Related papers: BoundaryNet: An Attentive Deep Network with Fast M…

Efficiently computing attention maps for videos is challenging due to the motion of objects between frames. While a standard non-local search is high-quality for a window surrounding each query point, the window's small size cannot…

Semantic segmentation is pixel-wise classification which retains critical spatial information. The "feature map reuse" has been commonly adopted in CNN based approaches to take advantage of feature maps in the early layers for the later…

In recent years, deep learning (DL) approaches have demonstrated promising results in decoding hemodynamic responses captured by functional near-infrared spectroscopy (fNIRS), particularly in the context of brain-computer interface (BCI)…

Medical image segmentation has made significant progress in recent years. Deep learning-based methods are recognized as data-hungry techniques, requiring large amounts of data with manual annotations. However, manual annotation is expensive…

Unconstrained handwritten text recognition is a challenging computer vision task. It is traditionally handled by a two-step approach, combining line segmentation followed by text line recognition. For the first time, we propose an…

The knowledge about the placement and appearance of lane markings is a prerequisite for the creation of maps with high precision, necessary for autonomous driving, infrastructure monitoring, lane-wise traffic management, and urban planning.…

Linguistic knowledge is of great benefit to scene text recognition. However, how to effectively model linguistic rules in end-to-end deep networks remains a research challenge. In this paper, we argue that the limited capacity of language…

Contextual information is vital in visual understanding problems, such as semantic segmentation and object detection. We propose a Criss-Cross Network (CCNet) for obtaining full-image contextual information in a very effective and efficient…

End-to-end text spotting aims to jointly optimize text detection and recognition within a unified framework. Despite significant progress, designing an accurate and efficient end-to-end text spotter for arbitrary-shaped text remains…

Dense prediction models are widely used for image segmentation. One important challenge is to sufficiently train these models to yield good generalizations for hard-to-learn pixels. A typical group of such hard-to-learn pixels are…

Scene text detection has witnessed rapid development in recent years. However, there still exists two main challenges: 1) many methods suffer from false positives in their text representations; 2) the large scale variance of scene texts…

Can we leverage high-resolution information without the unsustainable quadratic complexity to input scale? We propose Traversal Network (TNet), a novel multi-scale hard-attention architecture, which traverses image scale-space in a top-down…

We propose a method for high-performance semantic image segmentation (or semantic pixel labelling) based on very deep residual networks, which achieves the state-of-the-art performance. A few design factors are carefully considered to this…

The success of state-of-the-art deep neural networks heavily relies on the presence of large-scale labelled datasets, which are extremely expensive and time-consuming to annotate. This paper focuses on tackling semi-supervised part…

Learning to capture dependencies between spatial positions is essential to many visual tasks, especially the dense labeling problems like scene parsing. Existing methods can effectively capture long-range dependencies with self-attention…

This paper introduces a novel approach that combines unsupervised active contour models with deep learning for robust and adaptive image segmentation. Indeed, traditional active contours, provide a flexible framework for contour evolution…

One popular approach to interactively segment the foreground object of interest from an image is to annotate a bounding box that covers the foreground object. Then, a binary labeling is performed to achieve a refined segmentation. One major…

This paper presents a unified framework for codifying and automating optimization strategies to efficiently deploy deep neural networks (DNNs) on resource-constrained hardware, such as FPGAs, while maintaining high performance, accuracy,…

Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial…

In this work we introduce a new Bounding-Box Free Network (BBFNet) for panoptic segmentation. Panoptic segmentation is an ideal problem for proposal-free methods as it already requires per-pixel semantic class labels. We use this…