proposed and the competing approaches have…

Conventional deep learning based methods for object detection require a large amount of bounding box annotations for training, which is expensive to obtain such high quality annotated data. Few-shot object detection, which learns to adapt…

Context is essential for semantic segmentation. Due to the diverse shapes of objects and their complex layout in various scene images, the spatial scales and shapes of contexts for different objects have very large variation. It is thus…

Keypoint detection and description is fundamental yet important in many vision applications. Most existing methods use detect-then-describe or detect-and-describe strategy to learn local features without considering their context…

Small object detection presents a significant challenge in computer vision and object detection. The performance of small object detectors is often compromised by a lack of pixels and less significant features. This issue stems from…

State-of-the-art models for semantic segmentation are based on adaptations of convolutional networks that had originally been designed for image classification. However, dense prediction and image classification are structurally different.…

Matching-based methods, especially those based on space-time memory, are significantly ahead of other solutions in semi-supervised video object segmentation (VOS). However, continuously growing and redundant template features lead to an…