Open Access. Powered by Scholars. Published by Universities.®

Graphics and Human Computer Interfaces Commons™

Open Access. Powered by Scholars. Published by Universities.®

Research Collection School Of Computing and Information Systems

Discipline
Keyword
Publication Year

Articles 301 - 330 of 936

Full-Text Articles in Graphics and Human Computer Interfaces

Graph Neural Point Process For Temporal Interaction Prediction, Wenwen Xia, Yuchen Li, Shengdong Li May 2023

Graph Neural Point Process For Temporal Interaction Prediction, Wenwen Xia, Yuchen Li, Shengdong Li

Research Collection School Of Computing and Information Systems

Temporal graphs are ubiquitous data structures in many scenarios, including social networks, user-item interaction networks, etc. In this paper, we focus on predicting the exact time of the next interaction, given a node pair on a temporal graph. This novel problem can support interesting applications, such as time-sensitive items recommendation, congestion prediction on road networks, and many others. We present Graph Neural Point Process (GNPP) to tackle this problem. GNPP relies on the graph neural message passing and the temporal point process framework. Most previous graph neural models only utilize the chronological order of observed events and ignore exact timestamps. …

Go to article

Compositional Prompt Tuning With Motion Cues For Open-Vocabulary Video Relation Detection, Kaifeng Gao, Long Chen, Hanwang Zhang, Jun Xiao, Qianru Sun May 2023

Compositional Prompt Tuning With Motion Cues For Open-Vocabulary Video Relation Detection, Kaifeng Gao, Long Chen, Hanwang Zhang, Jun Xiao, Qianru Sun

Research Collection School Of Computing and Information Systems

Prompt tuning with large-scale pretrained vision-language models empowers open-vocabulary prediction trained on limited base categories, e.g., object classification and detection. In this paper, we propose compositional prompt tuning with motion cues: an extended prompt tuning paradigm for compositional predictions of video data. In particular, we present Relation Prompt (RePro) for Open-vocabulary Video Visual Relation Detection (Open-VidVRD), where conventional prompt tuning is easily biased to certain subject-object combinations and motion patterns. To this end, RePro addresses the two technical challenges of Open-VidVRD: 1) the prompt tokens should respect the two different semantic roles of subject and object, and 2) the tuning …

Go to article

Mando-Hgt: Heterogeneous Graph Transformers For Smart Contract Vulnerability Detection, Huu Hoang Nguyen, Nhat Minh Nguyen, Chunyao Xie, Zahra Ahmadi, Daniel Kudendo, Thanh-Nam Doan, Lingxiao Jiang May 2023

Mando-Hgt: Heterogeneous Graph Transformers For Smart Contract Vulnerability Detection, Huu Hoang Nguyen, Nhat Minh Nguyen, Chunyao Xie, Zahra Ahmadi, Daniel Kudendo, Thanh-Nam Doan, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Smart contracts in blockchains have been increasingly used for high-value business applications. It is essential to check smart contracts' reliability before and after deployment. Although various program analysis and deep learning techniques have been proposed to detect vulnerabilities in either Ethereum smart contract source code or bytecode, their detection accuracy and scalability are still limited. This paper presents a novel framework named MANDO-HGT for detecting smart contract vulnerabilities. Given Ethereum smart contracts, either in source code or bytecode form, and vulnerable or clean, MANDO-HGT custom-builds heterogeneous contract graphs (HCGs) to represent control-flow and/or function-call information of the code. It then …

Go to article

Chronos: Time-Aware Zero-Shot Identification Of Libraries From Vulnerability Reports, Yunbo Lyu, Thanh Le Cong, Hong Jin Kang, Ratnadira Widyasari, Zhipeng Zhao, Xuan-Bach Dinh Le, Ming Li, David Lo May 2023

Chronos: Time-Aware Zero-Shot Identification Of Libraries From Vulnerability Reports, Yunbo Lyu, Thanh Le Cong, Hong Jin Kang, Ratnadira Widyasari, Zhipeng Zhao, Xuan-Bach Dinh Le, Ming Li, David Lo

Research Collection School Of Computing and Information Systems

Tools that alert developers about library vulnerabilities depend on accurate, up-to-date vulnerability databases which are maintained by security researchers. These databases record the libraries related to each vulnerability. However, the vulnerability reports may not explicitly list every library and human analysis is required to determine all the relevant libraries. Human analysis may be slow and expensive, which motivates the need for automated approaches. Researchers and practitioners have proposed to automatically identify libraries from vulnerability reports using extreme multi-label learning (XML). While state-of-the-art XML techniques showed promising performance, their experimental settings do not practically fit what happens in reality. Previous studies …

Go to article

Diffseer: Difference-Based Dynamic Weighted Graph Visualization, Xiaolin Wen, Yong Wang, Meixuan Wu, Fengjie Wang, Xuanwu Yue, Qiaomu Shen, Yuxin Ma, Min Zhu May 2023

Diffseer: Difference-Based Dynamic Weighted Graph Visualization, Xiaolin Wen, Yong Wang, Meixuan Wu, Fengjie Wang, Xuanwu Yue, Qiaomu Shen, Yuxin Ma, Min Zhu

Research Collection School Of Computing and Information Systems

Existing dynamic weighted graph visualization approaches rely on users’ mental comparison to perceive temporal evolution of dynamic weighted graphs, hindering users from effectively analyzing changes across multiple timeslices. We propose DiffSeer, a novel approach for dynamic weighted graph visualization by explicitly visualizing the differences of graph structures (e.g., edge weight differences) between adjacent timeslices. Specifically, we present a novel nested matrix design that overviews the graph structure differences over a time period as well as shows graph structure details in the timeslices of user interest. By collectively considering the overall temporal evolution and structure details in each timeslice, an optimization-based …

Go to article

Lpt: Long-Tailed Prompt Tuning For Image Classification, Bowen Dong, Pan Zhou, Shuicheng Yan, Wangmeng Zuo May 2023

Lpt: Long-Tailed Prompt Tuning For Image Classification, Bowen Dong, Pan Zhou, Shuicheng Yan, Wangmeng Zuo

Research Collection School Of Computing and Information Systems

For long-tailed classification tasks, most works often pretrain a big model on a large-scale (unlabeled) dataset, and then fine-tune the whole pretrained model for adapting to long-tailed data. Though promising, fine-tuning the whole pretrained model tends to suffer from high cost in computation and deployment of different models for different tasks, as well as weakened generalization capability for overfitting to certain features of long-tailed data. To alleviate these issues, we propose an effective Long-tailed Prompt Tuning (LPT) method for long-tailed classification tasks. LPT introduces several trainable prompts into a frozen pretrained model to adapt it to long-tailed data. For better …

Go to article

Towards Understanding Why Mask Reconstruction Pretraining Helps In Downstream Tasks, Jiachun Pan, Pan Zhou, Shuicheng Yan May 2023

Towards Understanding Why Mask Reconstruction Pretraining Helps In Downstream Tasks, Jiachun Pan, Pan Zhou, Shuicheng Yan

Research Collection School Of Computing and Information Systems

For unsupervised pretraining, mask-reconstruction pretraining (MRP) approaches, e.g. MAE (He et al., 2021) and data2vec (Baevski et al., 2022), randomly mask input patches and then reconstruct the pixels or semantic features of these masked patches via an auto-encoder. Then for a downstream task, supervised fine-tuning the pretrained encoder remarkably surpasses the conventional “supervised learning" (SL) trained from scratch. However, it is still unclear 1) how MRP performs semantic feature learning in the pretraining phase and 2) why it helps in downstream tasks. To solve these problems, we first theoretically show that on an auto-encoder of a two/one-layered convolution encoder/decoder, MRP …

Go to article

Stargazer: An Interactive Camera Robot For Capturing How-To Videos Based On Subtle Instructor Cues, Jiannan Li, Mauricio Sousa, Karthik Mahadevan, Bryan Wang, Paula Akemi Aoyagui, Nicole Yu, Angela Yang, Ravin Balakrishnan, Anthony Tang, Tovi Grossman Apr 2023

Stargazer: An Interactive Camera Robot For Capturing How-To Videos Based On Subtle Instructor Cues, Jiannan Li, Mauricio Sousa, Karthik Mahadevan, Bryan Wang, Paula Akemi Aoyagui, Nicole Yu, Angela Yang, Ravin Balakrishnan, Anthony Tang, Tovi Grossman

Research Collection School Of Computing and Information Systems

Live and pre-recorded video tutorials are an effective means for teaching physical skills such as cooking or prototyping electronics. A dedicated cameraperson following an instructor’s activities can improve production quality. However, instructors who do not have access to a cameraperson’s help often have to work within the constraints of static cameras. We present Stargazer, a novel approach for assisting with tutorial content creation with a camera robot that autonomously tracks regions of interest based on instructor actions to capture dynamic shots. Instructors can adjust the camera behaviors of Stargazer with subtle cues, including gestures and speech, allowing them to fluidly …

Go to article

Subgraph Centralization: A Necessary Step For Graph Anomaly Detection, Zhong Zhuang, Kai Ming Ting, Guansong Pang, Shuaibin Song Apr 2023

Subgraph Centralization: A Necessary Step For Graph Anomaly Detection, Zhong Zhuang, Kai Ming Ting, Guansong Pang, Shuaibin Song

Research Collection School Of Computing and Information Systems

Abstract Graph anomaly detection has attracted a lot of interest recently. Despite their successes, existing detectors have at least two of the three weaknesses: (a) high computational cost which limits them to small-scale networks only; (b) existing treatment of subgraphs produces suboptimal detection accuracy; and (c) unable to provide an explanation as to why a node is anomalous, once it is identified. We identify that the root cause of these weaknesses is a lack of a proper treatment for subgraphs. A treatment called Subgraph Centralization for graph anomaly detection is proposed to address all the above weaknesses. Its importance is …

Go to article

Supporting Novices Author Audio Descriptions Via Automatic Feedback, Rosiana Natalie, Joshua Shi-Hao Tseng, Hernisa Kacorri, Kotaro Hara Apr 2023

Supporting Novices Author Audio Descriptions Via Automatic Feedback, Rosiana Natalie, Joshua Shi-Hao Tseng, Hernisa Kacorri, Kotaro Hara

Research Collection School Of Computing and Information Systems

Audio descriptions (AD) make videos accessible to those who cannot see them. But many videos lack AD and remain inaccessible as traditional approaches involve expensive professional production. We aim to lower production costs by involving novices in this process. We present an AD authoring system that supports novices to write scene descriptions (SD)—textual descriptions of video scenes—and convert them into AD via text-to-speech. The system combines video scene recognition and natural language processing to review novice-written SD and feeds back what to mention automatically. To assess the effectiveness of this automatic feedback in supporting novices, we recruited 60 participants to …

Go to article

Open-Set Domain Adaptation By Deconfounding Domain Gaps, Xin Zhao, Shengsheng Wang, Qianru Sun Apr 2023

Open-Set Domain Adaptation By Deconfounding Domain Gaps, Xin Zhao, Shengsheng Wang, Qianru Sun

Research Collection School Of Computing and Information Systems

Open-Set Domain Adaptation (OSDA) aims to adapt the model trained on a source domain to the recognition tasks in a target domain while shielding any distractions caused by open-set classes, i.e., the classes “unknown” to the source model. Compared to standard DA, the key of OSDA lies in the separation between known and unknown classes. Existing OSDA methods often fail the separation because of overlooking the confounders (i.e., the domain gaps), which means their recognition of “unknown classes” is not because of class semantics but domain difference (e.g., styles and contexts). We address this issue by explicitly deconfounding domain gaps …

Go to article

Wearables For In-Situ Monitoring Of Cognitive States: Challenges And Opportunities, Meera Radhakrishnan, Thivya Kandappu, Manoj Gulati, Archan Misra Mar 2023

Wearables For In-Situ Monitoring Of Cognitive States: Challenges And Opportunities, Meera Radhakrishnan, Thivya Kandappu, Manoj Gulati, Archan Misra

Research Collection School Of Computing and Information Systems

We propose using wrist and ear-based sensing, via multiple novel and complementary modalities, to unobtrusively infer activity-aware, complex cognitive and affective states (such as confusion, boredom, and recall failure) of individuals. While state-of-the-art wearable devices are predominantly used (a) independently, with limited coordination among multiple devices, and (b) to capture macro-level physical activity and physiological state, we seek to expand the ambit of unobtrusive wearable sensing to capture the cognitive states while performing commonplace physical activities. Such states typically manifest via fine-grained, almost unobservable, microscopic head, face, and eye movements. We identify some of these fine-grained physical markers that serve …

Go to article

Investigating Guardian Awareness Techniques To Promote Safety In Virtual Reality, Sixuan Wu, Jiannan Li, Maurício Sousa, Tovi Grossman Mar 2023

Investigating Guardian Awareness Techniques To Promote Safety In Virtual Reality, Sixuan Wu, Jiannan Li, Maurício Sousa, Tovi Grossman

Research Collection School Of Computing and Information Systems

Virtual Reality (VR) can completely immerse users in a virtual world and provide little awareness of bystanders in the surrounding physical environment. Current technologies use predefined guardian area visualizations to set safety boundaries for VR interactions. However, bystanders cannot perceive these boundaries and may collide with VR users if they accidentally enter guardian areas. In this paper, we investigate four awareness techniques on mobile phones and smartwatches to help bystanders avoid invading guardian areas. These techniques include augmented reality boundary overlays and visual, auditory, and haptic alerts indicating bystanders' distance from guardians. Our findings suggest that the proposed techniques effectively …

Go to article

Dminer: Dashboard Design Mining And Recommendation, Yanna Lin, Haotian Li, Aoyu Wu, Yong Wang, Huamin Qu Mar 2023

Dminer: Dashboard Design Mining And Recommendation, Yanna Lin, Haotian Li, Aoyu Wu, Yong Wang, Huamin Qu

Research Collection School Of Computing and Information Systems

Dashboards, which comprise multiple views on a single display, help analyze and communicate multiple perspectives of data simultaneously. However, creating effective and elegant dashboards is challenging since it requires careful and logical arrangement and coordination of multiple visualizations. To solve the problem, we propose a data-driven approach for mining design rules from dashboards and automating dashboard organization. Specifically, we focus on two prominent aspects of the organization: arrangement , which describes the position, size, and layout of each view in the display space; and coordination , which indicates the interaction between pairwise views. We build a new dataset containing 854 …

Go to article

Effective Graph Kernels For Evolving Functional Brain Networks, Xinlei Wang, Jinyi Chen, Bing Tian Dai, Junchang Xin, Yu Gu, Ge Yu Mar 2023

Effective Graph Kernels For Evolving Functional Brain Networks, Xinlei Wang, Jinyi Chen, Bing Tian Dai, Junchang Xin, Yu Gu, Ge Yu

Research Collection School Of Computing and Information Systems

The graph kernel of the functional brain network is an effective method in the field of neuropsychiatric disease diagnosis like Alzheimer's Disease (AD). The traditional static brain networks cannot reflect dynamic changes of brain activities, but evolving brain networks, which are a series of brain networks over time, are able to seize such dynamic changes. As far as we know, the graph kernel method is effective for calculating the differences among networks. Therefore, it has a great potential to understand the dynamic changes of evolving brain networks, which are a series of chronological differences. However, if the conventional graph kernel …

Go to article

Concept-Oriented Transformers For Visual Sentiment Analysis, Quoc Tuan Truong, Hady Wirawan Lauw Mar 2023

Concept-Oriented Transformers For Visual Sentiment Analysis, Quoc Tuan Truong, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

In the richly multimedia Web, detecting sentiment signals expressed in images would support multiple applications, e.g., measuring customer satisfaction from online reviews, analyzing trends and opinions from social media. Given an image, visual sentiment analysis aims at recognizing positive or negative sentiment, and occasionally neutral sentiment as well. A nascent yet promising direction is Transformer-based models applied to image data, whereby Vision Transformer (ViT) establishes remarkable performance on largescale vision benchmarks. In addition to investigating the fitness of ViT for visual sentiment analysis, we further incorporate concept orientation into the self-attention mechanism, which is the core component of Transformer. The …

Go to article

Investigating Noticeable Hand Redirection In Virtual Reality Using Physiological And Interaction Data, Martin Feick, Kora Regitz, Anthony Tang, Jungbluth Mar 2023

Investigating Noticeable Hand Redirection In Virtual Reality Using Physiological And Interaction Data, Martin Feick, Kora Regitz, Anthony Tang, Jungbluth

Research Collection School Of Computing and Information Systems

Hand redirection is effective so long as the introduced offsets are not noticeably disruptive to users. In this work we investigate the use of physiological and interaction data to detect movement discrepancies between a user's real and virtual hand, pushing towards a novel approach to identify discrepancies which are too large and therefore can be noticed. We ran a study with 22 participants, collecting EEG, ECG, EDA, RSP, and interaction data. Our results suggest that EEG and interaction data can be reliably used to detect visuo-motor discrepancies, whereas ECG and RSP seem to suffer from inconsistencies. Our findings also show …

Go to article

Towards A Design Space For Storytelling On The Fashion Technology Runway, Sydney Pratte, Anthony Tang, Shannon Hoover, Maria Elena Hoover, Matt Laprarie, Catherine Larose, Lora Oehlberg Mar 2023

Towards A Design Space For Storytelling On The Fashion Technology Runway, Sydney Pratte, Anthony Tang, Shannon Hoover, Maria Elena Hoover, Matt Laprarie, Catherine Larose, Lora Oehlberg

Research Collection School Of Computing and Information Systems

Fashion is driven by a narrative, i.e. a story or idea that the designer wants to convey to the audience. Fashion-tech now adds another dimension to this narrative through dynamically changing aspects of the garments. Many factors of presentation in a runway show affect how fashion-tech garments communicate a story to the audience. In this pictorial, we review a set of twenty-eight storytelling fashion-tech garments. We identify, catalogue, and categorize the factors designers used to convey stories to the audience from the runway. The design space consists of three levels: (1) the artifact-level, (2) the viewer-level, and (3) the context-level. …

Go to article

Wearables For In-Situ Monitoring Of Cognitive States: Challenges And Opportunities, Meeralakshmi Radhakrishnan, Thivya Kandappu, Manoj Gulati, Archan Misra Mar 2023

Wearables For In-Situ Monitoring Of Cognitive States: Challenges And Opportunities, Meeralakshmi Radhakrishnan, Thivya Kandappu, Manoj Gulati, Archan Misra

Research Collection School Of Computing and Information Systems

We propose using wrist and ear-based sensing, via multiple novel and complementary modalities, to unobtrusively infer activity-aware, complex cognitive and affective states (such as confusion, boredom, and recall failure) of individuals. While state-of-the-art wearable devices are predominantly used (a) independently, with limited coordination among multiple devices, and (b) to capture macro-level physical activity and physiological state, we seek to expand the ambit of unobtrusive wearable sensing to capture the cognitive states while performing commonplace physical activities. Such states typically manifest via fine-grained, almost unobservable, microscopic head, face, and eye movements. We identify some of these fine-grained physical markers that serve …

Go to article

Bidding Graph Games With Partially-Observable Budgets, Guy Avni, Ismael Jecker, Dorde Zikelic Feb 2023

Bidding Graph Games With Partially-Observable Budgets, Guy Avni, Ismael Jecker, Dorde Zikelic

Research Collection School Of Computing and Information Systems

Two-player zero-sum graph games are a central model, which proceeds as follows. A token is placed on a vertex of a graph, and the two players move it to produce an infinite play, which determines the winner or payoff of the game. Traditionally, the players alternate turns in moving the token. In bidding games, however, the players have budgets and in each turn, an auction (bidding) determines which player moves the token. So far, bidding games have only been studied as fullinformation games. In this work we initiate the study of partial-information bidding games: we study bidding games in which …

Go to article

Learning Comprehensive Global Features In Person Re-Identification: Ensuring Discriminativeness Of More Local Regions, Jiali Xia, Jianqiang Huang, Shibao Zheng, Qin Zhou, Bernt Schiele, Xian-Sheng Hua, Qianru Sun Feb 2023

Learning Comprehensive Global Features In Person Re-Identification: Ensuring Discriminativeness Of More Local Regions, Jiali Xia, Jianqiang Huang, Shibao Zheng, Qin Zhou, Bernt Schiele, Xian-Sheng Hua, Qianru Sun

Research Collection School Of Computing and Information Systems

Person re-identification (Re-ID) aims to retrieve person images from a large gallery given a query image of a person of interest. Global information and fine-grained local features are both essential for the representation. However, global embedding learned by naive classification model tends to be trapped in the most discriminative local region, leading to poor evaluation performance. To address the issue, we propose a novel baseline network that learns strong global feature termed as Comprehensive Global Embedding (CGE), ensuring more local regions of global feature maps to be discriminative. In this work, two key modules are proposed including Non-parameterized Local Classifier …

Go to article

Distance Based Image Classification: A Solution To Generative Classification’S Conundrum?, Wen-Yan Lin, Siying Liu, Bing Tian Dai, Hongdong Li Jan 2023

Distance Based Image Classification: A Solution To Generative Classification’S Conundrum?, Wen-Yan Lin, Siying Liu, Bing Tian Dai, Hongdong Li

Research Collection School Of Computing and Information Systems

Most classifiers rely on discriminative boundaries that separate instances of each class from everything else. We argue that discriminative boundaries are counter-intuitive as they define semantics by what-they-are-not; and should be replaced by generative classifiers which define semantics by what-they-are. Unfortunately, generative classifiers are significantly less accurate. This may be caused by the tendency of generative models to focus on easy to model semantic generative factors and ignore non-semantic factors that are important but difficult to model. We propose a new generative model in which semantic factors are accommodated by shell theory’s [25] hierarchical generative process and non-semantic factors by …

Go to article

Sleepmore: Inferring Sleep Duration At Scale Via Multi-Device Wifi Sensing, Camellia Zakaria, Gizem Yilmaz, Priyanka Mammen, Michael Chee, Prashant Shenoy, Rajesh Krishna Balan Jan 2023

Sleepmore: Inferring Sleep Duration At Scale Via Multi-Device Wifi Sensing, Camellia Zakaria, Gizem Yilmaz, Priyanka Mammen, Michael Chee, Prashant Shenoy, Rajesh Krishna Balan

Research Collection School Of Computing and Information Systems

The availability of commercial wearable trackers equipped with features to monitor sleep duration and quality has enabled more useful sleep health monitoring applications and analyses. However, much research has reported the challenge of long-term user retention in sleep monitoring through these modalities. Since modern Internet users own multiple mobile devices, our work explores the possibility of employing ubiquitous mobile devices and passive WiFi sensing techniques to predict sleep duration as the fundamental measure for complementing long-term sleep monitoring initiatives. In this paper, we propose SleepMore, an accurate and easy-to-deploy sleep-tracking approach based on machine learning over the user's WiFi network …

Go to article

Taurus: Towards A Unified Force Representation And Universal Solver For Graph Layout, Mingliang Xue, Zhi Wang, Fahai Zhong, Yong Wang, Mingliang Xu, Oliver Deussen, Yunhai Wang Jan 2023

Taurus: Towards A Unified Force Representation And Universal Solver For Graph Layout, Mingliang Xue, Zhi Wang, Fahai Zhong, Yong Wang, Mingliang Xu, Oliver Deussen, Yunhai Wang

Research Collection School Of Computing and Information Systems

Over the past few decades, a large number of graph layout techniques have been proposed for visualizing graphs from various domains. In this paper, we present a general framework, Taurus, for unifying popular techniques such as the spring-electrical model, stress model, and maxent-stress model. It is based on a unified force representation, which formulates most existing techniques as a combination of quotient-based forces that combine power functions of graph-theoretical and Euclidean distances. This representation enables us to compare the strengths and weaknesses of existing techniques, while facilitating the development of new methods. Based on this, we propose a new balanced …

Go to article

Relation Preserving Triplet Mining For Stabilising The Triplet Loss In Re-Identification Systems, Adhiraj Ghosh, Kuruparan Shanmugalingam, Wen-Yan Lin Jan 2023

Relation Preserving Triplet Mining For Stabilising The Triplet Loss In Re-Identification Systems, Adhiraj Ghosh, Kuruparan Shanmugalingam, Wen-Yan Lin

Research Collection School Of Computing and Information Systems

Object appearances change dramatically with pose variations. This creates a challenge for embedding schemes that seek to map instances with the same object ID to locations that are as close as possible. This issue becomes significantly heightened in complex computer vision tasks such as re-identification(reID). In this paper, we suggest that these dramatic appearance changes are indications that an object ID is composed of multiple natural groups, and it is counterproductive to forcefully map instances from different groups to a common location. This leads us to introduce Relation Preserving Triplet Mining (RPTM), a feature matching guided triplet mining scheme, that …

Go to article

Reinforcement Learning Enhanced Pichunter For Interactive Search, Zhixin Ma, Jiaxin Wu, Weixiong Loo, Chong-Wah Ngo Jan 2023

Reinforcement Learning Enhanced Pichunter For Interactive Search, Zhixin Ma, Jiaxin Wu, Weixiong Loo, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

With the tremendous increase in video data size, search performance could be impacted significantly. Specifically, in an interactive system, a real-time system allows a user to browse, search and refine a query. Without a speedy system quickly, the main ingredient to engage a user to stay focused, an interactive system becomes less effective even with a sophisticated deep learning system. This paper addresses this challenge by leveraging approximate search, Bayesian inference, and reinforcement learning. For approximate search, we apply a hierarchical navigable small world, which is an efficient approximate nearest neighbor search algorithm. To quickly prune the search scope, we …

Go to article

Causal Interventional Training For Image Recognition, Wei Qin, Hanwang Zhang, Richang Hong, Ee-Peng Lim, Qianru Sun Jan 2023

Causal Interventional Training For Image Recognition, Wei Qin, Hanwang Zhang, Richang Hong, Ee-Peng Lim, Qianru Sun

Research Collection School Of Computing and Information Systems

Deep learning models often fit undesired dataset bias in training. In this paper, we formulate the bias using causal inference, which helps us uncover the ever-elusive causalities among the key factors in training, and thus pursue the desired causal effect without the bias. We start from revisiting the process of building a visual recognition system, and then propose a structural causal model (SCM) for the key variables involved in dataset collection and recognition model: object, common sense, bias, context, and label prediction. Based on the SCM, one can observe that there are “good” and “bad” biases. Intuitively, in the image …

Go to article

Multi-Relation Extraction Via A Global-Local Graph Convolutional Network, Harry Cheng, Lizi Liao, Linmei Hu, Liqiang Nie Dec 2022

Multi-Relation Extraction Via A Global-Local Graph Convolutional Network, Harry Cheng, Lizi Liao, Linmei Hu, Liqiang Nie

Research Collection School Of Computing and Information Systems

Relation extraction (RE) extracts the semantic relations among entities in a sentence, which converts the unstructured text into structured and easy-to-understand information. Although RE has been studied over decades, it still faces two kinds of research challenges that are not well addressed thus far: 1) joint consideration of the global sentence structure and the local entity interaction, and 2) effective solution to the overlapping triplets within the same sentence. To tackle these issues, in this paper, we present globallocal graph-based convolutional network towards multi-relation extraction, GAME for short. In particular, we devise two layers of graph convolutional network (GCN) with …

Go to article

Appearance-Preserved Portrait-To-Anime Translation Via Proxy-Guided Domain Adaptation, Wenpeng Xiao, Cheng Xu, Jiajie Mai, Xuemiao Xu, Yue Li, Chengze Li, Xueting Liu, Shengfeng He Dec 2022

Appearance-Preserved Portrait-To-Anime Translation Via Proxy-Guided Domain Adaptation, Wenpeng Xiao, Cheng Xu, Jiajie Mai, Xuemiao Xu, Yue Li, Chengze Li, Xueting Liu, Shengfeng He

Research Collection School Of Computing and Information Systems

Converting a human portrait to anime style is a desirable but challenging problem. Existing methods fail to resolve this problem due to the large inherent gap between two domains that cannot be overcome by a simple direct mapping. For this reason, these methods struggle to preserve the appearance features in the original photo. In this paper, we discover an intermediate domain, the coser portrait (portraits of humans costuming as anime characters), that helps bridge this gap. It alleviates the learning ambiguity and loosens the mapping difficulty in a progressive manner. Specifically, we start from learning the mapping between coser and …

Go to article

Segment-Wise Time-Varying Dynamic Bayesian Network With Graph Regularization, Xing Yang, Chen Zhang, Baihua Zheng Dec 2022

Segment-Wise Time-Varying Dynamic Bayesian Network With Graph Regularization, Xing Yang, Chen Zhang, Baihua Zheng

Research Collection School Of Computing and Information Systems

Time-varying dynamic Bayesian network (TVDBN) is essential for describing time-evolving directed conditional dependence structures in complex multivariate systems. In this article, we construct a TVDBN model, together with a score-based method for its structure learning. The model adopts a vector autoregressive (VAR) model to describe inter-slice and intra-slice relations between variables. By allowing VAR parameters to change segment-wisely over time, the time-varying dynamics of the network structure can be described. Furthermore, considering some external information can provide additional similarity information of variables. Graph Laplacian is further imposed to regularize similar nodes to have similar network structures. The regularized maximum a …

Go to article

First Prev Next Last