Related papers: SAFE: Scale Aware Feature Encoder for Scene Text R…
This paper proposes a novel attention model for semantic segmentation, which aggregates multi-scale and context features to refine prediction. Specifically, the skeleton convolutional neural network framework takes in multiple different…
Convolutional neural networks (CNN) have enabled significant improvements in pedestrian detection owing to the strong representation ability of the CNN features. Recently, aggregating features from multiple layers of a CNN has been…
In this paper, we propose an effective scene text recognition method using sparse coding based features, called Histograms of Sparse Codes (HSC) features. For character detection, we use the HSC features instead of using the Histograms of…
Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To take a step in this direction, we recently proposed a problem-agnostic speech encoder (PASE), that…
Building robust recognizers for Arabic has always been challenging. We demonstrate the effectiveness of an end-to-end trainable CNN-RNN hybrid architecture in recognizing Arabic text in videos and natural scenes. We outperform previous…
Currently, most top-performing text detection networks tend to employ fixed-size anchor boxes to guide the search for text instances. They usually rely on a large amount of anchors with different scales to discover texts in scene images,…
Scene graph generation (SGG) has gained tremendous progress in recent years. However, its underlying long-tailed distribution of predicate classes is a challenging problem. For extremely unbalanced predicate distributions, existing…
Despite the growing success of Convolution neural networks (CNN) in the recent past in the task of scene segmentation, the standard models lack some of the important features that might result in sub-optimal segmentation outputs. The widely…
Recently, scene text detection has become an active research topic in computer vision and document analysis, because of its great importance and significant challenge. However, vast majority of the existing methods detect text within local…
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…
Convolutional neural networks typically encode an input image into a series of intermediate features with decreasing resolutions. While this structure is suited to classification tasks, it does not perform well for tasks requiring…
Most Graph Neural Networks (GNNs) operate at the first-order scale, even though multi-scale representations are known to be crucial in domains such as image classification. In this work, we investigate whether GNNs can similarly benefit…
In the last decade, the blossom of deep learning has witnessed the rapid development of scene text recognition. However, the recognition of low-resolution scene text images remains a challenge. Even though some super-resolution methods have…
Scene text recognition has recently been widely treated as a sequence-to-sequence prediction problem, where traditional fully-connected-LSTM (FC-LSTM) has played a critical role. Due to the limitation of FC-LSTM, existing methods have to…
In this paper, we share our experience in designing a convolutional network-based face detector that could handle faces of an extremely wide range of scales. We show that faces with different scales can be modeled through a specialized set…
Encoder-decoder models have become an effective approach for sequence learning tasks like machine translation, image captioning and speech recognition, but have yet to show competitive results for handwritten text recognition. To this end,…
Recently, a variety of vision transformers have been developed as their capability of modeling long-range dependency. In current transformer-based backbones for medical image segmentation, convolutional layers were replaced with pure…
Sparse autoencoders (SAEs) enable interpretability research by decomposing entangled model activations into monosemantic features. However, under what circumstances SAEs derive most fine-grained latent features for safety, a low-frequency…
Semantic segmentation has recently achieved notable advances by exploiting "class-level" contextual information during learning. However, these approaches simply concatenate class-level information to pixel features to boost the pixel…
Finding semantic correspondences is a challenging problem. With the breakthrough of CNNs stronger features are available for tasks like classification but not specifically for the requirements of semantic matching. In the following we…