Related papers: Translate-to-Recognize Networks for RGB-D Scene Re…

A powerful way to adapt a visual recognition model to a new domain is through image translation. However, common image translation approaches only focus on generating data from the same distribution as the target domain. Given a cross-modal…

Transfer learning is widely used in computer vision (CV), natural language processing (NLP) and achieves great success. Most transfer learning systems are based on the same modality (e.g. RGB image in CV and text in NLP). However, the…

We propose a novel deep convolutional neural network (CNN) based multi-task learning approach for open-set visual recognition. We combine a classifier network and a decoder network with a shared feature extractor network within a multi-task…

Scene text image super-resolution has significantly improved the accuracy of scene text recognition. However, many existing methods emphasize performance over efficiency and ignore the practical need for lightweight solutions in deployment…

This paper presents a novel training method for end-to-end scene text recognition. End-to-end scene text recognition offers high recognition accuracy, especially when using the encoder-decoder model based on Transformer. To train a highly…

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…

Encoder-decoder models have been widely used in RGBD semantic segmentation, and most of them are designed via a two-stream network. In general, jointly reasoning the color and geometric information from RGBD is beneficial for semantic…

While deep learning, particularly convolutional neural networks (CNNs), has revolutionized remote sensing (RS) change detection (CD), existing approaches often miss crucial features due to neglecting global context and incomplete change…

In this paper, we propose a Generative Translation Classification Network (GTCN) for improving visual classification accuracy in settings where classes are visually similar and data is scarce. For this purpose, we propose joint learning…

Recently, deep convolution neural networks (CNNs) steered face super-resolution methods have achieved great progress in restoring degraded facial details by jointly training with facial priors. However, these methods have some obvious…

Image fusion is a technique to integrate information from multiple source images with complementary information to improve the richness of a single image. Due to insufficient task-specific training data and corresponding ground truth, most…

The field of image classification has shown an outstanding success thanks to the development of deep learning techniques. Despite the great performance obtained, most of the work has focused on natural images ignoring other domains like…

Captioning images is a challenging scene-understanding task that connects computer vision and natural language processing. While image captioning models have been successful in producing excellent descriptions, the field has primarily…

Scene analysis is essential for enabling autonomous systems, such as mobile robots, to operate in real-world environments. However, obtaining a comprehensive understanding of the scene requires solving multiple tasks, such as panoptic…

Many RGB-T trackers attempt to attain robust feature representation by utilizing an adaptive weighting scheme (or attention mechanism). Different from these works, we propose a new dynamic modality-aware filter generation module (named…

In this work, we propose BertGCN, a model that combines large scale pretraining and transductive learning for text classification. BertGCN constructs a heterogeneous graph over the dataset and represents documents as nodes using BERT…

We propose a real-time general purpose semantic segmentation architecture, RGPNet, which achieves significant performance gain in complex environments. RGPNet consists of a light-weight asymmetric encoder-decoder and an adaptor. The adaptor…

Reading comprehension is a challenging task in natural language processing and requires a set of skills to be solved. While current approaches focus on solving the task as a whole, in this paper, we propose to use a neural network `skill'…

Traditional systems typically require different models for processing different modalities, such as one model for RGB images and another for depth images. Recent research has demonstrated that a single model for one modality can be adapted…

The hybrid architecture of convolution neural networks (CNN) and Transformer has been the most popular method for medical image segmentation. However, the existing networks based on the hybrid architecture suffer from two problems. First,…