Search Results for author: Jian Wang

Found 219 papers, 66 papers with code

RealMedDial: A Real Telemedical Dialogue Dataset Collected from Online Chinese Short-Video Clips

no code implementations COLING 2022 Bo Xu, Hongtong Zhang, Jian Wang, Xiaokun Zhang, Dezhi Hao, Linlin Zong, Hongfei Lin, Fenglong Ma

We collected and annotated a wide range of meta-data with respect to medical dialogue including doctor profiles, hospital departments, diseases and symptoms for fine-grained analysis on language usage pattern and clinical diagnosis.

Response Generation

多特征融合的越英端到端语音翻译方法(A Vietnamese-English end-to-end speech translation method based on multi-feature fusion)

no code implementations CCL 2022 Houli Ma, Ling Dong, Wenjun Wang, Jian Wang, Shengxiang Gao, Zhengtao Yu

“语音翻译的编码器需要同时编码语音中的声学和语义信息, 单一的Fbank或Wav2vec2语音特征表征能力存在不足。本文通过分析人工的Fbank特征与自监督的Wav2vec2特征间的差异性, 提出基于交叉注意力机制的声学特征融合方法, 并探究了不同的自监督特征和融合方式, 加强模型对语音中声学和语义信息的学习。结合越南语语音特点, 以Fbank特征为主、Pitch特征为辅混合编码Fbank表征, 构建多特征融合的越-英语音翻译模型。实验表明, 使用多特征的语音翻译模型相比单特征翻译效果更优, 与简单的特征拼接方法相比更有效, 所提的多特征融合方法在越-英语音翻译任务上提升了1. 97个BLEU值。”

Application of Quantum Tensor Networks for Protein Classification

no code implementations11 Mar 2024 Debarshi Kundu, Archisman Ghosh, Srinivasan Ekambaram, Jian Wang, Nikolay Dokholyan, Swaroop Ghosh

We show that protein sequences can be thought of as sentences in natural language processing and can be parsed using the existing Quantum Natural Language framework into parameterized quantum circuits of reasonable qubits, which can be trained to solve various protein-related machine-learning problems.

Binary Classification Classification +2

Target-constrained Bidirectional Planning for Generation of Target-oriented Proactive Dialogue

1 code implementation10 Mar 2024 Jian Wang, Dongding Lin, Wenjie Li

Inspired by decision-making theories in cognitive science, we propose a novel target-constrained bidirectional planning (TRIP) approach, which plans an appropriate dialogue path by looking ahead and looking back.

Dialogue Generation

Thyroid ultrasound diagnosis improvement via multi-view self-supervised learning and two-stage pre-training

no code implementations18 Feb 2024 Jian Wang, Xin Yang, Xiaohong Jia, Wufeng Xue, Rusi Chen, Yanlin Chen, Xiliang Zhu, Lian Liu, Yan Cao, Jianqiao Zhou, Dong Ni, Ning Gu

In this study, we proposed a multi-view contrastive self-supervised method to improve thyroid nodule classification and segmentation performance with limited manual labels.

Classification Segmentation +1

Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue

no code implementations10 Feb 2024 Jian Wang, Chak Tou Leong, Jiashuo Wang, Dongding Lin, Wenjie Li, Xiao-Yong Wei

Tuning pretrained language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents.

Dialogue Generation

OrchMoE: Efficient Multi-Adapter Learning with Task-Skill Synergy

no code implementations19 Jan 2024 Haowen Wang, Tao Sun, Kaixiang Ji, Jian Wang, Cong Fan, Jinjie Gu

We advance the field of Parameter-Efficient Fine-Tuning (PEFT) with our novel multi-adapter method, OrchMoE, which capitalizes on modular skill architecture for enhanced forward transfer in neural networks.

Multi-Task Learning

Enhancing Automatic Modulation Recognition through Robust Global Feature Extraction

no code implementations2 Jan 2024 Yunpeng Qu, Zhilin Lu, Rui Zeng, Jintao Wang, Jian Wang

Modulated signals exhibit long temporal dependencies, and extracting global features is crucial in identifying modulation schemes.

Automatic Modulation Recognition Data Augmentation

Personalized Restoration via Dual-Pivot Tuning

no code implementations28 Dec 2023 Pradyumna Chari, Sizhuo Ma, Daniil Ostashev, Achuta Kadambi, Gurunandan Krishnan, Jian Wang, Kfir Aberman

This approach ensures that personalization does not interfere with the restoration process, resulting in a natural appearance with high fidelity to the person's identity and the attributes of the degraded image.

Image Restoration

COOPER: Coordinating Specialized Agents towards a Complex Dialogue Goal

1 code implementation19 Dec 2023 Yi Cheng, Wenge Liu, Jian Wang, Chak Tou Leong, Yi Ouyang, Wenjie Li, Xian Wu, Yefeng Zheng

In recent years, there has been a growing interest in exploring dialogues with more complex goals, such as negotiation, persuasion, and emotional support, which go beyond traditional service-focused dialogue systems.

Robust Communicative Multi-Agent Reinforcement Learning with Active Defense

no code implementations16 Dec 2023 Lebin Yu, Yunbo Qiu, Quanming Yao, Yuan Shen, Xudong Zhang, Jian Wang

We propose an active defense strategy, where agents automatically reduce the impact of potentially harmful messages on the final decision.

Multi-agent Reinforcement Learning reinforcement-learning

Towards 4D Human Video Stylization

1 code implementation7 Dec 2023 Tiantian Wang, Xinxin Zuo, Fangzhou Mu, Jian Wang, Ming-Hsuan Yang

To overcome these limitations, we leverage Neural Radiance Fields (NeRFs) to represent videos, conducting stylization in the rendered feature space.

Novel View Synthesis Style Transfer +1

Layered Rendering Diffusion Model for Zero-Shot Guided Image Synthesis

1 code implementation30 Nov 2023 Zipeng Qi, Guoxi Huang, Zebin Huang, Qin Guo, Jinwen Chen, Junyu Han, Jian Wang, Gang Zhang, Lufei Liu, Errui Ding, Jingdong Wang

The LRDiff framework constructs an image-rendering process with multiple layers, each of which applies the vision guidance to instructively estimate the denoising direction for a single object.

Denoising Image Generation

Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement

no code implementations28 Nov 2023 Jian Wang, Zhe Cao, Diogo Luvizon, Lingjie Liu, Kripasindhu Sarkar, Danhang Tang, Thabo Beeler, Christian Theobalt

In this work, we explore egocentric whole-body motion capture using a single fisheye camera, which simultaneously estimates human body and hand motion.

 Ranked #1 on Egocentric Pose Estimation on GlobalEgoMocap Test Dataset (using extra training data)

Egocentric Pose Estimation Hand Detection +2

Clearer Frames, Anytime: Resolving Velocity Ambiguity in Video Frame Interpolation

1 code implementation14 Nov 2023 Zhihang Zhong, Gurunandan Krishnan, Xiao Sun, Yu Qiao, Sizhuo Ma, Jian Wang

Existing video frame interpolation (VFI) methods blindly predict where each object is at a specific timestep t ("time indexing"), which struggles to predict precise object movements.

Object Video Editing +1

A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations

1 code implementation31 Oct 2023 Hui Ma, Jian Wang, Hongfei Lin, Bo Zhang, Yijia Zhang, Bo Xu

Emotion recognition in conversations (ERC), the task of recognizing the emotion of each utterance in a conversation, is crucial for building empathetic machines.

Multimodal Emotion Recognition

Self-Detoxifying Language Models via Toxification Reversal

1 code implementation14 Oct 2023 Chak Tou Leong, Yi Cheng, Jiashuo Wang, Jian Wang, Wenjie Li

Drawing on this idea, we devise a method to identify the toxification direction from the normal generation process to the one prompted with the negative prefix, and then steer the generation to the reversed direction by manipulating the information movement within the attention layers.

Language Modelling

Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curation

1 code implementation11 Oct 2023 Jian Wang, Yi Cheng, Dongding Lin, Chak Tou Leong, Wenjie Li

Target-oriented dialogue systems, designed to proactively steer conversations toward predefined targets or accomplish specific system-side goals, are an exciting area in conversational AI.

PatchProto Networks for Few-shot Visual Anomaly Classification

no code implementations7 Oct 2023 Jian Wang, Yue Zhuo

The visual anomaly diagnosis can automatically analyze the defective products, which has been widely applied in industrial quality inspection.

Anomaly Classification Classification +1

Segmented Harmonic Loss: Handling Class-Imbalanced Multi-Label Clinical Data for Medical Coding with Large Language Models

no code implementations6 Oct 2023 Surjya Ray, Pratik Mehta, Hongen Zhang, Ada Chaman, Jian Wang, Chung-Jen Ho, Michael Chiou, Tashfeen Suleman

In this paper, we gauge the extent of the impact by evaluating the performance of LLMs for the task of medical coding on real-life noisy data.

Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification

1 code implementation ICCV 2023 Zhiyin Shao, Xinyu Zhang, Changxing Ding, Jian Wang, Jingdong Wang

In this way, the pre-training task and the T2I-ReID task are made consistent with each other on both data and training levels.

Person Re-Identification

FFPN: Fourier Feature Pyramid Network for Ultrasound Image Segmentation

no code implementations26 Aug 2023 Chaoyu Chen, Xin Yang, Rusi Chen, Junxuan Yu, Liwei Du, Jian Wang, Xindi Hu, Yan Cao, Yingying Liu, Dong Ni

In this paper, we introduce a novel Fourier-anchor-based DTS framework called Fourier Feature Pyramid Network (FFPN) to address the aforementioned issues.

Image Segmentation Semantic Segmentation

Model predictive control strategy in waked wind farms for optimal fatigue loads

no code implementations25 Aug 2023 Cheng Zhong, Yicheng Ding, Husai Wang, Jikai Chen, Jian Wang, Yang Li

In this paper, a closed-loop model predictive controller is developed that minimizes the wind farm tracking errors, the dynamical fatigue load, and and the load equalization.

Model Predictive Control

Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation

2 code implementations ICCV 2023 Huan Liu, Qiang Chen, Zichang Tan, Jiang-Jiang Liu, Jian Wang, Xiangbo Su, Xiaolong Li, Kun Yao, Junyu Han, Errui Ding, Yao Zhao, Jingdong Wang

State-of-the-art solutions adopt the DETR-like framework, and mainly develop the complex decoder, e. g., regarding pose estimation as keypoint box detection and combining with human detection in ED-Pose, hierarchically predicting with pose decoder and joint (keypoint) decoder in PETR.

Human Detection Multi-Person Pose Estimation

ZRIGF: An Innovative Multimodal Framework for Zero-Resource Image-Grounded Dialogue Generation

1 code implementation1 Aug 2023 Bo Zhang, Jian Wang, Hui Ma, Bo Xu, Hongfei Lin

To overcome this challenge, we propose an innovative multimodal framework, called ZRIGF, which assimilates image-grounded information for dialogue generation in zero-resource situations.

Dialogue Generation Response Generation

Stroke Extraction of Chinese Character Based on Deep Structure Deformable Image Registration

1 code implementation10 Jul 2023 Meng Li, Yahan Yu, Yi Yang, Guanghao Ren, Jian Wang

In this paper, we propose a deep learning-based character stroke extraction method that takes semantic features and prior information of strokes into consideration.

Image Registration Semantic Segmentation

Image Harmonization with Diffusion Model

no code implementations17 Jun 2023 Jiajie Li, Jian Wang, Chen Wang, JinJun Xiong

In this paper, we present a novel approach for image harmonization by leveraging diffusion models.

Image Harmonization

Weakly Supervised Lesion Detection and Diagnosis for Breast Cancers with Partially Annotated Ultrasound Images

no code implementations12 Jun 2023 Jian Wang, Liang Qiao, Shichong Zhou, Jin Zhou, Jun Wang, Juncheng Li, Shihui Ying, Cai Chang, Jun Shi

To address this issue, a novel Two-Stage Detection and Diagnosis Network (TSDDNet) is proposed based on weakly supervised learning to enhance diagnostic accuracy of the ultrasound-based CAD for breast cancers.

Lesion Detection Weakly-supervised Learning

Fourier Test-time Adaptation with Multi-level Consistency for Robust Classification

no code implementations5 Jun 2023 Yuhao Huang, Xin Yang, Xiaoqiong Huang, Xinrui Zhou, Haozhe Chi, Haoran Dou, Xindi Hu, Jian Wang, Xuedong Deng, Dong Ni

Second, we introduce a regularization technique that utilizes style interpolation consistency in the frequency space to encourage self-consistency in the logit space of the model output.

Robust classification Test-time Adaptation

Medical Dialogue Generation via Dual Flow Modeling

1 code implementation29 May 2023 Kaishuai Xu, Wenjun Hou, Yi Cheng, Jian Wang, Wenjie Li

It extracts the medical entities and dialogue acts used in the dialogue history and models their transitions with an entity-centric graph flow and a sequential act flow, respectively.

Dialogue Generation Dialogue Understanding

Dialogue Planning via Brownian Bridge Stochastic Process for Goal-directed Proactive Dialogue

1 code implementation9 May 2023 Jian Wang, Dongding Lin, Wenjie Li

The key to achieving this task lies in planning dialogue paths that smoothly and coherently direct conversations towards the target.

Dialogue Generation

Exploring Effective Factors for Improving Visual In-Context Learning

1 code implementation10 Apr 2023 Yanpeng Sun, Qiang Chen, Jian Wang, Jingdong Wang, Zechao Li

By doing this, the model can leverage the diverse knowledge stored in different parts of the model to improve its performance on new tasks.

In-Context Learning Meta-Learning +1

Robust Calibrate Proxy Loss for Deep Metric Learning

no code implementations6 Apr 2023 Xinyue Li, Jian Wang, Wei Song, Yanling Du, Zhixiang Liu

The mainstream researche in deep metric learning can be divided into two genres: proxy-based and pair-based methods.

Metric Learning Retrieval

Learning to Recover Spectral Reflectance from RGB Images

1 code implementation4 Apr 2023 Dong Huo, Jian Wang, Yiming Qian, Yee-Hong Yang

Instead of relying on naive end-to-end training, we also propose a novel architecture that integrates the physical relationship between the spectral reflectance and the corresponding RGB images into the network based on our mathematical analysis.

Auxiliary Learning

MetaMorph: Learning Metamorphic Image Transformation With Appearance Changes

no code implementations8 Mar 2023 Jian Wang, Jiarui Xing, Jason Druzgal, William M. Wells III, Miaomiao Zhang

This paper presents a novel predictive model, MetaMorph, for metamorphic registration of images with appearance changes (i. e., caused by brain tumors).

Segmentation

Exploring Adversarial Attacks on Neural Networks: An Explainable Approach

1 code implementation8 Mar 2023 Justus Renkhoff, Wenkai Tan, Alvaro Velasquez, illiam Yichen Wang, Yongxin Liu, Jian Wang, Shuteng Niu, Lejla Begic Fazlic, Guido Dartmann, Houbing Song

Finally, we demonstrate that the layers $Block4\_conv1$ and $Block5\_cov1$ of the VGG-16 model are more susceptible to adversarial attacks.

Autonomous Driving

Temporal Segment Transformer for Action Segmentation

no code implementations25 Feb 2023 Zhichao Liu, Leshan Wang, Desen Zhou, Jian Wang, Songyang Zhang, Yang Bai, Errui Ding, Rui Fan

To deal with these issues, we propose an attention based approach which we call \textit{temporal segment transformer}, for joint segment relation modeling and denoising.

Action Segmentation Denoising +1

DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs

no code implementations23 Feb 2023 Zhixiang Wang, Yu-Lun Liu, Jia-Bin Huang, Shin'ichi Satoh, Sizhuo Ma, Gurunandan Krishnan, Jian Wang

Close-up facial images captured at short distances often suffer from perspective distortion, resulting in exaggerated facial features and unnatural/unattractive appearances.

Scheduling

Differentiable Rotamer Sampling with Molecular Force Fields

no code implementations22 Feb 2023 Congzhou M. Sha, Jian Wang, Nikolay V. Dokholyan

Molecular dynamics is the primary computational method by which modern structural biology explores macromolecule structure and function.

Low Entropy Communication in Multi-Agent Reinforcement Learning

no code implementations10 Feb 2023 Lebin Yu, Yunbo Qiu, Qiexiang Wang, Xudong Zhang, Jian Wang

Communication in multi-agent reinforcement learning has been drawing attention recently for its significant role in cooperation.

Multi-agent Reinforcement Learning reinforcement-learning +1

CSDR-BERT: a pre-trained scientific dataset match model for Chinese Scientific Dataset Retrieval

no code implementations30 Jan 2023 Xintao Chu, Jianping Liu, Jian Wang, XiaoFeng Wang, Yingfei Wang, Meng Wang, Xunxun Gu

As the number of open and shared scientific datasets on the Internet increases under the open science movement, efficiently retrieving these datasets is a crucial task in information retrieval (IR) research.

Information Retrieval Retrieval +2

Graph Contrastive Learning for Skeleton-based Action Recognition

1 code implementation26 Jan 2023 Xiaohu Huang, Hao Zhou, Jian Wang, Haocheng Feng, Junyu Han, Errui Ding, Jingdong Wang, Xinggang Wang, Wenyu Liu, Bin Feng

In this paper, we propose a graph contrastive learning framework for skeleton-based action recognition (\textit{SkeletonGCL}) to explore the \textit{global} context across all sequences.

Action Recognition Contrastive Learning +2

FE-TCM: Filter-Enhanced Transformer Click Model for Web Search

no code implementations19 Jan 2023 Yingfei Wang, Jianping Liu, Jian Wang, XiaoFeng Wang, Meng Wang, Xintao Chu

In this paper, We use Transformer as the backbone network of feature extraction, add filter layer innovatively, and propose a new Filter-Enhanced Transformer Click Model (FE-TCM) for web search.

Uncertainty-guided Learning for Improving Image Manipulation Detection

no code implementations ICCV 2023 Kaixiang Ji, Feng Chen, Xin Guo, Yadong Xu, Jian Wang, Jingdong Chen

Image manipulation detection (IMD) is of vital importance as faking images and spreading misinformation can be malicious and harm our daily life.

Image Manipulation Image Manipulation Detection +1

s-Adaptive Decoupled Prototype for Few-Shot Object Detection

no code implementations ICCV 2023 Jinhao Du, Shan Zhang, Qiang Chen, Haifeng Le, Yanpeng Sun, Yao Ni, Jian Wang, Bin He, Jingdong Wang

To provide precise information for the query image, the prototype is decoupled into task-specific ones, which provide tailored guidance for 'where to look' and 'what to look for', respectively.

Few-Shot Object Detection Meta-Learning +3

Scene-aware Egocentric 3D Human Pose Estimation

1 code implementation CVPR 2023 Jian Wang, Lingjie Liu, Weipeng Xu, Kripasindhu Sarkar, Diogo Luvizon, Christian Theobalt

To this end, we propose an egocentric depth estimation network to predict the scene depth map from a wide-view egocentric fisheye camera while mitigating the occlusion of the human body with a depth-inpainting network.

Ranked #3 on Egocentric Pose Estimation on GlobalEgoMocap Test Dataset (using extra training data)

Depth Estimation Egocentric Pose Estimation

COLA: Improving Conversational Recommender Systems by Collaborative Augmentation

no code implementations15 Dec 2022 Dongding Lin, Jian Wang, Wenjie Li

Inspired by collaborative filtering, we propose a collaborative augmentation (COLA) method to simultaneously improve both item representation learning and user preference modeling to address these issues.

CoLA Collaborative Filtering +2

WAIR-D: Wireless AI Research Dataset

no code implementations5 Dec 2022 Yourui Huangfu, Jian Wang, Shengchen Dai, Rong Li, Jun Wang, Chongwen Huang, Zhaoyang Zhang

The statistical data hinder the trained AI models from further fine-tuning for a specific scenario, and ray-tracing data with limited environments lower down the generalization capability of the trained AI models.

Intelligent Communication

Attention-based Class Activation Diffusion for Weakly-Supervised Semantic Segmentation

no code implementations20 Nov 2022 Jianqiang Huang, Jian Wang, Qianru Sun, Hanwang Zhang

An intuitive solution is ``coupling'' the CAM with the long-range attention matrix of visual transformers (ViT) We find that the direct ``coupling'', e. g., pixel-wise multiplication of attention and activation, achieves a more global coverage (on the foreground), but unfortunately goes with a great increase of false positives, i. e., background pixels are mistakenly included.

Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation

Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining

no code implementations arXiv 2022 Qiang Chen, Jian Wang, Chuchu Han, Shan Zhang, Zexian Li, Xiaokang Chen, Jiahui Chen, Xiaodi Wang, Shuming Han, Gang Zhang, Haocheng Feng, Kun Yao, Junyu Han, Errui Ding, Jingdong Wang

The training process consists of self-supervised pretraining and finetuning a ViT-Huge encoder on ImageNet-1K, pretraining the detector on Object365, and finally finetuning it on COCO.

Object object-detection +1

A survey on the development status and application prospects of knowledge graph in smart grids

no code implementations2 Nov 2022 Jian Wang, Xi Wang, Chaoqun Ma, Lei Kou

With the advent of the electric power big data era, semantic interoperability and interconnection of power data have received extensive attention.

Decision Making

Geo-SIC: Learning Deformable Geometric Shapes in Deep Image Classifiers

1 code implementation25 Oct 2022 Jian Wang, Miaomiao Zhang

We introduce a newly designed framework that (i) simultaneously derives features from both image and latent shape spaces with large intra-class variations; and (ii) gains increased model interpretability by allowing direct access to the underlying geometric features of image data.

Image Classification

Self-Supervised 2D/3D Registration for X-Ray to CT Image Fusion

no code implementations14 Oct 2022 Srikrishna Jaganathan, Maximilian Kukla, Jian Wang, Karthik Shetty, Andreas Maier

Deep Learning-based 2D/3D registration enables fast, robust, and accurate X-ray to CT image fusion when large annotated paired datasets are available for training.

Domain Adaptation

U-HRNet: Delving into Improving Semantic Representation of High Resolution Network for Dense Prediction

4 code implementations13 Oct 2022 Jian Wang, Xiang Long, Guowei Chen, Zewu Wu, Zeyu Chen, Errui Ding

Therefore, we designed a U-shaped High-Resolution Network (U-HRNet), which adds more stages after the feature map with strongest semantic representation and relaxes the constraint in HRNet that all resolutions need to be calculated parallel for a newly added stage.

Depth Estimation Depth Prediction +1

Beam Management in Ultra-dense mmWave Network via Federated Reinforcement Learning: An Intelligent and Secure Approach

no code implementations4 Oct 2022 Qing Xue, Yi-Jing Liu, Yao Sun, Jian Wang, Li Yan, Gang Feng, Shaodan Ma

Deploying ultra-dense networks that operate on millimeter wave (mmWave) band is a promising way to address the tremendous growth on mobile data traffic.

Federated Learning Management

Design of the PID temperature controller for an alkaline electrolysis system with time delays

no code implementations3 Oct 2022 Ruomei Qi, Jiarong Li, Jin Lin, Yonghua Song, Jiepeng Wang, Qiangqiang Cui, Yiwei Qiu, Ming Tang, Jian Wang

This paper focuses on the design of the PID temperature controller for an alkaline electrolysis system to achieve fast and stable temperature control.

Sub-optimal Policy Aided Multi-Agent Reinforcement Learning for Flocking Control

no code implementations17 Sep 2022 Yunbo Qiu, Yue Jin, Jian Wang, Xudong Zhang

Flocking control is a challenging problem, where multiple agents, such as drones or vehicles, need to reach a target position while maintaining the flock and avoiding collisions with obstacles and collisions among agents in the environment.

Multi-agent Reinforcement Learning reinforcement-learning +2

Part-aware Prototypical Graph Network for One-shot Skeleton-based Action Recognition

no code implementations19 Aug 2022 Tailin Chen, Desen Zhou, Jian Wang, Shidong Wang, Qian He, Chuanyang Hu, Errui Ding, Yu Guan, Xuming He

In this paper, we study the problem of one-shot skeleton-based action recognition, which poses unique challenges in learning transferable representation from base classes to novel classes, particularly for fine-grained actions.

Action Recognition Meta-Learning +1

Multilayer Fisher extreme learning machine for classification

no code implementations Complex & Intelligent Systems 2022 Jie Lai, Xiaodan Wang, Qian Xiang, Jian Wang, Lei Lei

To address this problem, a novel Fisher extreme learning machine autoencoder (FELM-AE) is proposed and is used as the component for the multilayer Fisher extreme leaning machine (ML-FELM).

Classification Denoising +1

IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation

no code implementations6 Aug 2022 Zhongwei Qiu, Qiansheng Yang, Jian Wang, Dongmei Fu

In particular, we firstly formulate video frames as a series of instance-guided tokens and each token is in charge of predicting the 3D pose of a human instance.

Ranked #10 on 3D Multi-Person Pose Estimation on Panoptic (using extra training data)

2D Pose Estimation 3D Multi-Person Pose Estimation +1

Follow Me: Conversation Planning for Target-driven Recommendation Dialogue Systems

1 code implementation6 Aug 2022 Jian Wang, Dongding Lin, Wenjie Li

Recommendation dialogue systems aim to build social bonds with users and provide high-quality recommendations.

Dialogue Generation

Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment

2 code implementations ICCV 2023 Qiang Chen, Xiaokang Chen, Jian Wang, Shan Zhang, Kun Yao, Haocheng Feng, Junyu Han, Errui Ding, Gang Zeng, Jingdong Wang

Detection transformer (DETR) relies on one-to-one assignment, assigning one ground-truth object to one prediction, for end-to-end detection without NMS post-processing.

Data Augmentation Object +2

Action Quality Assessment with Temporal Parsing Transformer

1 code implementation19 Jul 2022 Yang Bai, Desen Zhou, Songyang Zhang, Jian Wang, Errui Ding, Yu Guan, Yang Long, Jingdong Wang

Action Quality Assessment(AQA) is important for action understanding and resolving the task poses unique challenges due to subtle visual differences.

Action Quality Assessment Action Understanding +1

Learning Granularity-Unified Representations for Text-to-Image Person Re-identification

2 code implementations16 Jul 2022 Zhiyin Shao, Xinyu Zhang, Meng Fang, Zhifeng Lin, Jian Wang, Changxing Ding

In PGU, we adopt a set of shared and learnable prototypes as the queries to extract diverse and semantically aligned features for both modalities in the granularity-unified feature space, which further promotes the ReID performance.

Person Re-Identification Text based Person Retrieval +1

Privacy-preserving household load forecasting based on non-intrusive load monitoring: A federated deep learning approach

no code implementations30 Jun 2022 Xinxin Zhou, Jingru Feng, Jian Wang, Jianhong Pan

In this method, the integrated power is decomposed into individual device power by non-intrusive load monitoring, and the power of individual appliances is predicted separately using a federated deep learning model.

Federated Learning Load Forecasting +2

MME-CRS: Multi-Metric Evaluation Based on Correlation Re-Scaling for Evaluating Open-Domain Dialogue

no code implementations19 Jun 2022 Pengfei Zhang, Xiaohui Hu, Kaidong Yu, Jian Wang, Song Han, Cao Liu, Chunyang Yuan

Firstly, we build an evaluation metric composed of 5 groups of parallel sub-metrics called Multi-Metric Evaluation (MME) to evaluate the quality of dialogue comprehensively.

Dialogue Evaluation

Structured Light with Redundancy Codes

no code implementations18 Jun 2022 Zhanghao Sun, Yu Zhang, Yicheng Wu, Dong Huo, Yiming Qian, Jian Wang

We propose three applications using our redundancy codes: (1) Self error-correction for SL imaging under strong ambient light, (2) Error detection for adaptive reconstruction under global illumination, and (3) Interference filtering with device-specific projection sequence encoding, especially for event camera-based SL and light curtain devices.

Object Scan Context: Object-centric Spatial Descriptor for Place Recognition within 3D Point Cloud Map

no code implementations7 Jun 2022 Haodong Yuan, Yudong Zhang, Shengyin Fan, Xue Li, Jian Wang

The integration of a SLAM algorithm with place recognition technology empowers it with the ability to mitigate accumulated errors and to relocalize itself.

Object

One-to-N & N-to-One: Two Advanced Backdoor Attacks Against Deep Learning Models

no code implementations IEEE Transactions on Dependable and Secure Computing 2022 Mingfu Xue, Can He, Jian Wang, and Weiqiang Liu

In this article, for the first time, we propose two advanced backdoor attacks, the multi-target backdoor attacks and multi-trigger backdoor attacks: 1) One-to-N attack, where the attacker can trigger multiple backdoor targets by controlling the different intensities of the same backdoor; 2) N-to-One attack, where such attack is triggered only when all the N backdoors are satisfied.

Face Recognition

Human-Object Interaction Detection via Disentangled Transformer

no code implementations CVPR 2022 Desen Zhou, Zhichao Liu, Jian Wang, Leshan Wang, Tao Hu, Errui Ding, Jingdong Wang

To associate the predictions of disentangled decoders, we first generate a unified representation for HOI triplets with a base decoder, and then utilize it as input feature of each disentangled decoder.

Human-Object Interaction Detection Object

Implicit Sample Extension for Unsupervised Person Re-Identification

1 code implementation CVPR 2022 Xinyu Zhang, Dongdong Li, Zhigang Wang, Jian Wang, Errui Ding, Javen Qinfeng Shi, Zhaoxiang Zhang, Jingdong Wang

Specifically, we generate support samples from actual samples and their neighbouring clusters in the embedding space through a progressive linear interpolation (PLI) strategy.

Clustering Unsupervised Person Re-Identification

Glass Segmentation with RGB-Thermal Image Pairs

1 code implementation12 Apr 2022 Dong Huo, Jian Wang, Yiming Qian, Yee-Hong Yang

Due to the large difference between the transmission property of visible light and that of the thermal energy through the glass where most glass is transparent to the visible light but opaque to thermal energy, glass regions of a scene are made more distinguishable with a pair of RGB and thermal images than solely with an RGB image.

Segmentation Thermal Image Segmentation

NPC: Neuron Path Coverage via Characterizing Decision Logic of Deep Neural Networks

no code implementations24 Mar 2022 Xiaofei Xie, Tianlin Li, Jian Wang, Lei Ma, Qing Guo, Felix Juefei-Xu, Yang Liu

Inspired by software testing, a number of structural coverage criteria are designed and proposed to measure the test adequacy of DNNs.

Defect Detection DNN Testing +1

Exploiting Pairwise Mutual Information for Knowledge-Grounded Dialogue

1 code implementation IEEE/ACM Transactions on Audio, Speech, and Language Processing 2022 Bo Zhang, Jian Wang, Hongfei Lin, Hui Ma, Bo Xu

Correlation integration is designed to fully exploit the pairwise mutual information among dialogue context, knowledge, and responses, while overall integration adopts an integration gate to capture global information.

Dialogue Generation

Hierarchical Memory Learning for Fine-Grained Scene Graph Generation

no code implementations14 Mar 2022 Youming Deng, Yansheng Li, Yongjun Zhang, Xiang Xiang, Jian Wang, Jingdong Chen, Jiayi Ma

After the autonomous partition of coarse and fine predicates, the model is first trained on the coarse predicates and then learns the fine predicates.

Graph Generation Scene Graph Generation

Image Steganography based on Style Transfer

no code implementations9 Mar 2022 Donghui Hu, Yu Zhang, Cong Yu, Jian Wang, Yaofei Wang

Image steganography is the art and science of using images as cover for covert communications.

Image Steganography Image Stylization +1

Thermal Modelling and Controller Design of an Alkaline Electrolysis System under Dynamic Operating Conditions

no code implementations27 Feb 2022 Ruomei Qi, Jiarong Li, Jin Lin, Yonghua Song, Jiepeng Wang, Qiangqiang Cui, Yiwei Qiu, Ming Tang, Jian Wang

A control-oriented thermal model is established in the form of a third-order time-delay process, which is used for simulation and controller design.

Management

Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision

no code implementations CVPR 2022 Jian Wang, Lingjie Liu, Weipeng Xu, Kripasindhu Sarkar, Diogo Luvizon, Christian Theobalt

Specifically, we first generate pseudo labels for the EgoPW dataset with a spatio-temporal optimization method by incorporating the external-view supervision.

Ranked #4 on Egocentric Pose Estimation on GlobalEgoMocap Test Dataset (using extra training data)

Egocentric Pose Estimation

An Adaptive Neuro-Fuzzy System with Integrated Feature Selection and Rule Extraction for High-Dimensional Classification Problems

no code implementations10 Jan 2022 Guangdong Xue, Qin Chang, Jian Wang, Kai Zhang, Nikhil R. Pal

The effectiveness of the FSRE-AdaTSK is demonstrated on 19 datasets of which five are in more than 2000 dimension including two with dimension greater than 7000.

feature selection

Training Object Detectors From Scratch: An Empirical Study in the Era of Vision Transformer

no code implementations CVPR 2022 Weixiang Hong, Jiangwei Lao, Wang Ren, Jian Wang, Jingdong Chen, Wei Chu

Instead of proposing a specific vision transformer based detector, in this work, our goal is to reveal the insights of training vision transformer based detectors from scratch.

object-detection Object Detection +1

Hybrid Atlas Building with Deep Registration Priors

no code implementations13 Dec 2021 Nian Wu, Jian Wang, Miaomiao Zhang, Guixu Zhang, Yaxin Peng, Chaomin Shen

Registration-based atlas building often poses computational challenges in high-dimensional image spaces.

MFNet: Multi-filter Directive Network for Weakly Supervised Salient Object Detection

1 code implementation ICCV 2021 Yongri Piao, Jian Wang, Miao Zhang, Huchuan Lu

The multiple accurate cues from multiple DFs are then simultaneously propagated to the saliency network with a multi-guidance loss.

object-detection Object Detection +2

Image-Guided Navigation of a Robotic Ultrasound Probe for Autonomous Spinal Sonography Using a Shadow-aware Dual-Agent Framework

no code implementations3 Nov 2021 Keyu Li, Yangxin Xu, Jian Wang, Dong Ni, Li Liu, Max Q. -H. Meng

Ultrasound (US) imaging is commonly used to assist in the diagnosis and interventions of spine diseases, while the standardized US acquisitions performed by manually operating the probe require substantial experience and training of sonographers.

Anatomy Decision Making +2

URIR: Recommendation algorithm of user RNN encoder and item encoder based on knowledge graph

no code implementations1 Nov 2021 Na Zhao, Zhen Long, Zhi-Dan Zhao, Jian Wang

This implies that URIR can effectively use knowledge graph to obtain better user codes and item codes, thereby obtaining better recommendation results.

Knowledge Graphs Recommendation Systems

One-Bit Matrix Completion with Differential Privacy

no code implementations2 Oct 2021 Zhengpin Li, Zheng Wei, Zengfeng Huang, Xiaojun Mao, Jian Wang

In this paper, we propose a unified framework for ensuring a strong privacy guarantee of one-bit matrix completion with DP.

Collaborative Filtering Matrix Completion +2

Applying Differential Privacy to Tensor Completion

no code implementations1 Oct 2021 Zheng Wei, Zhengpin Li, Xiaojun Mao, Jian Wang

Tensor completion aims at filling the missing or unobserved entries based on partially observed tensors.

Tensor Decomposition

SAM: A Self-adaptive Attention Module for Context-Aware Recommendation System

no code implementations1 Oct 2021 Jiabin Liu, Zheng Wei, Zhengpin Li, Xiaojun Mao, Jian Wang, Zhongyu Wei, Qi Zhang

In this work, we propose a novel and general self-adaptive module, the Self-adaptive Attention Module (SAM), which adjusts the selection bias by capturing contextual information based on its representation.

Recommendation Systems Representation Learning +1

To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection

no code implementations4 Sep 2021 Yongri Piao, Jian Wang, Miao Zhang, Zhengxuan Ma, Huchuan Lu

Despite of the success of previous works, explorations on an effective training strategy for the saliency network and accurate matches between image-level annotations and salient objects are still inadequate.

object-detection Object Detection +2

Mining Contextual Information Beyond Image for Semantic Segmentation

1 code implementation ICCV 2021 Zhenchao Jin, Tao Gong, Dongdong Yu, Qi Chu, Jian Wang, Changhu Wang, Jie Shao

To address this, this paper proposes to mine the contextual information beyond individual images to further augment the pixel representations.

Image Segmentation Segmentation +1

Learning to Detect: A Data-driven Approach for Network Intrusion Detection

no code implementations18 Aug 2021 Zachary Tauscher, Yushan Jiang, Kai Zhang, Jian Wang, Houbing Song

With massive data being generated daily and the ever-increasing interconnectivity of the world's Internet infrastructures, a machine learning based intrusion detection system (IDS) has become a vital component to protect our economic and national security.

Network Intrusion Detection Representation Learning

Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition

1 code implementation10 Aug 2021 Tailin Chen, Desen Zhou, Jian Wang, Shidong Wang, Yu Guan, Xuming He, Errui Ding

The task of skeleton-based action recognition remains a core challenge in human-centred scene understanding due to the multiple granularities and large variation in human motion.

Action Classification Action Recognition +2

Distributed Learning for Time-varying Networks: A Scalable Design

no code implementations31 Jul 2021 Jian Wang, Yourui Huangfu, Rong Li, Yiqun Ge, Jun Wang

The wireless network is undergoing a trend from "onnection of things" to "connection of intelligence".

Federated Learning

A Novel Interactive Two-stage Joint Retail Electricity Market for Multiple Microgrids

no code implementations27 Jul 2021 Chunyi Huang, Mingzhi Zhang, Chengmin Wang, Ning Xie, Jian Wang, Shi Peng

To accommodate the advent of microgrids (MG) managing distributed energy resources (DER) in distribution systems, an interactive two-stage joint retail electricity market mechanism is proposed to provide an effective platform for these prosumers to proactively join in retail transactions.

energy trading

Deep Iterative 2D/3D Registration

no code implementations21 Jul 2021 Srikrishna Jaganathan, Jian Wang, Anja Borsdorf, Karthik Shetty, Andreas Maier

A refinement step using the classical optimization-based 2D/3D registration method applied in combination with Deep Learning-based techniques can provide the required accuracy.

Optical Flow Estimation

Bayesian Atlas Building with Hierarchical Priors for Subject-specific Regularization

1 code implementation12 Jul 2021 Jian Wang, Miaomiao Zhang

This paper presents a novel hierarchical Bayesian model for unbiased atlas building with subject-specific regularizations of image registration.

Image Registration

Seeing in Extra Darkness Using a Deep-Red Flash

no code implementations CVPR 2021 Jinhui Xiong, Jian Wang, Wolfgang Heidrich, Shree Nayar

We propose a new flash technique for low-light imaging, using deep-red light as an illuminating source.

Video Reconstruction

Detect and remove watermark in deep neural networks via generative adversarial networks

no code implementations15 Jun 2021 Haoqi Wang, Mingfu Xue, Shichang Sun, Yushu Zhang, Jian Wang, Weiqiang Liu

Experimental evaluations on the MNIST and CIFAR10 datasets demonstrate that, the proposed method can effectively remove about 98% of the watermark in DNN models, as the watermark retention rate reduces from 100% to less than 2% after applying the proposed attack.

Detecting Backdoor in Deep Neural Networks via Intentional Adversarial Perturbations

no code implementations29 May 2021 Mingfu Xue, Yinghao Wu, Zhiyu Wu, Yushu Zhang, Jian Wang, Weiqiang Liu

Experimental results show that, the backdoor detection rate of the proposed defense method is 99. 63%, 99. 76% and 99. 91% on Fashion-MNIST, CIFAR-10 and GTSRB datasets, respectively.

Backdoor Attack

AdvParams: An Active DNN Intellectual Property Protection Technique via Adversarial Perturbation Based Parameter Encryption

no code implementations28 May 2021 Mingfu Xue, Zhiyu Wu, Jian Wang, Yushu Zhang, Weiqiang Liu

Moreover, the proposed method only needs to encrypt an extremely low number of parameters, and the proportion of the encrypted parameters of all the model's parameters is as low as 0. 000205%.

One Shot Face Swapping on Megapixels

1 code implementation CVPR 2021 Yuhao Zhu, Qi Li, Jian Wang, Chengzhong Xu, Zhenan Sun

Extensive experiments demonstrate the superiority of MegaFS and the first megapixel level face swapping database is released for research on DeepFake detection and face image editing in the public domain.

DeepFake Detection Disentanglement +2

Class-Incremental Learning for Wireless Device Identification in IoT

1 code implementation8 May 2021 Yongxin Liu, Jian Wang, Jianqiang Li, Shuteng Niu, Houbing Song

The proposed framework has the potential to be applied to accurate identification of IoT devices in a variety of IoT applications and services.

Class Incremental Learning Incremental Learning

Estimating Egocentric 3D Human Pose in Global Space

1 code implementation ICCV 2021 Jian Wang, Lingjie Liu, Weipeng Xu, Kripasindhu Sarkar, Christian Theobalt

Furthermore, these methods suffer from limited accuracy and temporal instability due to ambiguities caused by the monocular setup and the severe occlusion in a strongly distorted egocentric perspective.

Ranked #4 on Egocentric Pose Estimation on SceneEgo (using extra training data)

Egocentric Pose Estimation

Unsupervised Multi-Source Domain Adaptation for Person Re-Identification

1 code implementation CVPR 2021 Zechen Bai, Zhigang Wang, Jian Wang, Di Hu, Errui Ding

Although achieving great success, most of them only use limited data from a single-source domain for model pre-training, making the rich labeled data insufficiently exploited.

Person Re-Identification Unsupervised Domain Adaptation

Protecting the Intellectual Properties of Deep Neural Networks with an Additional Class and Steganographic Images

no code implementations19 Apr 2021 Shichang Sun, Mingfu Xue, Jian Wang, Weiqiang Liu

To address these challenges, in this paper, we propose a method to protect the intellectual properties of DNN models by using an additional class and steganographic images.

Image Steganography Management

XCloud-pFISTA: A Medical Intelligence Cloud for Accelerated MRI

no code implementations18 Apr 2021 Yirong Zhou, Chen Qian, Yi Guo, Zi Wang, Jian Wang, Biao Qu, Di Guo, Yongfu You, Xiaobo Qu

Machine learning and artificial intelligence have shown remarkable performance in accelerated magnetic resonance imaging (MRI).

Cloud Computing Image Reconstruction

Robust Backdoor Attacks against Deep Neural Networks in Real Physical World

no code implementations15 Apr 2021 Mingfu Xue, Can He, Shichang Sun, Jian Wang, Weiqiang Liu

In this paper, we propose a robust physical backdoor attack method, PTB (physical transformations for backdoors), to implement the backdoor attacks against deep learning models in the real physical world.

Backdoor Attack Face Recognition

Robust Reinforcement Learning under model misspecification

1 code implementation29 Mar 2021 Lebin Yu, Jian Wang, Xudong Zhang

Reinforcement learning has achieved remarkable performance in a wide range of tasks these days.

Adversarial Attack reinforcement-learning +1

Smart Scheduling based on Deep Reinforcement Learning for Cellular Networks

no code implementations22 Mar 2021 Jian Wang, Chen Xu, Rong Li, Yiqun Ge, Jun Wang

We not only verify the performance gain achieved, but also provide implementation-friend designs, i. e., a scalable neural network design for the agent and a virtual environment training framework.

Fairness Management +3

ActiveGuard: An Active DNN IP Protection Technique via Adversarial Examples

no code implementations2 Mar 2021 Mingfu Xue, Shichang Sun, Can He, Yushu Zhang, Jian Wang, Weiqiang Liu

For ownership verification, the embedded watermark can be successfully extracted, while the normal performance of the DNN model will not be affected.

Management

Learning the Update Operator for 2D/3D Image Registration

no code implementations4 Feb 2021 Srikrishna Jaganathan, Jian Wang, Anja Borsdorf, Andreas Maier

We aim to address this gap by incorporating traditional methods in deep neural networks using known operator learning.

Computational Efficiency Image Registration +1

Incentive-based Decentralized Routing for Connected and Autonomous Vehicles using Information Propagation

no code implementations1 Feb 2021 Chaojie Wang, Srinivas Peeta, Jian Wang

The first stage incorporates a decentralized local route switching dynamical system to approximate the system optimal route flow in a local area based on vehicles' knowledge of local traffic information.

Autonomous Vehicles Physics and Society Computer Science and Game Theory Systems and Control Systems and Control

Two-sided Dirichlet heat estimates of symmetric stable processes on horn-shaped regions

no code implementations29 Jan 2021 Xin Chen, Panki Kim, Jian Wang

In this paper, we consider symmetric $\alpha$-stable processes on (unbounded) horn-shaped regions which are non-uniformly $C^{1, 1}$ near infinity.

Probability

Machine Learning for the Detection and Identification of Internet of Things (IoT) Devices: A Survey

no code implementations25 Jan 2021 Yongxin Liu, Jian Wang, Jianqiang Li, Shuteng Niu, Houbing Song

In this paper, we provide a comprehensive survey on machine learning technologies for the identification of IoT devices along with the detection of compromised or falsified ones from the viewpoint of passive surveillance agents or network operators.

Anomaly Detection BIG-bench Machine Learning +2

Systematic electrochemical etching of various metal tips for tunneling spectroscopy and scanning probe microscopy

no code implementations18 Jan 2021 Jiawei Zhang, Pinyuan Wang, Xuao Zhang, Haoran Ji, Jiawei Luo, He Wang, Jian Wang

To ensure the reproducibility of experimental results, the fabrication of tips should be standardized, and a controllable and convenient system should be set up.

Materials Science

Run Away From your Teacher: a New Self-Supervised Approach Solving the Puzzle of BYOL

no code implementations1 Jan 2021 Haizhou Shi, Dongliang Luo, Siliang Tang, Jian Wang, Yueting Zhuang

Recently, a newly proposed self-supervised framework Bootstrap Your Own Latent (BYOL) seriously challenges the necessity of negative samples in contrastive-based learning frameworks.

Self-Supervised Learning

Detection of magnetic gap in the topological surface states of MnBi2Te4

no code implementations31 Dec 2020 Haoran Ji, Yanzhao Liu, He Wang, Jiawei Luo, Jiaheng Li, Hao Li, Yang Wu, Yong Xu, Jian Wang

An essential ingredient to realize these quantum states is the magnetic gap in the topological surface states induced by the out-of-plane ferromagnetism on the surface of MnBi2Te4.

Materials Science

Distant Domain Transfer Learning for Medical Imaging

no code implementations10 Dec 2020 Shuteng Niu, Meryl Liu, Yongxin Liu, Jian Wang, Houbing Song

In this paper, we propose a distant domain transfer learning (DDTL) method for medical image classification.

Computed Tomography (CT) COVID-19 Diagnosis +5

Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems

1 code implementation COLING 2020 Jian Wang, Junhao Liu, Wei Bi, Xiaojiang Liu, Kejing He, Ruifeng Xu, Min Yang

To conquer these limitations, we propose a Dual Dynamic Memory Network (DDMN) for multi-turn dialog generation, which maintains two core components: dialog memory manager and KB memory manager.

Group Contextual Encoding for 3D Point Clouds

1 code implementation NeurIPS 2020 Xu Liu, Chengtao Li, Jian Wang, Jingbo Wang, Boxin Shi, Xiaodong He

In this work, we extended the contextual encoding layer that was originally designed for 2D tasks to 3D Point Cloud scenarios.

Scene Understanding

Deep Learning for Regularization Prediction in Diffeomorphic Image Registration

no code implementations28 Nov 2020 Jian Wang, Miaomiao Zhang

This paper presents a predictive model for estimating regularization parameters of diffeomorphic image registration.

Image Registration

NaturalAE: Natural and Robust Physical Adversarial Examples for Object Detectors

no code implementations27 Nov 2020 Mingfu Xue, Chengxiang Yuan, Can He, Jian Wang, Weiqiang Liu

Experimental results demonstrate that, the generated adversarial examples are robust under various indoor and outdoor physical conditions, including different distances, angles, illuminations, and photographing.

Adversarial Attack