Zhiwei Jiang

Zhiwei Jiang

Auto-generated profile, based on publicly available information

Zhiwei Jiang

State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 January 2024 in IEEE Communications Surveys & Tutorials
Verified
Journal Article
Closed access
YYYafeng Yin
Yafeng Yin
LXLei Xie
Lei Xie
ZJZhiwei Jiang
Zhiwei Jiang
FXFu Xiao
Fu Xiao
JCJiannong Cao
Jiannong Cao
SLSanglu Lu
Sanglu Lu
Due to the ever-growing powers in sensing, computing, communicating and storing, mobile devices (e.g., smartphone, smartwatch, smart glasses) become ubiquitous and an indispensable part of people’s daily life. Until now, mobile devices have been adopted in many applications, e.g., exercise assessment, daily life monitoring, human-computer interactions, user authentication, etc. Among the various applications, Human Activity Recognition (HAR) is the core technology behind them. Specifically, HAR gets the sensor data corresponding to human activities based on the built-in sensors of mobile devices, and then adopts suitable recognition approaches to infer the type of activity based on sensor data. The last two decades have witnessed the ever-increasing research in HAR. However, new challenges and opportunities are emerging, especially for HAR based on mobile devices. Therefore, in this paper, we review the research of HAR based on mobile devices, aiming to advance the following research in this area. Firstly, we give an overview of HAR based on mobile devices, including the general rationales, main components and challenges. Secondly, we review and analyze the research progress of HAR based on mobile devices from each main aspect, including human activities, sensor data, data preprocessing, recognition approaches, evaluation standards and application cases. Finally, we present some promising trends in HAR based on mobile devices for future research.

11 August 2021 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
ZCZifeng Cheng
Zifeng Cheng
ZJZhiwei Jiang
Zhiwei Jiang
YYYafeng Yin
Yafeng Yin
NLNa Li
Na Li
QGQing Gu
Qing Gu
Emotion-cause pair extraction is a recently proposed task that aims at extracting all potential clause-level pairs of emotion and cause in text. To solve this task, researchers first proposed a two-step pipeline method. This method extracts the emotions and causes individually in the first step, then pairs the extracted emotions and causes and filters the invalid emotion-cause pairs in the second step. Due to that the two-step method has the error accumulation problem and is hard to be optimized jointly, several one-step end-to-end models have been proposed. These models share a similar underlying idea, that is, reframing the emotion-cause pair extraction task as a classification problem of candidate clause pairs. Unlike these models, in this paper, we reframe the emotion-cause pair extraction task as a unified sequence labeling problem, which allows to extract emotion-cause pairs through one pass of sequence labeling. This is realized by designing a special set of unified labels. In the unified label, we design a content part for emotion/cause identification and a pairing part for clause pairing. Then the emotion-cause pairs can be implicitly derived from the unified labels. To address this unified sequence labeling problem, we propose a unified target-oriented sequence-to-sequence model, which comprehensively utilizes the information of target clause, global context, and former decoded label, to perform end-to-end unified sequence labeling. The experimental results demonstrate the effectiveness of both our proposed unified sequence labeling scheme and unified target-oriented sequence-to-sequence model. All the code and data of this work can be obtained at https://github.com/zifengcheng/UTOS.

8 April 2023 in ACM Transactions on Information Systems
Verified
Journal Article
Open access
ZCZifeng Cheng
Zifeng Cheng
ZJZhiwei Jiang
Zhiwei Jiang
YYYafeng Yin
Yafeng Yin
CWCong Wang
Cong Wang
SGShiping Ge
Shiping Ge
QGQing Gu
Qing Gu
Emotion-cause pair extraction (ECPE) is a recently proposed task that aims to extract the potential clause pairs of emotions and its corresponding causes in a document. In this article, we propose a new paradigm for the ECPE task. We cast the task as a two-turn machine reading comprehension (MRC) task, i.e., the extraction of emotions and causes is transformed to the task of identifying answer clauses from the input document specific to a query. This two-turn MRC formalization brings several key advantages: First, the QA manner provides an explicit pairing way to identify causes specific to the target emotion; second, it provides a natural way of jointly modeling the emotion extraction, the cause extraction, and the pairing of emotion and cause; and third, it allows us to exploit the well-developed MRC models. Based on the two-turn MRC formalization, we propose a dual-MRC framework to extract emotion-cause pairs in a dual-direction way, which enables a more comprehensive coverage of all pairing cases. Furthermore, we propose a consistent training strategy for the second-turn query, so the model is able to filter the errors produced by the first turn at inference. Experiments on two benchmark datasets demonstrate that our method outperforms previous methods and achieves state-of-the-art performance. All the code and data of this work can be obtained at https://github.com/zifengcheng/CD-MRC .

25 January 2022 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
ZCZifeng Cheng
Zifeng Cheng
ZJZhiwei Jiang
Zhiwei Jiang
YYYafeng Yin
Yafeng Yin
CWCong Wang
Cong Wang
QGQing Gu
Qing Gu
Open intent classification is a practical yet challenging task in dialogue systems. Its objective is to accurately classify samples of known intents while at the same time detecting those of open (unknown) intents. Existing methods usually use outlier detection algorithms combined with K-class classifier to detect open intents, where K represents the class number of known intents. Different from them, in this paper, we consider another way without using outlier detection algorithms. Specifically, we directly train a (K+1)-class classifier for open intent classification, where the (K+1)-th class represents open intents. To address the challenge that training a (K+1)-class classifier with training samples of only K classes, we propose a deep model based on Soft Labeling and Manifold Mixup (SLMM). In our method, soft labeling is used to reshape the label distribution of the known intent samples, aiming at reducing model’s overconfident on known intents. Manifold mixup is used to generate pseudo samples for open intents, aiming at well optimizing the decision boundary of open intents. Experiments on four benchmark datasets demonstrate that our method outperforms previous methods and achieves state-of-the-art performance. All the code and data of this work can be obtained at. 1

30 April 2023
Verified
Conference Paper
Open access
SGShiping Ge
Shiping Ge
ZJZhiwei Jiang
Zhiwei Jiang
ZCZifeng Cheng
Zifeng Cheng
CWCong Wang
Cong Wang
YYYafeng Yin
Yafeng Yin
QGQing Gu
Qing Gu
Recognizing emotions from multi-modal data is an emotion recognition task that requires strong multi-modal representation ability. The general approach to this task is to naturally train the representation model on training data without intervention. However, such natural training scheme is prone to modality bias of representation (i.e., tending to over-encode some informative modalities while neglecting other modalities) and data bias of training (i.e., tending to overfit training data). These biases may lead to instability (e.g., performing poorly when the neglected modality is dominant for recognition) and weak generalization (e.g., performing poorly when unseen data is inconsistent with overfitted data) of the model on unseen data. To address these problems, this paper presents two adversarial training strategies to learn more robust multi-modal representation for multi-label emotion recognition. Firstly, we propose an adversarial temporal masking strategy, which can enhance the encoding of other modalities by masking the most emotion-related temporal units (e.g., words for text or frames for video) of the informative modality. Secondly, we propose an adversarial parameter perturbation strategy, which can enhance the generalization of the model by adding the adversarial perturbation to the parameters of model. Both strategies boost model performance on the benchmark MMER datasets CMU-MOSEI and NEMu. Experimental results demonstrate the effectiveness of the proposed method compared with the previous state-of-the-art method. Code will be released at https://github.com/ShipingGe/MMER.

1 February 2022 in Computers & Geosciences
Verified
Journal Article
Closed access
HHHuizhen Hao
Huizhen Hao
ZJZhiwei Jiang
Zhiwei Jiang
SGShiping Ge
Shiping Ge
CWCong Wang
Cong Wang
QGQing Gu
Qing Gu