Search Results for author: Qing Li

Found 195 papers, 77 papers with code

Exploring Non-Autoregressive Text Style Transfer

1 code implementation EMNLP 2021 Yun Ma, Qing Li

In this paper, we explore Non-AutoRegressive (NAR) decoding for unsupervised text style transfer.

Contrastive Learning Knowledge Distillation +3

Conditional Causal Relationships between Emotions and Causes in Texts

no code implementations EMNLP 2020 Xinhong Chen, Qing Li, JianPing Wang

The causal relationships between emotions and causes in text have recently received a lot of attention.


Collaborative Learning of Bidirectional Decoders for Unsupervised Text Style Transfer

1 code implementation EMNLP 2021 Yun Ma, Yangbin Chen, Xudong Mao, Qing Li

In this paper, we propose a collaborative learning framework for unsupervised text style transfer using a pair of bidirectional decoders, one decoding from left to right while the other decoding from right to left.

Attribute Decoder +4

Task-oriented Domain-specific Meta-Embedding for Text Classification

no code implementations EMNLP 2020 Xin Wu, Yi Cai, Yang Kai, Tao Wang, Qing Li

Meta-embedding learning, which combines complementary information in different word embeddings, have shown superior performances across different Natural Language Processing tasks.

General Classification text-classification +2

Make Your Home Safe: Time-aware Unsupervised User Behavior Anomaly Detection in Smart Homes via Loss-guided Mask

1 code implementation16 Jun 2024 Jingyu Xiao, Zhiyao Xu, Qingsong Zou, Qing Li, Dan Zhao, Dong Fang, Ruoyu Li, Wenxin Tang, Kang Li, Xudong Zuo, Penghui Hu, Yong Jiang, Zixuan Weng, Michael R. Lyv

However, their performance often falls short because they do not effectively learn less frequent behaviors, consider temporal context, or account for the impact of noise in human behaviors.

Anomaly Detection

TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendation

no code implementations15 Jun 2024 Haohao Qu, Wenqi Fan, Zihuai Zhao, Qing Li

There is a growing interest in utilizing large-scale language models (LLMs) to advance next-generation Recommender Systems (RecSys), driven by their outstanding language understanding and in-context learning capabilities.

Collaborative Filtering In-Context Learning +2

Towards Flexible Interactive Reflection Removal with Human Guidance

1 code implementation3 Jun 2024 Xiao Chen, Xudong Jiang, Yunkang Tao, Zhen Lei, Qing Li, Chenyang Lei, Zhaoxiang Zhang

However, incorporating the raw user guidance naively into the existing reflection removal network does not result in performance gains.

Interactive Segmentation Reflection Removal

MGCP: A Multi-Grained Correlation based Prediction Network for Multivariate Time Series

no code implementations30 May 2024 Zhicheng Chen, Xi Xiao, Ke Xu, Zhong Zhang, Yu Rong, Qing Li, Guojun Gan, Zhiqiang Xu, Peilin Zhao

Multivariate time series prediction is widely used in daily life, which poses significant challenges due to the complex correlations that exist at multi-grained levels.

Time Series Time Series Prediction

Expert-Guided Extinction of Toxic Tokens for Debiased Generation

no code implementations29 May 2024 Xueyao Sun, Kaize Shi, Haoran Tang, Guandong Xu, Qing Li

Large language models (LLMs) can elicit social bias during generations, especially when inference with toxic prompts.

Fairness Retrieval

Unifying 3D Vision-Language Understanding via Promptable Queries

no code implementations19 May 2024 Ziyu Zhu, Zhuofan Zhang, Xiaojian Ma, Xuesong Niu, Yixin Chen, Baoxiong Jia, Zhidong Deng, Siyuan Huang, Qing Li

A unified model for 3D vision-language (3D-VL) understanding is expected to take various scene representations and perform a wide range of tasks in a 3D scene.

Decoder Information Retrieval +2

A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models

no code implementations10 May 2024 Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, Qing Li

Given the powerful abilities of RAG in providing the latest and helpful auxiliary information, Retrieval-Augmented Large Language Models (RA-LLMs) have emerged to harness external and authoritative knowledge bases, rather than solely relying on the model's internal knowledge, to augment the generation quality of LLMs.

Information Retrieval Retrieval

Compressing Long Context for Enhancing RAG with AMR-based Concept Distillation

no code implementations6 May 2024 Kaize Shi, Xueyao Sun, Qing Li, Guandong Xu

The proposed algorithm compresses the cluttered raw retrieved documents into a compact set of crucial concepts distilled from the informative nodes of AMR by referring to reliable linguistic features.

Open-Domain Question Answering Reading Comprehension

SlotGAT: Slot-based Message Passing for Heterogeneous Graph Neural Network

1 code implementation3 May 2024 Ziang Zhou, Jieming Shi, Renchi Yang, Yuanhang Zou, Qing Li

We identify a potential semantic mixing issue in existing message passing processes, where the representations of the neighbors of a node $v$ are forced to be transformed to the feature space of $v$ for aggregation, though the neighbors are in different types.

Graph Neural Network Link Prediction +1

Graph Machine Learning in the Era of Large Language Models (LLMs)

no code implementations23 Apr 2024 Wenqi Fan, Shijie Wang, Jiani Huang, Zhikai Chen, Yu Song, Wenzhuo Tang, Haitao Mao, Hui Liu, Xiaorui Liu, Dawei Yin, Qing Li

Meanwhile, graphs, especially knowledge graphs, are rich in reliable factual knowledge, which can be utilized to enhance the reasoning capabilities of LLMs and potentially alleviate their limitations such as hallucinations and the lack of explainability.

Few-Shot Learning Knowledge Graphs +1

MaterialSeg3D: Segmenting Dense Materials from 2D Priors for 3D Assets

no code implementations22 Apr 2024 Zeyu Li, Ruitong Gan, Chuanchen Luo, Yuxi Wang, Jiaheng Liu, Ziwei Zhu Man Zhang, Qing Li, XuCheng Yin, Zhaoxiang Zhang, Junran Peng

Driven by powerful image diffusion models, recent research has achieved the automatic creation of 3D objects from textual or visual guidance.

CLIP-GS: CLIP-Informed Gaussian Splatting for Real-time and View-consistent 3D Semantic Understanding

1 code implementation22 Apr 2024 Guibiao Liao, Jiankun Li, Zhenyu Bao, Xiaoqing Ye, Jingdong Wang, Qing Li, Kanglin Liu

Additionally, to address the semantic ambiguity, caused by utilizing view-inconsistent 2D CLIP semantics to supervise Gaussians, we introduce a 3D Coherent Self-training (3DCS) strategy, resorting to the multi-view consistency originated from the 3D model.


Advancing the Robustness of Large Language Models through Self-Denoised Smoothing

1 code implementation18 Apr 2024 Jiabao Ji, Bairu Hou, Zhen Zhang, Guanhua Zhang, Wenqi Fan, Qing Li, Yang Zhang, Gaowen Liu, Sijia Liu, Shiyu Chang

Although large language models (LLMs) have achieved significant success, their vulnerability to adversarial perturbations, including recent jailbreak attacks, has raised considerable concerns.

PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics

1 code implementation6 Apr 2024 Derui Zhu, Dingfan Chen, Qing Li, Zongxiong Chen, Lei Ma, Jens Grossklags, Mario Fritz

Despite tremendous advancements in large language models (LLMs) over recent years, a notably urgent challenge for their practical deployment is the phenomenon of hallucination, where the model fabricates facts and produces non-factual statements.

Benchmarking Hallucination

Generative Active Learning for Image Synthesis Personalization

1 code implementation22 Mar 2024 Xulu Zhang, WengYu Zhang, Xiao-Yong Wei, Jinlin Wu, Zhaoxiang Zhang, Zhen Lei, Qing Li

The primary challenge in conducting active learning on generative models lies in the open-ended nature of querying, which differs from the closed form of querying in discriminative models that typically target a single concept.

Active Learning Image Generation

Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting

no code implementations22 Mar 2024 Jun Guo, Xiaojian Ma, Yue Fan, Huaping Liu, Qing Li

Open-vocabulary 3D scene understanding presents a significant challenge in computer vision, withwide-ranging applications in embodied agents and augmented reality systems.

Scene Understanding Segmentation +2

A Picture Is Worth a Graph: Blueprint Debate on Graph for Multimodal Reasoning

no code implementations22 Mar 2024 Changmeng Zheng, Dayong Liang, WengYu Zhang, Xiao-Yong Wei, Tat-Seng Chua, Qing Li

The study addresses two key challenges: the trivialization of opinions resulting from excessive summarization and the diversion of focus caused by distractor concepts introduced from images.

Multimodal Reasoning

End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations

1 code implementation19 Mar 2024 Lirui Luo, Guoxi Zhang, Hongming Xu, Yaodong Yang, Cong Fang, Qing Li

Neuro-symbolic reinforcement learning (NS-RL) has emerged as a promising paradigm for explainable decision-making, characterized by the interpretability of symbolic policies.

Decision Making reinforcement-learning

VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding

no code implementations18 Mar 2024 Yue Fan, Xiaojian Ma, Rujie Wu, Yuntao Du, Jiaqi Li, Zhi Gao, Qing Li

We explore how reconciling several foundation models (large language models and vision-language models) with a novel unified memory mechanism could tackle the challenging video understanding problem, especially capturing the long-term temporal relations in lengthy videos.

Video Understanding

FashionReGen: LLM-Empowered Fashion Report Generation

no code implementations11 Mar 2024 Yujuan Ding, Yunshan Ma, Wenqi Fan, Yige Yao, Tat-Seng Chua, Qing Li

Fashion analysis refers to the process of examining and evaluating trends, styles, and elements within the fashion industry to understand and interpret its current state, generating fashion reports.

Large Language Models are In-Context Molecule Learners

1 code implementation7 Mar 2024 Jiatong Li, Wei Liu, Zhihao Ding, Wenqi Fan, Yuqiang Li, Qing Li

Specifically, ICMA incorporates the following three stages: Hybrid Context Retrieval, Post-retrieval Re-ranking, and In-context Molecule Tuning.

Cross-Modal Retrieval Re-Ranking +2

ESE: Espresso Sentence Embeddings

1 code implementation22 Feb 2024 Xianming Li, Zongxi Li, Jing Li, Haoran Xie, Qing Li

High-quality sentence embeddings are fundamental in many natural language processing (NLP) tasks, such as semantic textual similarity (STS) and retrieval-augmented generation (RAG).

Retrieval Semantic Textual Similarity +4

Linear-Time Graph Neural Networks for Scalable Recommendations

1 code implementation21 Feb 2024 Jiahao Zhang, Rui Xue, Wenqi Fan, Xin Xu, Qing Li, Jian Pei, Xiaorui Liu

In this paper, we propose a Linear-Time Graph Neural Network (LTGNN) to scale up GNN-based recommender systems to achieve comparable scalability as classic MF approaches while maintaining GNNs' powerful expressiveness for superior prediction accuracy.

Graph Neural Network Recommendation Systems

One Train for Two Tasks: An Encrypted Traffic Classification Framework Using Supervised Contrastive Learning

1 code implementation12 Feb 2024 Haozhen Zhang, Xi Xiao, Le Yu, Qing Li, Zhen Ling, Ye Zhang

In particular, we utilize supervised contrastive learning to enhance the packet-level and flow-level representations and perform graph data augmentation on the byte-level traffic graph so that the fine-grained semantic-invariant characteristics between bytes can be captured through contrastive learning.

Classification Contrastive Learning +3

OV-NeRF: Open-vocabulary Neural Radiance Fields with Vision and Language Foundation Models for 3D Semantic Understanding

no code implementations7 Feb 2024 Guibiao Liao, Kaichen Zhou, Zhenyu Bao, Kanglin Liu, Qing Li

First, from the single-view perspective, we introduce Region Semantic Ranking (RSR) regularization by leveraging 2D mask proposals derived from SAM to rectify the noisy semantics of each training view, facilitating accurate semantic field learning.

Progress and Opportunities of Foundation Models in Bioinformatics

no code implementations6 Feb 2024 Qing Li, Zhihang Hu, YiXuan Wang, Lei LI, Yimin Fan, Irwin King, Le Song, Yu Li

Central to our focus is the application of FMs to specific biological problems, aiming to guide the research community in choosing appropriate FMs for their research needs.

Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey

1 code implementation3 Feb 2024 Yi Xin, Siqi Luo, Haodi Zhou, Junlong Du, Xiaohong Liu, Yue Fan, Qing Li, Yuntao Du

Large-scale pre-trained vision models (PVMs) have shown great potential for adaptability across various downstream vision tasks.

Transfer Learning

SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition

1 code implementation31 Jan 2024 Xu Hu, Yuxi Wang, Lue Fan, Junsong Fan, Junran Peng, Zhen Lei, Qing Li, Zhaoxiang Zhang

3D Gaussian Splatting has emerged as an alternative 3D representation for novel view synthesis, benefiting from its high-quality rendering results and real-time rendering speed.

Novel View Synthesis Segmentation +1

One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training

1 code implementation30 Jan 2024 Lianbo Ma, Yuee Zhou, Jianlun Ma, Guo Yu, Qing Li

During the gradient descent learning, a one-step forward search is designed to find the trial gradient of the next-step, which is adopted to adjust the gradient of current step towards the direction of fast convergence.


3D Reconstruction and New View Synthesis of Indoor Environments based on a Dual Neural Radiance Field

1 code implementation26 Jan 2024 Zhenyu Bao, Guibiao Liao, Zhongyuan Zhao, Kanglin Liu, Qing Li, Guoping Qiu

One of the innovative features of Du-NeRF is that it decouples a view-independent component from the density field and uses it as a label to supervise the learning process of the SDF field.

3D Reconstruction Novel View Synthesis

PSAvatar: A Point-based Morphable Shape Model for Real-Time Head Avatar Animation with 3D Gaussian Splatting

1 code implementation23 Jan 2024 Zhongyuan Zhao, Zhenyu Bao, Qing Li, Guoping Qiu, Kanglin Liu

In this paper, we introduce PSAvatar, a novel framework for animatable head avatar creation that utilizes discrete geometric primitive to create a parametric morphable shape model and employs 3D Gaussian for fine detail representation and high fidelity rendering.

SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding

no code implementations17 Jan 2024 Baoxiong Jia, Yixin Chen, Huangyue Yu, Yan Wang, Xuesong Niu, Tengyu Liu, Qing Li, Siyuan Huang

In comparison to recent advancements in the 2D domain, grounding language in 3D scenes faces several significant challenges: (i) the inherent complexity of 3D scenes due to the diverse object configurations, their rich attributes, and intricate relationships; (ii) the scarcity of paired 3D vision-language data to support grounded learning; and (iii) the absence of a unified learning framework to distill knowledge from grounded 3D data.

3D visual grounding Scene Understanding

Developing ChatGPT for Biology and Medicine: A Complete Review of Biomedical Question Answering

no code implementations15 Jan 2024 Qing Li, Lei LI, Yu Li

Central to our focus is the utilizing of language models and multimodal paradigms for medical question answering, aiming to guide the research community in selecting appropriate mechanisms for their specific medical research requirements.

Cross-Modal Retrieval Medical Diagnosis +3

3D Landmark Detection on Human Point Clouds: A Benchmark and A Dual Cascade Point Transformer Framework

no code implementations14 Jan 2024 Fan Zhang, Shuyi Mao, Qing Li, Xiaojiang Peng

Comparative evaluations with popular point-based methods on HPoint103 and the public dataset DHP19 demonstrate the dramatic outperformance of our D-CPT.

Decoder Pose Estimation +1

Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models

1 code implementation13 Jan 2024 Zhengxin Zhang, Dan Zhao, Xupeng Miao, Gabriele Oliaro, Qing Li, Yong Jiang, Zhihao Jia

Experiments show that QST can reduce the total memory footprint by up to 2. 3 $\times$ and speed up the finetuning process by up to 3 $\times$ while achieving competent performance compared with the state-of-the-art.

Cross Initialization for Face Personalization of Text-to-Image Models

1 code implementation CVPR 2024 Lianyu Pang, Jian Yin, Haoran Xie, Qiping Wang, Qing Li, Xudong Mao

Additionally a fast version of our method allows for capturing an input image in roughly 26 seconds while surpassing the baseline methods in terms of both reconstruction and editability.

Cross Initialization for Personalized Text-to-Image Generation

1 code implementation26 Dec 2023 Lianyu Pang, Jian Yin, Haoran Xie, Qiping Wang, Qing Li, Xudong Mao

Additionally, a fast version of our method allows for capturing an input image in roughly 26 seconds, while surpassing the baseline methods in terms of both reconstruction and editability.

Text-to-Image Generation

CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update

no code implementations CVPR 2024 Zhi Gao, Yuntao Du, Xintong Zhang, Xiaojian Ma, Wenjuan Han, Song-Chun Zhu, Qing Li

However, these methods often overlook the potential for continual learning, typically by freezing the utilized tools, thus limiting their adaptation to environments requiring new knowledge.

Continual Learning Question Answering +1

Compositional Inversion for Stable Diffusion Models

1 code implementation13 Dec 2023 Xulu Zhang, Xiao-Yong Wei, Jinlin Wu, Tianyi Zhang, Zhaoxiang Zhang, Zhen Lei, Qing Li

It stems from the fact that during inversion, the irrelevant semantics in the user images are also encoded, forcing the inverted concepts to occupy locations far from the core distribution in the embedding space.

Recognizing Conditional Causal Relationships about Emotions and Their Corresponding Conditions

no code implementations28 Nov 2023 Xinhong Chen, Zongxi Li, YaoWei Wang, Haoran Xie, JianPing Wang, Qing Li

To highlight the context in such special causal relationships, we propose a new task to determine whether or not an input pair of emotion and cause has a valid causal relationship under different contexts and extract the specific context clauses that participate in the causal relationship.


An Embodied Generalist Agent in 3D World

1 code implementation18 Nov 2023 Jiangyong Huang, Silong Yong, Xiaojian Ma, Xiongkun Linghu, Puhao Li, Yan Wang, Qing Li, Song-Chun Zhu, Baoxiong Jia, Siyuan Huang

However, several significant challenges remain: (i) most of these models rely on 2D images yet exhibit a limited capacity for 3D input; (ii) these models rarely explore the tasks inherently defined in 3D world, e. g., 3D grounding, embodied reasoning and acting.

3D dense captioning Question Answering +3

Untargeted Black-box Attacks for Social Recommendations

no code implementations13 Nov 2023 Wenqi Fan, Shijie Wang, Xiao-Yong Wei, Xiaowei Mei, Qing Li

To perform untargeted attacks on social recommender systems, attackers can construct malicious social relationships for fake users to enhance the attack performance.

Decision Making Multi-agent Reinforcement Learning +1

NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Function

1 code implementation NeurIPS 2023 Qing Li, Huifang Feng, Kanle Shi, Yue Gao, Yi Fang, Yu-Shen Liu, Zhizhong Han

Specifically, we introduce loss functions to facilitate query points to iteratively reach the moving targets and aggregate onto the approximated surface, thereby learning a global surface representation of the data.

Embedding in Recommender Systems: A Survey

1 code implementation28 Oct 2023 Xiangyu Zhao, Maolin Wang, Xinjian Zhao, Jiansheng Li, Shucheng Zhou, Dawei Yin, Qing Li, Jiliang Tang, Ruocheng Guo

This survey covers embedding methods like collaborative filtering, self-supervised learning, and graph-based techniques.

AutoML Collaborative Filtering +3

Fast Graph Condensation with Structure-based Neural Tangent Kernel

1 code implementation17 Oct 2023 Lin Wang, Wenqi Fan, Jiatong Li, Yao Ma, Qing Li

The rapid development of Internet technology has given rise to a vast amount of graph-structured data.

Dataset Condensation Graph Mining

Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World

1 code implementation16 Oct 2023 Rujie Wu, Xiaojian Ma, Zhenliang Zhang, Wei Wang, Qing Li, Song-Chun Zhu, Yizhou Wang

We even conceived a neuro-symbolic reasoning approach that reconciles LLMs & VLMs with logical reasoning to emulate the human problem-solving process for Bongard Problems.

Few-Shot Learning Logical Reasoning +1

Multi-Scale Spatial-Temporal Recurrent Networks for Traffic Flow Prediction

no code implementations12 Oct 2023 Haiyang Liu, Chunjiang Zhu, Detian Zhang, Qing Li

Traffic flow prediction is one of the most fundamental tasks of intelligent transportation systems.

Dataset Condensation for Recommendation

no code implementations2 Oct 2023 Jiahao Wu, Wenqi Fan, Shengcai Liu, Qijiong Liu, Rui He, Qing Li, Ke Tang

However, applying existing approaches to condense recommendation datasets is impractical due to following challenges: (i) sampling-based methods are inadequate in addressing the long-tailed distribution problem; (ii) synthesizing-based methods are not applicable due to discreteness of interactions and large size of recommendation datasets; (iii) neither of them fail to address the specific issue in recommendation of false negative items, where items with potential user interest are incorrectly sampled as negatives owing to insufficient exposure.

Dataset Condensation

Label Supervised LLaMA Finetuning

2 code implementations2 Oct 2023 Zongxi Li, Xianming Li, Yuzhang Liu, Haoran Xie, Jing Li, Fu-lee Wang, Qing Li, Xiaoqin Zhong

We evaluate this approach with Label Supervised LLaMA (LS-LLaMA), based on LLaMA-2-7B, a relatively small-scale LLM, and can be finetuned on a single GeForce RTX4090 GPU.

 Ranked #1 on Named Entity Recognition (NER) on CoNLL03 (F1 (micro) metric)

named-entity-recognition Named Entity Recognition +7

Enhancing Graph Collaborative Filtering via Uniformly Co-Clustered Intent Modeling

no code implementations22 Sep 2023 Jiahao Wu, Wenqi Fan, Shengcai Liu, Qijiong Liu, Qing Li, Ke Tang

To model the compatibility between user intents and item properties, we design the user-item co-clustering module, maximizing the mutual information of co-clusters of users and items.

Collaborative Filtering

Neural Gradient Learning and Optimization for Oriented Point Normal Estimation

1 code implementation17 Sep 2023 Qing Li, Huifang Feng, Kanle Shi, Yi Fang, Yu-Shen Liu, Zhizhong Han

We propose Neural Gradient Learning (NGL), a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation.

Variational Tracking and Redetection for Closely-spaced Objects in Heavy Clutter: Supplementary Materials

no code implementations4 Sep 2023 Runze Gan, Qing Li, Simon Godsill

The non-homogeneous Poisson process (NHPP) is a widely used measurement model that allows for an object to generate multiple measurements over time.

Effective Multi-Graph Neural Networks for Illicit Account Detection on Cryptocurrency Transaction Networks

1 code implementation4 Sep 2023 Zhihao Ding, Jieming Shi, Qing Li, Jiannong Cao

Extensive experiments, comparing against 14 existing solutions on 4 large cryptocurrency datasets of Bitcoin and Ethereum, demonstrate that DIAM consistently achieves the best performance to accurately detect illicit accounts, while being efficient.

Feature Engineering Graph Neural Network

Consensus-based Distributed Variational Multi-object Tracker in Multi-Sensor Network

no code implementations2 Sep 2023 Qing Li, Runze Gan, Simon Godsill

Then, we develop a distributed version leveraging the average consensus algorithm, which is theoretically equivalent to the centralised sensor fusion tracker and requires only local message passing with neighbouring sensors.

Object Tracking Sensor Fusion

LLaMA-E: Empowering E-commerce Authoring with Object-Interleaved Instruction Following

no code implementations9 Aug 2023 Kaize Shi, Xueyao Sun, Dingxian Wang, Yinlin Fu, Guandong Xu, Qing Li

E-commerce authoring entails creating engaging, diverse, and targeted content to enhance preference elicitation and retrieval experience.

Common Sense Reasoning Instruction Following +1

3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment

1 code implementation ICCV 2023 Ziyu Zhu, Xiaojian Ma, Yixin Chen, Zhidong Deng, Siyuan Huang, Qing Li

3D vision-language grounding (3D-VL) is an emerging field that aims to connect the 3D physical world with natural language, which is crucial for achieving embodied intelligence.

Dense Captioning Question Answering +3

DiffusePast: Diffusion-based Generative Replay for Class Incremental Semantic Segmentation

no code implementations2 Aug 2023 Jingfan Chen, Yuxi Wang, Pengfei Wang, Xiao Chen, Zhaoxiang Zhang, Zhen Lei, Qing Li

The Class Incremental Semantic Segmentation (CISS) extends the traditional segmentation task by incrementally learning newly added classes.

Class-Incremental Semantic Segmentation Segmentation

Certified Robustness for Large Language Models with Self-Denoising

1 code implementation14 Jul 2023 Zhen Zhang, Guanhua Zhang, Bairu Hou, Wenqi Fan, Qing Li, Sijia Liu, Yang Zhang, Shiyu Chang

This largely falls into the study of certified robust LLMs, i. e., all predictions of LLM are certified to be correct in a local region around the input.


Counterfactual Explanation for Fairness in Recommendation

no code implementations10 Jul 2023 Xiangmeng Wang, Qian Li, Dianer Yu, Qing Li, Guandong Xu

The counterfactual explanations help to provide rational and proximate explanations for model fairness, while the attentive action pruning narrows the search space of attributes.

Attribute Causal Inference +4

STG4Traffic: A Survey and Benchmark of Spatial-Temporal Graph Neural Networks for Traffic Prediction

1 code implementation2 Jul 2023 Xunlian Luo, Chunjiang Zhu, Detian Zhang, Qing Li

However, a survey study of graph learning, spatial-temporal graph models for traffic, as well as a fair comparison of baseline models are pending and unavoidable issues.

Graph Learning Traffic Prediction

Farthest Streamline Sampling for the Uniform Distribution of Forearm Muscle Fiber Tracts from Diffusion Tensor Imaging

no code implementations24 Jun 2023 Yang Li, Shihan Ma, Jiamin Zhao, Qing Li, Xinjun Sheng

FSS reduced the sampling of long tracts (10% reduction in fiber length, P<0. 05), and the architectural parameters were within physiological ranges (two parameters with P<0. 05).

Recurrent Attention Networks for Long-text Modeling

1 code implementation12 Jun 2023 Xianming Li, Zongxi Li, Xiaotian Luo, Haoran Xie, Xing Lee, Yingbin Zhao, Fu Lee Wang, Qing Li

Revisiting the self-attention mechanism and the recurrent structure, this paper proposes a novel long-document encoding model, Recurrent Attention Network (RAN), to enable the recurrent operation of self-attention.


Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective

1 code implementation11 Jun 2023 Jiatong Li, Yunqing Liu, Wenqi Fan, Xiao-Yong Wei, Hui Liu, Jiliang Tang, Qing Li

In this work, we propose a novel LLM-based framework (MolReGPT) for molecule-caption translation, where an In-Context Few-Shot Molecule Learning paradigm is introduced to empower molecule discovery with LLMs like ChatGPT to perform their in-context learning capability without domain-specific pre-training and fine-tuning.

In-Context Learning Molecule Captioning +3

FERN: Leveraging Graph Attention Networks for Failure Evaluation and Robust Network Design

no code implementations30 May 2023 Chenyi Liu, Vaneet Aggarwal, Tian Lan, Nan Geng, Yuan Yang, Mingwei Xu, Qing Li

By providing a neural network function approximation of this common kernel using graph attention networks, we develop a unified learning-based framework, FERN, for scalable Failure Evaluation and Robust Network design.

Graph Attention

Inferring Attracting Basins of Power System with Machine Learning

no code implementations20 May 2023 Yao Du, Qing Li, Huawei Fan, Meng Zhan, Jinghua Xiao, Xingang Wang

Power systems dominated by renewable energy encounter frequently large, random disturbances, and a critical challenge faced in power-system management is how to anticipate accurately whether the perturbed systems will return to the functional state after the transient or collapse.

Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy

no code implementations10 May 2023 Thanveer Shaik, Xiaohui Tao, Haoran Xie, Lin Li, Xiaofeng Zhu, Qing Li

Machine unlearning (MU) is gaining increasing attention due to the need to remove or modify predictions made by machine learning (ML) models.

Fairness Machine Unlearning +1

SHS-Net: Learning Signed Hyper Surfaces for Oriented Normal Estimation of Point Clouds

1 code implementation CVPR 2023 Qing Li, Huifang Feng, Kanle Shi, Yue Gao, Yi Fang, Yu-Shen Liu, Zhizhong Han

In this work, we introduce signed hyper surfaces (SHS), which are parameterized by multi-layer perceptron (MLP) layers, to learn to estimate oriented normals from point clouds in an end-to-end manner.


An Adversarial Non-Autoregressive Model for Text Generation with Incomplete Information

no code implementations6 May 2023 Da Ren, Yi Cai, Qing Li

Non-autoregressive models have been widely studied in the Complete Information Scenario (CIS), in which the input has complete information of corresponding output.

Position Text Generation

MD-Manifold: A Medical-Distance-Based Representation Learning Approach for Medical Concept and Patient Representation

no code implementations30 Apr 2023 Shaodong Wang, Qing Li, Wenli Zhang

Representing medical concepts for healthcare analytical tasks requires incorporating medical domain knowledge and prior information from patient description data.

Data Augmentation Feature Engineering +1

Attention-based Spatial-Temporal Graph Convolutional Recurrent Networks for Traffic Forecasting

no code implementations25 Feb 2023 Haiyang Liu, Chunjiang Zhu, Detian Zhang, Qing Li

The key challenge is to effectively model complex spatial-temporal dependencies and correlations in modern traffic data.

Dynamic Graph Convolutional Network with Attention Fusion for Traffic Flow Prediction

1 code implementation24 Feb 2023 Xunlian Luo, Chunjiang Zhu, Detian Zhang, Qing Li

Accurate and real-time traffic state prediction is of great practical importance for urban traffic control and web mapping services.

Fairly Adaptive Negative Sampling for Recommendations

no code implementations16 Feb 2023 Xiao Chen, Wenqi Fan, Jingfan Chen, Haochen Liu, Zitao Liu, Zhaoxiang Zhang, Qing Li

Pairwise learning strategies are prevalent for optimizing recommendation models on implicit feedback data, which usually learns user preference by discriminating between positive (i. e., clicked by a user) and negative items (i. e., obtained by negative sampling).

Attribute Fairness

Generative Diffusion Models on Graphs: Methods and Applications

1 code implementation6 Feb 2023 Chengyi Liu, Wenqi Fan, Yunqing Liu, Jiatong Li, Hang Li, Hui Liu, Jiliang Tang, Qing Li

Given the great success of diffusion models in image generation, increasing efforts have been made to leverage these techniques to advance graph generation in recent years.

Denoising Graph Generation +2

AttMEMO : Accelerating Transformers with Memoization on Big Memory Systems

no code implementations23 Jan 2023 Yuan Feng, Hyeran Jeon, Filip Blagojevic, Cyril Guyot, Qing Li, Dong Li

Transformer models gain popularity because of their superior inference accuracy and inference throughput.

Graph Learning and Its Advancements on Large Language Models: A Holistic Survey

no code implementations17 Dec 2022 Shaopeng Wei, Yu Zhao, Xingyan Chen, Qing Li, Fuzhen Zhuang, Ji Liu, Fuji Ren, Gang Kou

Different from previous surveys on graph learning, we provide a holistic review that analyzes current works from the perspective of graph structure, and discusses the latest applications, trends, and challenges in graph learning.

Graph Learning Representation Learning

Hierarchical Deep Reinforcement Learning for VWAP Strategy Optimization

no code implementations11 Dec 2022 XiaoDong Li, Pangjing Wu, Chenxin Zou, Qing Li

Designing an intelligent volume-weighted average price (VWAP) strategy is a critical concern for brokers, since traditional rule-based strategies are relatively static that cannot achieve a lower transaction cost in a dynamic market.

Hierarchical Reinforcement Learning reinforcement-learning +1

A Comprehensive Survey on Enterprise Financial Risk Analysis from Big Data Perspective

no code implementations28 Nov 2022 Yu Zhao, Huaming Du, Qing Li, Fuzhen Zhuang, Ji Liu, Gang Kou

In contrast, this paper attempts to provide a systematic literature survey of enterprise risk analysis approaches from Big Data perspective, which reviews more than 250 representative articles in the past almost 50 years (from 1968 to 2023).


Joint Multimodal Entity-Relation Extraction Based on Edge-enhanced Graph Alignment Network and Word-pair Relation Tagging

1 code implementation28 Nov 2022 Li Yuan, Yi Cai, Jin Wang, Qing Li

This paper is the first to propose jointly performing MNER and MRE as a joint multimodal entity-relation extraction task (JMERE).

graph construction named-entity-recognition +5

ESIE-BERT: Enriching Sub-words Information Explicitly with BERT for Joint Intent Classification and SlotFilling

no code implementations27 Nov 2022 Yu Guo, Zhilong Xie, Xingyan Chen, Huangen Chen, Leilei Wang, Huaming Du, Shaopeng Wei, Yu Zhao, Qing Li, Gang Wu

We address the problem by introducing a novel joint method on top of BERT which explicitly models the multiple sub-tokens features after wordpiece tokenization, thereby contributing to the two tasks.

intent-classification Intent Classification +5

Scene-Text Oriented Reffering Expression Comprehension

1 code implementation 2023 2022 Yuqi Bu, Liuwu Li, Jiayuan Xie, Qiong Liu, Yi Cai, Qingbao Huang, Qing Li

Abstract—Referring expression comprehension (REC) aims to identify and locate a specific object in visual scenes referred to by a natural language expression.

Object Localization Referring Expression +1

SQA3D: Situated Question Answering in 3D Scenes

1 code implementation14 Oct 2022 Xiaojian Ma, Silong Yong, Zilong Zheng, Qing Li, Yitao Liang, Song-Chun Zhu, Siyuan Huang

We propose a new task to benchmark scene understanding of embodied agents: Situated Question Answering in 3D Scenes (SQA3D).

Question Answering Referring Expression +1

HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces

1 code implementation13 Oct 2022 Qing Li, Yu-Shen Liu, Jin-San Cheng, Cheng Wang, Yi Fang, Zhizhong Han

To address these issues, we introduce hyper surface fitting to implicitly learn hyper surfaces, which are represented by multi-layer perceptron (MLP) layers that take point features as input and output surface patterns in a high dimensional feature space.

Surface Normals Estimation

Neural-Symbolic Recursive Machine for Systematic Generalization

no code implementations4 Oct 2022 Qing Li, Yixin Zhu, Yitao Liang, Ying Nian Wu, Song-Chun Zhu, Siyuan Huang

We evaluate NSR's efficacy across four challenging benchmarks designed to probe systematic generalization capabilities: SCAN for semantic parsing, PCFG for string manipulation, HINT for arithmetic reasoning, and a compositional machine translation task.

Arithmetic Reasoning Machine Translation +2

Fairness Reprogramming

1 code implementation21 Sep 2022 Guanhua Zhang, Yihua Zhang, Yang Zhang, Wenqi Fan, Qing Li, Sijia Liu, Shiyu Chang

Specifically, FairReprogram considers the case where models can not be changed and appends to the input a set of perturbations, called the fairness trigger, which is tuned towards the fairness criteria under a min-max formulation.


A Comprehensive Survey on Trustworthy Recommender Systems

no code implementations21 Sep 2022 Wenqi Fan, Xiangyu Zhao, Xiao Chen, Jingran Su, Jingtong Gao, Lin Wang, Qidong Liu, Yiqi Wang, Han Xu, Lei Chen, Qing Li

As one of the most successful AI-powered applications, recommender systems aim to help people make appropriate decisions in an effective and efficient way, by providing personalized suggestions in many aspects of our lives, especially for various human-oriented online services such as e-commerce platforms and social media sites.

Fairness Recommendation Systems

Disentangled Contrastive Learning for Social Recommendation

1 code implementation18 Aug 2022 Jiahao Wu, Wenqi Fan, Jingfan Chen, Shengcai Liu, Qing Li, Ke Tang

In this work, to address such limitation, we propose a novel Disentangled contrastive learning framework for social Recommendations DcRec.

Contrastive Learning Representation Learning +1

InitialGAN: A Language GAN with Completely Random Initialization

no code implementations4 Aug 2022 Da Ren, Qing Li

Text generative models trained via Maximum Likelihood Estimation (MLE) suffer from the notorious exposure bias problem, and Generative Adversarial Networks (GANs) are shown to have potential to tackle this problem.

IPDAE: Improved Patch-Based Deep Autoencoder for Lossy Point Cloud Geometry Compression

1 code implementation4 Aug 2022 Kang You, Pan Gao, Qing Li

Point cloud is a crucial representation of 3D contents, which has been widely used in many areas such as virtual reality, mixed reality, autonomous driving, etc.

Autonomous Driving Mixed Reality

Knowledge-enhanced Black-box Attacks for Recommendations

no code implementations21 Jul 2022 Jingfan Chen, Wenqi Fan, Guanghui Zhu, Xiangyu Zhao, Chunfeng Yuan, Qing Li, Yihua Huang

Recent studies have shown that deep neural networks-based recommender systems are vulnerable to adversarial attacks, where attackers can inject carefully crafted fake user profiles (i. e., a set of items that fake users have interacted with) into a target recommender system to achieve malicious purposes, such as promote or demote a set of target items.

Attribute Recommendation Systems

Cycle Encoding of a StyleGAN Encoder for Improved Reconstruction and Editability

1 code implementation19 Jul 2022 Xudong Mao, Liujuan Cao, Aurele T. Gnanha, Zhenguo Yang, Qing Li, Rongrong Ji

The recently proposed pivotal tuning model makes significant progress towards reconstruction and editability, by using a two-step approach that first inverts the input image into a latent code, called pivot code, and then alters the generator so that the input image can be accurately mapped into the pivot code.

Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarios

no code implementations4 Jul 2022 Xueying Zhan, Zeyu Dai, Qingzhong Wang, Qing Li, Haoyi Xiong, Dejing Dou, Antoni B. Chan

In this paper, we propose a sampling scheme, Monte-Carlo Pareto Optimization for Active Learning (POAL), which selects optimal subsets of unlabeled samples with fixed batch size from the unlabeled data pool.

Active Learning

Saliency Attack: Towards Imperceptible Black-box Adversarial Attack

1 code implementation4 Jun 2022 Zeyu Dai, Shengcai Liu, Ke Tang, Qing Li

In this paper, we propose to restrict the perturbations to a small salient region to generate adversarial examples that can hardly be perceived.

Adversarial Attack

Simultaneous Double Q-learning with Conservative Advantage Learning for Actor-Critic Methods

1 code implementation8 May 2022 Qing Li, Wengang Zhou, Zhenbo Lu, Houqiang Li

Actor-critic Reinforcement Learning (RL) algorithms have achieved impressive performance in continuous control tasks.

Continuous Control Q-Learning +1

Towards Sustainable Satellite Edge Computing

no code implementations10 Mar 2022 Qing Li, Shangguang Wang, Xiao Ma, Ao Zhou, Fangchun Yang

Recently, Low Earth Orbit (LEO) satellites experience rapid development and satellite edge computing emerges to address the limitation of bent-pipe architecture in existing satellite systems.

Earth Observation Edge-computing +1

An End-to-End Cascaded Image Deraining and Object Detection Neural Network

no code implementations23 Feb 2022 Kaige Wang, Tianming Wang, Jianchuang Qu, Huatao Jiang, Qing Li, Lin Chang

Firstly, the gap between the low-level vision task represented by rain removal and the high-level vision task represented by object detection is significant, and the low-level vision task can hardly contribute to the high-level vision task.

Object object-detection +2

Combining Intra-Risk and Contagion Risk for Enterprise Bankruptcy Prediction Using Graph Neural Networks

1 code implementation1 Feb 2022 Yu Zhao, Shaopeng Wei, Yu Guo, Qing Yang, Xingyan Chen, Qing Li, Fuzhen Zhuang, Ji Liu, Gang Kou

This study for the first time considers both types of risk and their joint effects in bankruptcy prediction.

Indicative Image Retrieval: Turning Blackbox Learning into Grey

no code implementations28 Jan 2022 Xulu Zhang, Zhenqun Yang, Hao Tian, Qing Li, XiaoYong Wei

In many applications, we need the matching evidence to be indicated rather than just have the ranked list (e. g., the locations of the target proteins/cells/lesions in medical images).

Image Retrieval Representation Learning +1

Conceptor Learning for Class Activation Mapping

no code implementations21 Jan 2022 Guangwu Qian, Zhen-Qun Yang, Xu-Lu Zhang, YaoWei Wang, Qing Li, Xiao-Yong Wei

Class Activation Mapping (CAM) has been widely adopted to generate saliency maps which provides visual explanations for deep neural networks (DNNs).


Stock Movement Prediction Based on Bi-typed Hybrid-relational Market Knowledge Graph via Dual Attention Networks

1 code implementation11 Jan 2022 Yu Zhao, Huaming Du, Ying Liu, Shaopeng Wei, Xingyan Chen, Fuzhen Zhuang, Qing Li, Ji Liu, Gang Kou

Stock Movement Prediction (SMP) aims at predicting listed companies' stock future price trend, which is a challenging task due to the volatile nature of financial markets.

Implicit Relations Stock Prediction

Learning Bi-typed Multi-relational Heterogeneous Graph via Dual Hierarchical Attention Networks

1 code implementation24 Dec 2021 Yu Zhao, Shaopeng Wei, Huaming Du, Xingyan Chen, Qing Li, Fuzhen Zhuang, Ji Liu, Gang Kou

To address this issue, we propose a novel Dual Hierarchical Attention Networks (DHAN) based on the bi-typed multi-relational heterogeneous graphs to learn comprehensive node representations with the intra-class and inter-class attention-based encoder under a hierarchical mechanism.

Graph Learning

Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text

no code implementations14 Dec 2021 Qing Li, Boqing Gong, Yin Cui, Dan Kondratyuk, Xianzhi Du, Ming-Hsuan Yang, Matthew Brown

The experiments show that the resultant unified foundation transformer works surprisingly well on both the vision-only and text-only tasks, and the proposed knowledge distillation and gradient masking strategy can effectively lift the performance to approach the level of separately-trained models.

Image Classification Knowledge Distillation +1

Self-Ensemling for 3D Point Cloud Domain Adaption

no code implementations10 Dec 2021 Qing Li, Xiaojiang Peng, Chuan Yan, Pan Gao, Qi Hao

In SEN, a student network is kept in a collaborative manner with supervised learning and self-supervised learning, and a teacher network conducts temporal consistency to learn useful representations and ensure the quality of point clouds reconstruction.

Autonomous Driving Self-Supervised Learning +1

Deep Keyphrase Completion

no code implementations29 Oct 2021 Yu Zhao, Jia Song, Huali Feng, Fuzhen Zhuang, Qing Li, Xiaojie Wang, Ji Liu

Keyphrase provides accurate information of document content that is highly compact, concise, full of meanings, and widely used for discourse comprehension, organization, and text retrieval.

Decoder Keyphrase Extraction +3

Towards General Deep Leakage in Federated Learning

no code implementations18 Oct 2021 Jiahui Geng, Yongli Mou, Feifei Li, Qing Li, Oya Beyan, Stefan Decker, Chunming Rong

We find that image restoration fails even if there is only one incorrectly inferred label in the batch; we also find that when batch images have the same label, the corresponding image is restored as a fusion of that class of images.

Federated Learning Image Restoration +1

Benchmark Problems for CEC2021 Competition on Evolutionary Transfer Multiobjectve Optimization

1 code implementation15 Oct 2021 Songbai Liu, Qiuzhen Lin, Kay Chen Tan, Qing Li

Evolutionary transfer multiobjective optimization (ETMO) has been becoming a hot research topic in the field of evolutionary computation, which is based on the fact that knowledge learning and transfer across the related optimization exercises can improve the efficiency of others.

Multiobjective Optimization Transfer Learning

SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing

3 code implementations ACL 2022 Junyi Ao, Rui Wang, Long Zhou, Chengyi Wang, Shuo Ren, Yu Wu, Shujie Liu, Tom Ko, Qing Li, Yu Zhang, Zhihua Wei, Yao Qian, Jinyu Li, Furu Wei

Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +8

Multi-View Self-Attention Based Transformer for Speaker Recognition

no code implementations11 Oct 2021 Rui Wang, Junyi Ao, Long Zhou, Shujie Liu, Zhihua Wei, Tom Ko, Qing Li, Yu Zhang

In this work, we propose a novel multi-view self-attention mechanism and present an empirical study of different Transformer variants with or without the proposed attention mechanism for speaker recognition.

Speaker Recognition

Imperceptible Black-box Attack via Refining in Salient Region

no code implementations29 Sep 2021 Zeyu Dai, Shengcai Liu, Ke Tang, Qing Li

To address this issue, in this paper we propose to use segmentation priors for black-box attacks such that the perturbations are limited in the salient region.

Stabilized Self-training with Negative Sampling on Few-labeled Graph Data

no code implementations29 Sep 2021 Ziang Zhou, Jieming Shi, Shengzhong Zhang, Zengfeng Huang, Qing Li

Therefore, we propose an effective framework, Stabilized self-training with Negative sampling (SN), which is applicable to existing GNNs to stabilize the training process and enhance the training data, and consequently, boost classification accuracy on graphs with few labeled data.

Benchmarking Node Classification

DM-CT: Consistency Training with Data and Model Perturbation

no code implementations29 Sep 2021 Xiaobo Liang, Runze Mao, Lijun Wu, Juntao Li, Weiqing Liu, Qing Li, Min Zhang

The common approach of consistency training is performed on the data-level, which typically utilizes the data augmentation strategy (or adversarial training) to make the predictions from the augmented input and the original input to be consistent, so that the model is more robust and attains better generalization ability.

Data Augmentation Image Classification +2

YouRefIt: Embodied Reference Understanding with Language and Gesture

no code implementations ICCV 2021 Yixin Chen, Qing Li, Deqian Kong, Yik Lun Kei, Song-Chun Zhu, Tao Gao, Yixin Zhu, Siyuan Huang

To the best of our knowledge, this is the first embodied reference dataset that allows us to study referring expressions in daily physical scenes to understand referential behavior, human communication, and human-robot interaction.

Graph Trend Filtering Networks for Recommendations

1 code implementation12 Aug 2021 Wenqi Fan, Xiaorui Liu, Wei Jin, Xiangyu Zhao, Jiliang Tang, Qing Li

The key of recommender systems is to predict how likely users will interact with items based on their historical online behaviors, e. g., clicks, add-to-cart, purchases, etc.

Collaborative Filtering Graph Representation Learning +1

DGEM: A New Dual-modal Graph Embedding Method in Recommendation System

no code implementations9 Aug 2021 Huimin Zhou, Qing Li, Yong Jiang, Rongwei Yang, Zhuyun Qi

In the current deep learning based recommendation system, the embedding method is generally employed to complete the conversion from the high-dimensional sparse feature vector to the low-dimensional dense feature vector.

Graph Embedding

Jointly Attacking Graph Neural Network and its Explanations

no code implementations7 Aug 2021 Wenqi Fan, Wei Jin, Xiaorui Liu, Han Xu, Xianfeng Tang, Suhang Wang, Qing Li, Jiliang Tang, JianPing Wang, Charu Aggarwal

Despite the great success, recent studies have shown that GNNs are highly vulnerable to adversarial attacks, where adversaries can mislead the GNNs' prediction by modifying graphs.

Graph Neural Network

Adversarial Learning with Mask Reconstruction for Text-Guided Image Inpainting

1 code implementation Conference 2021 Xingcai Wu, Yucheng Xie, Jiaqi Zeng, Zhenguo Yang, Yi Yu, Qing Li, and Wenyin Liu

In this paper, we propose an adversarial learning framework with mask reconstruction (ALMR) for image inpainting with textual guidance, which consists of a two-stage generator and dual discriminators.

Image Inpainting Sentence

Multiple-criteria Based Active Learning with Fixed-size Determinantal Point Processes

no code implementations4 Jul 2021 Xueying Zhan, Qing Li, Antoni B. Chan

In this paper, we introduce a multiple-criteria based active learning algorithm, which incorporates three complementary criteria, i. e., informativeness, representativeness and diversity, to make appropriate selections in the active learning rounds under different data types.

Active Learning Informativeness +1

Intent Disentanglement and Feature Self-supervision for Novel Recommendation

no code implementations28 Jun 2021 Tieyun Qian, Yile Liang, Qing Li, Xuan Ma, Ke Sun, Zhiyong Peng

Improving the recommendation of tail items can promote novelty and bring positive effects to both users and providers, and thus is a desirable property of recommender systems.

Disentanglement Recommendation Systems +1

Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering

no code implementations8 Mar 2021 Qing Li, Xiaojiang Peng, Yu Qiao, Qi Hao

The multi-label learning module leverages a memory feature bank and assigns each image with a multi-label vector based on the similarities between the image and feature bank.

Clustering Multi-Label Learning +2

A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics

no code implementations2 Mar 2021 Qing Li, Siyuan Huang, Yining Hong, Yixin Zhu, Ying Nian Wu, Song-Chun Zhu

We believe the HINT dataset and the experimental findings are of great interest to the learning community on systematic generalization.

Few-Shot Learning Program Synthesis +1

Tips and Tricks for Webly-Supervised Fine-Grained Recognition: Learning from the WebFG 2020 Challenge

no code implementations29 Dec 2020 Xiu-Shen Wei, Yu-Yan Xu, Yazhou Yao, Jia Wei, Si Xi, Wenyuan Xu, Weidong Zhang, Xiaoxin Lv, Dengpan Fu, Qing Li, Baoying Chen, Haojie Guo, Taolue Xue, Haipeng Jing, Zhiheng Wang, Tianming Zhang, Mingwen Zhang

WebFG 2020 is an international challenge hosted by Nanjing University of Science and Technology, University of Edinburgh, Nanjing University, The University of Adelaide, Waseda University, etc.

SMART: A Situation Model for Algebra Story Problems via Attributed Grammar

no code implementations27 Dec 2020 Yining Hong, Qing Li, Ran Gong, Daniel Ciao, Siyuan Huang, Song-Chun Zhu

Solving algebra story problems remains a challenging task in artificial intelligence, which requires a detailed understanding of real-world situations and a strong mathematical reasoning capability.

Math Mathematical Reasoning

Learning by Fixing: Solving Math Word Problems with Weak Supervision

1 code implementation19 Dec 2020 Yining Hong, Qing Li, Daniel Ciao, Siyuan Huang, Song-Chun Zhu

To generate more diverse solutions, \textit{tree regularization} is applied to guide the efficient shrinkage and exploration of the solution space, and a \textit{memory buffer} is designed to track and save the discovered various fixes for each problem.

 Ranked #1 on Math Word Problem Solving on Math23K (weakly-supervised metric)

Math Weakly-supervised Learning

Multi Scale Temporal Graph Networks For Skeleton-based Action Recognition

no code implementations5 Dec 2020 Tingwei Li, Ruiwen Zhang, Qing Li

To appropriately describe the relations between joints in the skeleton graph, we propose a multi-scale graph strategy, adopting a full-scale graph, part-scale graph, and core-scale graph to capture the local features of each joint and the contour features of important joints.

Action Recognition Skeleton Based Action Recognition

A Unified Sequence Labeling Model for Emotion Cause Pair Extraction

no code implementations COLING 2020 Xinhong Chen, Qing Li, JianPing Wang

Existing approaches address the task by first extracting emotion and cause clauses via two binary classifiers separately, and then training another binary classifier to pair them up.

Emotion-Cause Pair Extraction

Deep Learning based Monocular Depth Prediction: Datasets, Methods and Applications

no code implementations9 Nov 2020 Qing Li, Jiasong Zhu, Jun Liu, Rui Cao, Qingquan Li, Sen Jia, Guoping Qiu

Despite the rapid progress in this topic, there are lacking of a comprehensive review, which is needed to summarize the current progress and provide the future directions.

Depth Prediction Indoor Localization +2

Suppressing Mislabeled Data via Grouping and Self-Attention

1 code implementation ECCV 2020 Xiaojiang Peng, Kai Wang, Zhaoyang Zeng, Qing Li, Jianfei Yang, Yu Qiao

Specifically, this plug-and-play AFM first leverages a \textit{group-to-attend} module to construct groups and assign attention weights for group-wise samples, and then uses a \textit{mixup} module with the attention weights to interpolate massive noisy-suppressed samples.

Image Classification

MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization

no code implementations29 Sep 2020 Yangbin Chen, Yun Ma, Tom Ko, Jian-Ping Wang, Qing Li

MetaMix can be integrated with any of the MAML-based algorithms and learn the decision boundaries generalizing better to new tasks.

Few-Shot Learning Transfer Learning

Object-aware Multimodal Named Entity Recognition in Social Media Posts with Adversarial Learning

1 code implementation3 Aug 2020 Changmeng Zheng, Zhiwei Wu, Tao Wang, Cai Yi, Qing Li

To better exploit visual and textual information in NER, we propose an adversarial gated bilinear attention neural network (AGBAN).

named-entity-recognition Named Entity Recognition +1

Physical properties revealed by transport measurements on superconducting Nd$_{0.8}$Sr$_{0.2}$NiO$_{2}$ thin films

no code implementations9 Jul 2020 Ying Xiang, Qing Li, Yueying Li, Huan Yang, Yuefeng Nie, Hai-Hu Wen

The angle dependent resistivity at a fixed temperature and different magnetic fields cannot be scaled to one curve, which deviates from the prediction of the anisotropic Ginzburg-Landau theory.

Superconductivity Materials Science Strongly Correlated Electrons

Neural Mixed Counting Models for Dispersed Topic Discovery

no code implementations ACL 2020 Jiemin Wu, Yanghui Rao, Zusheng Zhang, Haoran Xie, Qing Li, Fu Lee Wang, Ziye Chen

Mixed counting models that use the negative binomial distribution as the prior can well model over-dispersed and hierarchically dependent random variables; thus they have attracted much attention in mining dispersed document topics.

Variational Inference