Artificial Intelligence and Robotics Commons^™

Context In Computer Vision: A Taxonomy, Multi-Stage Integration, And A General Framework, Xuan Wang

Dissertations, Theses, and Capstone Projects

Contextual information has been widely used in many computer vision tasks, such as object detection, video action detection, image classification, etc. Recognizing a single object or action out of context could be sometimes very challenging, and context information may help improve the understanding of a scene or an event greatly. However, existing approaches design specific contextual information mechanisms for different detection tasks.

In this research, we first present a comprehensive survey of context understanding in computer vision, with a taxonomy to describe context in different types and levels. Then we proposed MultiCLU, a new multi-stage context learning and utilization framework, …

Locality-Aware Tail Node Embeddings On Homogeneous And Heterogeneous Networks, Zemin Liu, Yuan Fang, Wentao Zhang, Xinming Zhang, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

While the state-of-the-art network embedding approaches often learn high-quality embeddings for high-degree nodes with abundant structural connectivity, the quality of the embeddings for low-degree or nodes is often suboptimal due to their limited structural connectivity. While many real-world networks are long-tailed, to date little effort has been devoted to tail node embeddings. In this article, we formulate the goal of learning tail node embeddings as a problem, given the few links on each tail node. In particular, since each node resides in its own local context, we personalize the regression model for each tail node. To reduce overfitting in the …

Posmlp-Video: Spatial And Temporal Relative Position Encoding For Efficient Video Recognition, Yanbin Hao, Diansong Zhou, Zhicai Wang, Chong-Wah Ngo, Xiangnan He, Meng Wang

Research Collection School Of Computing and Information Systems

In recent years, vision Transformers and MLPs have demonstrated remarkable performance in image understanding tasks. However, their inherently dense computational operators, such as self-attention and token-mixing layers, pose significant challenges when applied to spatio-temporal video data. To address this gap, we propose PosMLP-Video, a lightweight yet powerful MLP-like backbone for video recognition. Instead of dense operators, we use efficient relative positional encoding (RPE) to build pairwise token relations, leveraging small-sized parameterized relative position biases to obtain each relation score. Specifically, to enable spatio-temporal modeling, we extend the image PosMLP’s positional gating unit to temporal, spatial, and spatio-temporal variants, namely PoTGU, …

Violet: Visual Analytics For Explainable Quantum Neural Networks, Shaolun Ruan, Zhiding Liang, Qiang Guan, Paul Robert Griffin, Xiaolin Wen, Yanna Lin, Yong Wang

Research Collection School Of Computing and Information Systems

With the rapid development of Quantum Machine Learning, quantum neural networks (QNN) have experienced great advancement in the past few years, harnessing the advantages of quantum computing to significantly speed up classical machine learning tasks. Despite their increasing popularity, the quantum neural network is quite counter-intuitive and difficult to understand, due to their unique quantum-specific layers (e.g., data encoding and measurement) in their architecture. It prevents QNN users and researchers from effectively understanding its inner workings and exploring the model training status. To fill the research gap, we propose VIOLET , a novel visual analytics approach to improve the explainability …

Poster: Profiling Event Vision Processing On Edge Devices, Ila Nitin Gokarn, Archan Misra

Research Collection School Of Computing and Information Systems

As RGB camera resolutions and frame-rates improve, their increased energy requirements make it challenging to deploy fast, efficient, and low-power applications on edge devices. Newer classes of sensors, such as the biologically inspired neuromorphic event-based camera, capture only changes in light intensity per-pixel to achieve operational superiority in sensing latency (O(μs)), energy consumption (O(mW)), high dynamic range (140dB), and task accuracy such as in object tracking, over traditional RGB camera streams. However, highly dynamic scenes can yield an event rate of up to 12MEvents/second, the processing of which could overwhelm …

The Low-Carbon Vehicle Routing Problem With Dynamic Speed On Steep Roads, Jianhua Xiao, Xiaoyang Liu, Huixian Zhang, Zhiguang Cao, Liujiang Kang, Yunyun Niu

Research Collection School Of Computing and Information Systems

The low-carbon vehicle routing problem with dynamic speeds on steep roads (LCVRPDS-SR) considers the combined effects of dynamic speeds, steep roads, and loads on carbon emissions. Earlier low-carbon vehicle routing problems typically assumed that vehicles travel at a constant speed on flat roads. However, such models do not apply in urban or rural areas with steep roads. Although the subsequent studies further explored the effect of steep roads, their performance are still suboptimal since they fail to take into account the varying speeds on the terrain. This paper proposes an extended LCVRPDS-SR model that tackles dynamic speed decisions on steep …

Imitating Cost-Constrained Behaviors In Reinforcement Learning, Qian Shao, Pradeep Varakantham, Shih-Fen Cheng

Research Collection School Of Computing and Information Systems

Complex planning and scheduling problems have long been solved using various optimization or heuristic approaches. In recent years, imitation learning that aims to learn from expert demonstrations has been proposed as a viable alternative to solving these problems. Generally speaking, imitation learning is designed to learn either the reward (or preference) model or directly the behavioral policy by observing the behavior of an expert. Existing work in imitation learning and inverse reinforcement learning has focused on imitation primarily in unconstrained settings (e.g., no limit on fuel consumed by the vehicle). However, in many real-world domains, the behavior of an expert …

The Next 'Deep' Thing In X To Z Marketing: An Artificial Intelligence Driven Approach, Vincent Charles, Nripendra Rana, Ilias O. Pappas, Morten Kamphaug, Keng Siau, Kenth Engo-Monsen

Research Collection School Of Computing and Information Systems

The existing body of literature indicates a growing interest in research pertaining to the influence of artificial intelligence (AI) on marketing strategies, processes, and practices. However, further studies are required to fully unravel its complete potential and the implications it holds for practical application. The aim of this special issue on “The Next ‘Deep’ Thing in X to Z Marketing: An Artificial Intelligence-Driven Approach” is to explore the next frontiers and delve into the various facets of AI-driven marketing, shedding light on cutting-edge research and practical insights that can shape the future of the field. It also focuses on novel …

Sgsh : Stimulate Large Language Models With Skeleton Heuristics For Knowledge Base Question Generation, Shasha Guo, Lizi Liao, Jing Zhang, Yanling Wang, Cuiping Li, Hong Chen

Research Collection School Of Computing and Information Systems

Knowledge base question generation (KBQG) aims to generate natural language questions from a set of triplet facts extracted from KB. Existing methods have significantly boosted the performance of KBQG via pre-trained language models (PLMs) thanks to the richly endowed semantic knowledge. With the advance of pre-training techniques, large language models (LLMs) (e.g., GPT-3.5) undoubtedly possess much more semantic knowledge. Therefore, how to effectively organize and exploit the abundant knowledge for KBQG becomes the focus of our study. In this work, we propose SGSH — a simple and effective framework to Stimulate GPT-3.5 with Skeleton Heuristics to enhance KBQG. The framework …

Learning Transferable Negative Prompts For Out-Of-Distribution Detection, Tianqi Li, Guansong Pang, Xiao Bai, Wenjun Miao, Jin Zheng

Research Collection School Of Computing and Information Systems

Existing prompt learning methods have shown certain capabilities in Out-of-Distribution (OOD) detection, but the lack of OOD images in the target dataset in their training can lead to mismatches between OOD images and In-Distribution (ID) categories, resulting in a high false positive rate. To address this issue, we introduce a novel OOD detection method, named ‘NegPrompt’, to learn a set of negative prompts, each representing a negative connotation of a given class label, for delineating the boundaries between ID and OOD images. It learns such negative prompts with ID data only, without any reliance on external out-lier data. Further, current …

Anomaly Heterogeneity Learning For Open-Set Supervised Anomaly Detection, Jiawen Zhu, Choubo Ding, Yu Tian, Guansong Pang

Research Collection School Of Computing and Information Systems

Open-set supervised anomaly detection (OSAD) - a recently emerging anomaly detection area - aims at utilizing a few samples of anomaly classes seen during training to detect unseen anomalies (i.e., samples from open-set anomaly classes), while effectively identifying the seen anomalies. Benefiting from the prior knowledge illustrated by the seen anomalies, current OSAD methods can often largely reduce false positive errors. However, these methods are trained in a closed-set setting and treat the anomaly examples as from a homogeneous distribution, rendering them less effective in generalizing to unseen anomalies that can be drawn from any distribution. This paper proposes to …

Toward Generalist Anomaly Detection Via In-Context Residual Learning With Few-Shot Sample Prompts, Jiawen Zhu, Guansong Pang

Research Collection School Of Computing and Information Systems

This paper explores the problem of Generalist Anomaly Detection (GAD), aiming to train one single detection model that can generalize to detect anomalies in diverse datasets from different application domains without any further training on the target data. Some recent studies have showed that large pre-trained Visual-Language Models (VLMs) like CLIP have strong generalization capabilities on detecting industrial defects from various datasets, but their methods rely heavily on handcrafted text prompts about defects, making them difficult to generalize to anomalies in other applications, e.g., medical image anomalies or semantic anomalies in natural images. In this work, we propose to train …

Drag Your Noise: Interactive Point-Based Editing Via Diffusion Semantic Propagation, Haofeng Liu, Chenshu Xu, Yifei Yang, Lihua Zeng, Shengfeng He

Research Collection School Of Computing and Information Systems

Point-based interactive editing serves as an essential tool to complement the controllability of existing generative models. A concurrent work, DragDiffusion, updates the diffusion latent map in response to user inputs, causing global latent map alterations. This results in imprecise preservation of the original content and unsuccessful editing due to gradient vanishing. In contrast, we present DragNoise, offering robust and accelerated editing without retracing the latent map. The core rationale of DragNoise lies in utilizing the predicted noise output of each U-Net as a semantic editor. This approach is grounded in two critical observations: firstly, the bottleneck features of U-Net inherently …

Learning With Unreliability : Fast Few-Shot Voxel Radiance Fields With Relative Geometric Consistency, Yingjie Xu, Bangzhen Liu, Hao Tang, Bailin Deng, Shengfeng He

Research Collection School Of Computing and Information Systems

We propose a voxel-based optimization framework, Re VoRF, for few-shot radiance fields that strategically ad-dress the unreliability in pseudo novel view synthesis. Our method pivots on the insight that relative depth relationships within neighboring regions are more reliable than the ab-solute color values in disoccluded areas. Consequently, we devise a bilateral geometric consistency loss that carefully navigates the trade-off between color fidelity and geometric accuracy in the context of depth consistency for uncertain regions. Moreover, we present a reliability-guided learning strategy to discern and utilize the variable quality across syn-thesized views, complemented by a reliability-aware voxel smoothing algorithm that smoothens …

The Whole Is Better Than The Sum : Using Aggregated Demonstrations In In-Context Learning For Sequential Recommendation, Wang Lei, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Large language models (LLMs) have shown excellent performance on various NLP tasks. To use LLMs as strong sequential recommenders, we explore the in-context learning approach to sequential recommendation. We investigate the effects of instruction format, task consistency, demonstration selection, and number of demonstrations. As increasing the number of demonstrations in ICL does not improve accuracy despite using a long prompt, we propose a novel method called LLMSRec-Syn that incorporates multiple demonstration users into one aggregated demonstration. Our experiments on three recommendation datasets show that LLMSRec-Syn outperforms state-of-the-art LLM-based sequential recommendation methods. In some cases, LLMSRec-Syn can perform on par with …

Zero-Shot Out-Of-Distribution Detection With Outlier Label Exposure, Choubo Ding, Guansong Pang

Research Collection School Of Computing and Information Systems

As vision-language models like CLIP are widely applied to zero-shot tasks and gain remarkable performance on in-distribution (ID) data, detecting and rejecting out-of-distribution (OOD) inputs in the zero-shot setting have become crucial for ensuring the safety of using such models on the fly. Most existing zero-shot OOD detectors rely on ID class label-based prompts to guide CLIP in classifying ID images and rejecting OOD images. In this work we instead propose to leverage a large set of diverse auxiliary outlier class labels as pseudo OOD class text prompts to CLIP for enhancing zero-shot OOD detection, an approach we called Outlier …

Analyzing Swimming Performance Using Drone Captured Aerial Videos, Ngoc Doan Thu Tran, Kenny Tsu Wei Choo, Shaohui Foong, Hitesh Bhardwaj, Shane Kyi Hla Win, Wei Jun Ang, Kenneth T. Goh, Rajesh Krishna Balan

Research Collection School Of Computing and Information Systems

Monitoring swimmer performance is crucial for improving training and enhancing athletic techniques. Traditional methods for tracking swimmers, such as above-water and underwater cameras, face limitations due to the need for multiple cameras and obstructions from water splashes. This paper presents a novel approach for tracking swimmers using a moving UAV. The proposed system employs a UAV equipped with a high-resolution camera to capture aerial footage of the swimmers. The footage is then processed using computer vision algorithms to extract the swimmers' positions and movements. This approach offers several advantages, including single camera use and comprehensive coverage. The system's accuracy is …

More Human-Likeness, Less Self-Disclosure? Avatars' Form Realism And Job Applicants' Self-Disclosure In Ai Interviews, Yamin Xu, Keng Siau, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

The rise of AI in recruitment promises to revolutionize how organizations evaluate job candidates. The quality of AI evaluations is determined by the input data, which depends on job applicants' self-disclosure. However, little is known about how the design elements of AI interview systems, particularly avatar interviewers, influence job applicants' self-disclosure during these interactions. This study aims to address this gap by specifically focusing on how the form realism of avatar interviewers affects job applicants' self-disclosure through their perceptions. In addition, the study will examine the effects of job type as a moderator. Drawing on the Stimulus-Organism-Response (S-O-R) model, this …

Enhancing Government Service Delivery: A Case Study Of Acqar Implementation And Lessons Learned From Chatgpt Integration In A Singapore Government Agency, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh

Research Collection Lee Kong Chian School Of Business

This paper presents the pilot implementation of AI Based Citizen Question-Answer Recommender (ACQAR) as an attempt to enhance citizen service delivery within a Singaporean government agency. Drawing insights from previous studies on the Empath library's use in Service Level Agreement (SLA) prediction and the implementation of the Citizen Question-Answer system (CQAS), we redesigned the pilot system, ACQAR. ACQAR integrates the outputs from Empath X SLA predictor and CQAS as essential inputs to the ChatGPT engine, creating contextually aware responses for customer service officers to use as responses to the citizens.Empath X SLA predictor anticipates the expected service response time based …

Ai Competency Acquisition Online? Engaging Undergraduate Students In An Ai 101 Course Through A Chatbot Workshop, Thomas Menkhoff, Lydia Teo

Research Collection Lee Kong Chian School Of Business

In recent years, digital transformation has dominated industries at an unprecedented rate. Alongside the proliferation of Artificial ntelligence (AI) technologies in the workplace, institutions of higher learning are experiencing an unprecedented push to integrate AI into the education ecosystem (Popenici & Kerr, 2017; Renz & Hilbig, 2020). AI in education (AIED) has the propensity to enrich teaching and learning in higher education by personalising students’ learning courses, automating assessment tasks, or providing24/7 access to learning resources (Karandish, 2021). According to estimates by the AI Market in the US Education Report, the AIEDmarket will grow at a CAGR of 47.77% during …