72 citations · 327 across the 20 of their papers we have counts for
20 papers
Sentiment-enhanced Graph-based Sarcasm Explanation in Dialogue
Kun Ouyang, Liqiang Jing, Xuemeng Song +3
Sarcasm Explanation in Dialogue (SED) is a new yet challenging task, which aims to generate a natural language explanation for the given sarcastic dialogue that involves multiple m…
VK-G2T: Vision and Context Knowledge enhanced Gloss2Text
Liqiang Jing, Xuemeng Song, Xinxing Zu +3
Existing sign language translation methods follow a two-stage pipeline: first converting the sign language video to a gloss sequence (i.e. Sign2Gloss) and then translating the gene…
Target-Guided Composed Image Retrieval
Haokun Wen, Xian Zhang, Xuemeng Song +2
Composed image retrieval (CIR) is a new and flexible image retrieval paradigm, which can retrieve the target image for a multimodal query, including a reference image and its corre…
Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation
Liqiang Jing, Xuemeng Song, Kun Ouyang +2
Multimodal Sarcasm Explanation (MuSE) is a new yet challenging task, which aims to generate a natural language sentence for a multimodal social post (an image as well as its captio…
Dual Semantic Knowledge Composed Multimodal Dialog Systems
Xiaolin Chen, Xuemeng Song, Yinwei Wei +2
Textual response generation is an essential task for multimodal task-oriented dialog systems.Although existing studies have achieved fruitful progress, they still suffer from two c…
Stylized Data-to-Text Generation: A Case Study in the E-Commerce Domain
Liqiang Jing, Xuemeng Song, Xuming Lin +3
Existing data-to-text generation efforts mainly focus on generating a coherent text from non-linguistic input data, such as tables and attribute-value pairs, but overlook that diff…
Self-Training Boosted Multi-Factor Matching Network for Composed Image Retrieval
Haokun Wen, Xuemeng Song, Jianhua Yin +3
The composed image retrieval (CIR) task aims to retrieve the desired target image for a given multimodal query, i.e., a reference image with its corresponding modification text. Th…
OFAR: A Multimodal Evidence Retrieval Framework for Illegal Live-streaming Identification
Lin Dengtian, Ma Yang, Li Yuhong +3
Illegal live-streaming identification, which aims to help live-streaming platforms immediately recognize the illegal behaviors in the live-streaming, such as selling precious and e…
Multimodal Matching-aware Co-attention Networks with Mutual Knowledge Distillation for Fake News Detection
Linmei Hu, Ziwang Zhao, Weijian Qi +2
Fake news often involves multimedia information such as text and image to mislead readers, proliferating and expanding its influence. Most existing fake news detection methods appl…
Counterfactual Reasoning for Out-of-distribution Multimodal Sentiment Analysis
Teng Sun, Wenjie Wang, Liqiang Jing +3
Existing studies on multimodal sentiment analysis heavily rely on textual modality and unavoidably induce the spurious correlations between textual words and sentiment labels. This…
Multimodal Dialog Systems with Dual Knowledge-enhanced Generative Pretrained Language Model
Xiaolin Chen, Xuemeng Song, Liqiang Jing +3
Text response generation for multimodal task-oriented dialog systems, which aims to generate the proper text response given the multimodal context, is an essential yet challenging…
Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation
Xingning Dong, Tian Gan, Xuemeng Song +3
Scene Graph Generation, which generally follows a regular encoder-decoder pipeline, aims to first encode the visual contents within the given image and then parse them into a compa…
MERIt: Meta-Path Guided Contrastive Learning for Logical Reasoning
Fangkai Jiao, Yangyang Guo, Xuemeng Song +1
Logical reasoning is of vital importance to natural language understanding. Previous studies either employ graph-based models to incorporate prior knowledge about logical relations…
Dual Preference Distribution Learning for Item Recommendation
Xue Dong, Xuemeng Song, Na Zheng +2
Recommender systems can automatically recommend users with items that they probably like. The goal of them is to model the user-item interaction by effectively representing the use…
Hierarchical Deep Residual Reasoning for Temporal Moment Localization
Ziyang Ma, Xianjing Han, Xuemeng Song +2
Temporal Moment Localization (TML) in untrimmed videos is a challenging task in the field of multimedia, which aims at localizing the start and end points of the activity in the vi…
Multi-Modal Interaction Graph Convolutional Network for Temporal Language Localization in Videos
Zongmeng Zhang, Xianjing Han, Xuemeng Song +2
This paper focuses on tackling the problem of temporal language localization in videos, which aims to identify the start and end points of a moment described by a natural language…
Answer Questions with Right Image Regions: A Visual Attention Regularization Approach
Yibing Liu, Yangyang Guo, Jianhua Yin +3
Visual attention in Visual Question Answering (VQA) targets at locating the right image regions regarding the answer prediction, offering a powerful technique to promote multi-moda…
Market2Dish: Health-aware Food Recommendation
Wenjie Wang, Ling-yu Duan, Hao Jiang +3
With the rising incidence of some diseases, such as obesity and diabetes, a healthy diet is arousing increasing attention. However, most existing food-related research efforts focu…
Adaptive Collaborative Similarity Learning for Unsupervised Multi-view Feature Selection
Xiao Dong, Lei Zhu, Xuemeng Song +2
In this paper, we investigate the research problem of unsupervised multi-view feature selection. Conventional solutions first simply combine multiple pre-constructed view-specific…
Neural Compatibility Modeling with Attentive Knowledge Distillation
Xuemeng Song, Fuli Feng, Xianjing Han +3
Recently, the booming fashion sector and its huge potential benefits have attracted tremendous attention from many research communities. In particular, increasing research efforts…