242 citations · 481 across the 13 of their papers we have counts for
13 papers
NavAgent: Multi-scale Urban Street View Fusion For UAV Embodied Vision-and-Language Navigation
Youzhi Liu, Fanglong Yao, Yuanchang Yue +3
Vision-and-Language Navigation (VLN), as a widely discussed research direction in embodied intelligence, aims to enable embodied agents to navigate in complicated visual environmen…
COT: A Generative Approach for Hate Speech Counter-Narratives via Contrastive Optimal Transport
Linhao Zhang, Li Jin, Guangluan Xu +2
Counter-narratives, which are direct responses consisting of non-aggressive fact-based arguments, have emerged as a highly effective approach to combat the proliferation of hate sp…
TOT: Topology-Aware Optimal Transport For Multimodal Hate Detection
Linhao Zhang, Li Jin, Xian Sun +6
Multimodal hate detection, which aims to identify harmful content online such as memes, is crucial for building a wholesome internet environment. Previous work has made enlightenin…
HYPER^2: Hyperbolic Poincare Embedding for Hyper-Relational Link Prediction
Shiyao Yan, Zequn Zhang, Xian Sun +3
Link Prediction, addressing the issue of completing KGs with missing facts, has been broadly studied. However, less light is shed on the ubiquitous hyper-relational KGs. Most exist…
High Quality Remote Sensing Image Super-Resolution Using Deep Memory Connected Network
Wenjia Xu, Guangluan Xu, Yang Wang +3
Single image super-resolution is an effective way to enhance the spatial resolution of remote sensing image, which is crucial for many applications such as target detection and ima…
Where is the Model Looking At?--Concentrate and Explain the Network Attention
Wenjia Xu, Jiuniu Wang, Yang Wang +3
Image classification models have achieved satisfactory performance on many datasets, sometimes even better than human. However, The model attention is unclear since the lack of int…
SRQA: Synthetic Reader for Factoid Question Answering
Jiuniu Wang, Wenjia Xu, Xingyu Fu +5
The question answering system can answer questions from various fields and forms with deep neural networks, but it still lacks effective ways when facing multiple evidences. We int…
ASTRAL: Adversarial Trained LSTM-CNN for Named Entity Recognition
Jiuniu Wang, Wenjia Xu, Xingyu Fu +2
Named Entity Recognition (NER) is a challenging task that extracts named entities from unstructured text data, including news, articles, social comments, etc. The NER system has be…
Deep Discriminative Representation Learning with Attention Map for Scene Classification
Jun Li, Daoyu Lin, Yang Wang +2
Learning powerful discriminative features for remote sensing image scene classification is a challenging computer vision problem. In the past, most classification approaches were b…
A Remote Sensing Image Dataset for Cloud Removal
Daoyu Lin, Guangluan Xu, Xiaoke Wang +3
Cloud-based overlays are often present in optical remote sensing images, thus limiting the application of acquired data. Removing clouds is an indispensable pre-processing step in…
Wider Channel Attention Network for Remote Sensing Image Super-resolution
Jun Gu, Guangluan Xu, Yue Zhang +3
Recently, deep convolutional neural networks (CNNs) have obtained promising results in image processing tasks including super-resolution (SR). However, most CNN-based SR methods tr…
A3Net: Adversarial-and-Attention Network for Machine Reading Comprehension
Jiuniu Wang, Xingyu Fu, Guangluan Xu +4
In this paper, we introduce Adversarial-and-attention Network (A3Net) for Machine Reading Comprehension. This model extends existing approaches from two perspectives. First, advers…
MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification
Daoyu Lin, Kun Fu, Yang Wang +2
With the development of deep learning, supervised learning has frequently been adopted to classify remotely sensed images using convolutional networks (CNNs). However, due to the l…