1 code implementation • ACL 2022 • Yongqi Li, Wenjie Li, Liqiang Nie
In this paper, we hence define a novel research task, i. e., multimodal conversational question answering (MMCoQA), aiming to answer users’ questions with multimodal knowledge sources via multi-turn conversations.
1 code implementation • 15 Mar 2023 • Xiao Wang, Tian Gan, Yinwei Wei, Jianlong Wu, Dai Meng, Liqiang Nie
Existing methods mostly focus on analyzing video content, neglecting users' social influence and tag relation.
no code implementations • 14 Mar 2023 • Min Cao, Yang Bai, Jingyao Wang, Ziqiang Cao, Liqiang Nie, Min Zhang
The proposed framework equipped with only two embedding layers achieves $O(1)$ querying time complexity, while improving the retrieval efficiency and keeping its performance, when applied prior to the common image-text retrieval methods.
no code implementations • 13 Feb 2023 • Song Wu, Yazhou Ren, Aodi Yang, Xinyue Chen, Xiaorong Pu, Jing He, Liqiang Nie, Philip S. Yu
In this survey, we investigate the main contributions of deep learning applications using medical images in fighting against COVID-19 from the aspects of image classification, lesion localization, and severity quantification, and review different deep learning architectures and some image preprocessing techniques for achieving a preciser diagnosis.
no code implementations • 4 Feb 2023 • Zhenyang Li, Yangyang Guo, Kejie Wang, Fan Liu, Liqiang Nie, Mohan Kankanhalli
Visual Commonsense Reasoning (VCR) remains a significant yet challenging research problem in the realm of visual reasoning.
1 code implementation • 13 Jan 2023 • Han Liu, Yinwei Wei, Jianhua Yin, Liqiang Nie
Towards this end, existing methods tend to code users by modeling their Hamming similarities with the items they historically interact with, which are termed as the first-order similarities in this work.
1 code implementation • 22 Dec 2022 • Yali Du, Yinwei Wei, Wei Ji, Fan Liu, Xin Luo, Liqiang Nie
The booming development and huge market of micro-videos bring new e-commerce channels for merchants.
1 code implementation • 20 Dec 2022 • Yinwei Wei, Xiang Wang, Liqiang Nie, Shaoyu Li, Dingxian Wang, Tat-Seng Chua
Knowledge Graph (KG), as a side-information, tends to be utilized to supplement the collaborative filtering (CF) based recommendation model.
no code implementations • 12 Dec 2022 • Linmei Hu, Ziwang Zhao, Xinkai Ge, Xuemeng Song, Liqiang Nie
The rapid development of social media provides a hotbed for the dissemination of fake news, which misleads readers and causes negative effects on society.
no code implementations • 11 Nov 2022 • Linmei Hu, Zeyi Liu, Ziwang Zhao, Lei Hou, Liqiang Nie, Juanzi Li
We introduce appropriate taxonomies respectively for Natural Language Understanding (NLU) and Natural Language Generation (NLG) to highlight these two main tasks of NLP.
1 code implementation • 27 Sep 2022 • Fan Liu, Zhiyong Cheng, Huilin Chen, Yinwei Wei, Liqiang Nie, Mohan Kankanhalli
At the item level, a synthetic data generation module is proposed to generate a synthetic item corresponding to the selected item based on the user's preferences.
no code implementations • 12 Sep 2022 • Tianyi Wang, Harry Cheng, Kam Pui Chow, Liqiang Nie
Most existing deep learning methods mainly focus on local features and relations within the face image using convolutional neural networks as a backbone.
no code implementations • 24 Jul 2022 • Yudong Han, Liqiang Nie, Jianhua Yin, Jianlong Wu, Yan Yan
Several studies have recently pointed that existing Visual Question Answering (VQA) models heavily suffer from the language prior problem, which refers to capturing superficial statistical correlations between the question type and the answer whereas ignoring the image contents.
1 code implementation • 24 Jul 2022 • Teng Sun, Wenjie Wang, Liqiang Jing, Yiran Cui, Xuemeng Song, Liqiang Nie
Inspired by this, we devise a model-agnostic counterfactual framework for multimodal sentiment analysis, which captures the direct effect of textual modality via an extra text model and estimates the indirect one by a multimodal model.
no code implementations • 21 Jul 2022 • Yudong Han, Jianhua Yin, Jianlong Wu, Yinwei Wei, Liqiang Nie
Visual Question Answering (VQA) is fundamentally compositional in nature, and many questions are simply answered by decomposing them into modular sub-problems.
no code implementations • 16 Jul 2022 • Xiaolin Chen, Xuemeng Song, Liqiang Jing, Shuo Li, Linmei Hu, Liqiang Nie
To address these limitations, we propose a novel dual knowledge-enhanced generative pretrained language model for multimodal task-oriented dialog systems (DKMD), consisting of three key components: dual knowledge selection, dual knowledge-enhanced context learning, and knowledge-enhanced response generation.
1 code implementation • 13 Jul 2022 • Yuzhang Shang, Dan Xu, Bin Duan, Ziliang Zong, Liqiang Nie, Yan Yan
Relying on the premise that the performance of a binary neural network can be largely restored with eliminated quantization error between full-precision weight vectors and their corresponding binary vectors, existing works of network binarization frequently adopt the idea of model robustness to reach the aforementioned objective.
1 code implementation • 6 Jul 2022 • Yuzhang Shang, Dan Xu, Ziliang Zong, Liqiang Nie, Yan Yan
Neural network binarization accelerates deep models by quantizing their weights and activations into 1-bit.
1 code implementation • 30 Jun 2022 • Yangyang Guo, Liqiang Nie, Yongkang Wong, Yibing Liu, Zhiyong Cheng, Mohan Kankanhalli
On the other hand, pertaining to the implicit knowledge, the multi-modal implicit knowledge for knowledge-based VQA still remains largely unexplored.
1 code implementation • 29 Apr 2022 • Wenjie Wang, Fuli Feng, Liqiang Nie, Tat-Seng Chua
both accuracy and diversity.
no code implementations • 28 Mar 2022 • Min Cao, Shiping Li, Juntao Li, Liqiang Nie, Min Zhang
On top of this, the efficiency-focused study on the ITR system is introduced as the third perspective.
1 code implementation • CVPR 2022 • Xingning Dong, Tian Gan, Xuemeng Song, Jianlong Wu, Yuan Cheng, Liqiang Nie
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 compact summary graph.
Ranked #1 on Unbiased Scene Graph Generation on Visual Genome (mR@20 metric)
1 code implementation • 10 Mar 2022 • Fan Liu, Huilin Chen, Zhiyong Cheng, AnAn Liu, Liqiang Nie, Mohan Kankanhalli
However, existing methods ignore the fact that different modalities contribute differently towards a user's preference on various factors of an item.
no code implementations • 4 Mar 2022 • Harry Cheng, Yangyang Guo, Tianyi Wang, Qi Li, Xiaojun Chang, Liqiang Nie
To this end, a voice-face matching method is devised to measure the matching degree of these two.
1 code implementation • Findings (ACL) 2022 • Fangkai Jiao, Yangyang Guo, Xuemeng Song, Liqiang Nie
Logical reasoning is of vital importance to natural language understanding.
Ranked #3 on Reading Comprehension on ReClor
1 code implementation • 25 Feb 2022 • Zhenyang Li, Yangyang Guo, Kejie Wang, Yinwei Wei, Liqiang Nie, Mohan Kankanhalli
Given that our framework is model-agnostic, we apply it to the existing popular baselines and validate its effectiveness on the benchmark dataset.
no code implementations • 25 Feb 2022 • Yangyang Guo, Liqiang Nie, Harry Cheng, Zhiyong Cheng, Mohan Kankanhalli, Alberto del Bimbo
From the results on four datasets regarding the above three tasks, our method yields remarkable performance improvements compared with the baselines, demonstrating its superiority on reducing the modality bias problem.
no code implementations • 30 Jan 2022 • Yuzhang Shang, Bin Duan, Ziliang Zong, Liqiang Nie, Yan Yan
Extensive experiments on CIFAR-10 and CIFAR-100 demonstrate the superiority of our novel Fourier analysis based MBP compared to other traditional MBP algorithms.
1 code implementation • 2 Dec 2021 • Wenjie Wang, Fuli Feng, Xiangnan He, Liqiang Nie, Tat-Seng Chua
Inspired by this observation, we propose a new training strategy named Adaptive Denoising Training (ADT), which adaptively prunes the noisy interactions by two paradigms (i. e., Truncated Loss and Reweighted Loss).
1 code implementation • 31 Oct 2021 • Ziyang Ma, Xianjing Han, Xuemeng Song, Yiran Cui, Liqiang Nie
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 video, described by a sentence query.
1 code implementation • 12 Oct 2021 • Zongmeng Zhang, Xianjing Han, Xuemeng Song, Yan Yan, Liqiang Nie
Towards this end, in this work, we propose a Multi-modal Interaction Graph Convolutional Network (MIGCN), which jointly explores the complex intra-modal relations and inter-modal interactions residing in the video and sentence query to facilitate the understanding and semantic correspondence capture of the video and sentence query.
no code implementations • 29 Sep 2021 • Yuzhang Shang, Dan Xu, Ziliang Zong, Liqiang Nie, Yan Yan
Neural network binarization accelerates deep models by quantizing their weights and activations into 1-bit.
no code implementations • ICCV 2021 • Yuzhang Shang, Bin Duan, Ziliang Zong, Liqiang Nie, Yan Yan
Knowledge distillation has become one of the most important model compression techniques by distilling knowledge from larger teacher networks to smaller student ones.
no code implementations • 17 Aug 2021 • Xiangkun Yin, Yangyang Guo, Liqiang Nie, Zhiyong Cheng
In addition, we empirically prove that collaborative filtering and semantic matching are complementary to each other in product search performance enhancement.
1 code implementation • 12 Jul 2021 • Yinwei Wei, Xiang Wang, Qi Li, Liqiang Nie, Yan Li, Xuanping Li, Tat-Seng Chua
It aims to maximize the mutual dependencies between item content and collaborative signals.
1 code implementation • ACM Special Interest Group on Information Retrieval 2021 • Leigang Qu, Meng Liu, Jianlong Wu, Zan Gao, Liqiang Nie
To address these issues, we develop a novel modality interaction modeling network based upon the routing mechanism, which is the first unified and dynamic multimodal interaction framework towards image-text retrieval.
1 code implementation • 8 Jun 2021 • Han Liu, Yangyang Guo, Jianhua Yin, Zan Gao, Liqiang Nie
To be specific, in this model, positive and negative reviews are separately gathered and utilized to model the user-preferred and user-rejected aspects, respectively.
1 code implementation • Findings (ACL) 2021 • Fangkai Jiao, Yangyang Guo, Yilin Niu, Feng Ji, Feng-Lin Li, Liqiang Nie
Pre-trained Language Models (PLMs) have achieved great success on Machine Reading Comprehension (MRC) over the past few years.
1 code implementation • 5 May 2021 • Yangyang Guo, Liqiang Nie, Zhiyong Cheng, Feng Ji, Ji Zhang, Alberto del Bimbo
Experimental results demonstrate that our adapted margin cosine loss can greatly enhance the baseline models with an absolute performance gain of 15\% on average, strongly verifying the potential of tackling the language prior problem in VQA from the angle of the answer feature space learning.
no code implementations • 17 Apr 2021 • Yongqi Li, Wenjie Li, Liqiang Nie
Moreover, in order to collect more complementary information in the historical context, we also propose to incorporate the multi-round relevance feedback technique to explore the impact of the retrieval context on current question understanding.
Conversational Question Answering Open-Domain Question Answering +1
1 code implementation • ICCV 2021 • Huasong Zhong, Jianlong Wu, Chong Chen, Jianqiang Huang, Minghua Deng, Liqiang Nie, Zhouchen Lin, Xian-Sheng Hua
On the other hand, a novel graph-based contrastive learning strategy is proposed to learn more compact clustering assignments.
1 code implementation • 22 Feb 2021 • Zhiyong Cheng, Fan Liu, Shenghan Mei, Yangyang Guo, Lei Zhu, Liqiang Nie
To demonstrate the effectiveness of our method, we design a light attention neural network to integrate both item-level and feature-level attention for neural ICF models.
1 code implementation • 19 Feb 2021 • Fan Liu, Zhiyong Cheng, Lei Zhu, Zan Gao, Liqiang Nie
To form the subgraphs, we design an unsupervised subgraph generation module, which can effectively identify users with common interests by exploiting both user feature and graph structure.
1 code implementation • 3 Feb 2021 • Yibing Liu, Yangyang Guo, Jianhua Yin, Xuemeng Song, Weifeng Liu, Liqiang Nie
However, recent studies have pointed out that the highlighted image regions from the visual attention are often irrelevant to the given question and answer, leading to model confusion for correct visual reasoning.
no code implementations • 18 Jan 2021 • Yongqi Li, Wenjie Li, Liqiang Nie
In the past years, Knowledge-Based Question Answering (KBQA), which aims to answer natural language questions using facts in a knowledge base, has been well developed.
1 code implementation • 11 Dec 2020 • Wenjie Wang, Ling-Yu Duan, Hao Jiang, Peiguang Jing, Xuemeng Song, Liqiang Nie
With the rising incidence of some diseases, such as obesity and diabetes, a healthy diet is arousing increasing attention.
1 code implementation • 30 Oct 2020 • Yangyang Guo, Liqiang Nie, Zhiyong Cheng, Qi Tian, Min Zhang
Concretely, we design a novel interpretation scheme whereby the loss of mis-predicted frequent and sparse answers of the same question type is distinctly exhibited during the late training phase.
1 code implementation • 20 Jun 2020 • Yangyang Guo, Zhiyong Cheng, Jiazheng Jing, Yanpeng Lin, Liqiang Nie, Meng Wang
Traditional FMs adopt the inner product to model the second-order interactions between different attributes, which are represented via feature vectors.
1 code implementation • 7 Jun 2020 • Wenjie Wang, Fuli Feng, Xiangnan He, Liqiang Nie, Tat-Seng Chua
In this work, we explore the central theme of denoising implicit feedback for recommender training.
no code implementations • 20 Mar 2020 • Fan Liu, Zhiyong Cheng, Lei Zhu, Chenghao Liu, Liqiang Nie
Considering the fact that for different users, the attributes of an item have different influence on their preference for this item, we design a novel attention mechanism to filter the message passed from an item to a target user by considering the attribute information.
no code implementations • IJCNLP 2019 • Linmei Hu, Luhao Zhang, Chuan Shi, Liqiang Nie, Weili Guan, Cheng Yang
Distantly-supervised relation extraction has proven to be effective to find relational facts from texts.
1 code implementation • 27 Aug 2019 • Yinwei Wei, Zhiyong Cheng, Xuzheng Yu, Zhou Zhao, Lei Zhu, Liqiang Nie
The hashtags, that a user provides to a post (e. g., a micro-video), are the ones which in her mind can well describe the post content where she is interested in.
1 code implementation • 21 Aug 2019 • Fan Liu, Zhiyong Cheng, Changchang Sun, Yinglong Wang, Liqiang Nie, Mohan Kankanhalli
To tackle this problem, in this paper, we propose a novel Multimodal Attentive Metric Learning (MAML) method to model user diverse preferences for various items.
1 code implementation • 13 May 2019 • Yangyang Guo, Zhiyong Cheng, Liqiang Nie, Yibing Liu, Yinglong Wang, Mohan Kankanhalli
Benefiting from the advancement of computer vision, natural language processing and information retrieval techniques, visual question answering (VQA), which aims to answer questions about an image or a video, has received lots of attentions over the past few years.
1 code implementation • 23 Nov 2018 • Cunxiao Du, Zhaozheng Chin, Fuli Feng, Lei Zhu, Tian Gan, Liqiang Nie
To address this problem, we introduce the interaction mechanism to incorporate word-level matching signals into the text classification task.
Ranked #4 on Text Classification on Yahoo! Answers
1 code implementation • ACL 2018 • Yansen Wang, Chen-Yi Liu, Minlie Huang, Liqiang Nie
Asking good questions in large-scale, open-domain conversational systems is quite significant yet rather untouched.
1 code implementation • 6 May 2018 • Han Liu, Xiangnan He, Fuli Feng, Liqiang Nie, Rui Liu, Hanwang Zhang
In this paper, we develop a generic feature-based recommendation model, called Discrete Factorization Machine (DFM), for fast and accurate recommendation.
no code implementations • 17 Apr 2018 • Xuemeng Song, Fuli Feng, Xianjing Han, Xin Yang, Wei Liu, Liqiang Nie
Nevertheless, existing studies overlook the rich valuable knowledge (rules) accumulated in fashion domain, especially the rules regarding clothing matching.
41 code implementations • WWW 2017 • Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, Tat-Seng Chua
When it comes to model the key factor in collaborative filtering -- the interaction between user and item features, they still resorted to matrix factorization and applied an inner product on the latent features of users and items.
3 code implementations • 5 Jul 2017 • Shaohua Li, Xinxing Xu, Liqiang Nie, Tat-Seng Chua
However in the traditional optimization objective, low-level features of the content image are absent, and the low-level features of the style image dominate the low-level detail structures of the new image.
no code implementations • 10 Jun 2017 • Xiang Wang, Xiangnan He, Liqiang Nie, Tat-Seng Chua
In this work, we address the problem of cross-domain social recommendation, i. e., recommending relevant items of information domains to potential users of social networks.
Ranked #2 on Recommendation Systems on Epinions
no code implementations • 7 Apr 2017 • Dan Wang, He-Yan Huang, Chi Lu, Bo-Si Feng, Liqiang Nie, Guihua Wen, Xian-Ling Mao
Specifically, we define a novel similarity formula for hierarchical labeled data by weighting each layer, and design a deep convolutional neural network to obtain a hash code for each data point.
no code implementations • 4 Feb 2017 • Minnan Luo, Xiaojun Chang, Zhihui Li, Liqiang Nie, Alexander G. Hauptmann, Qinghua Zheng
The heterogeneity-gap between different modalities brings a significant challenge to multimedia information retrieval.
2 code implementations • CVPR 2017 • Long Chen, Hanwang Zhang, Jun Xiao, Liqiang Nie, Jian Shao, Wei Liu, Tat-Seng Chua
Existing visual attention models are generally spatial, i. e., the attention is modeled as spatial probabilities that re-weight the last conv-layer feature map of a CNN encoding an input image.
no code implementations • 7 Nov 2016 • Ye Liu, Liqiang Nie, Lei Han, Luming Zhang, David S. Rosenblum
As compared to simple actions, activities are much more complex, but semantically consistent with a human's real life.