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 181 - 210 of 933

Full-Text Articles in Graphics and Human Computer Interfaces

Unifying Global-Local Representations In Salient Object Detection With Transformers, Sucheng Ren, Nanxuan Zhao, Qiang Wen, Guoqiang Han, Shengfeng He Aug 2024

Unifying Global-Local Representations In Salient Object Detection With Transformers, Sucheng Ren, Nanxuan Zhao, Qiang Wen, Guoqiang Han, Shengfeng He

Research Collection School Of Computing and Information Systems

The fully convolutional network (FCN) has dominated salient object detection for a long period. However, the locality of CNN requires the model deep enough to have a global receptive field and such a deep model always leads to the loss of local details. In this paper, we introduce a new attention-based encoder, vision transformer, into salient object detection to ensure the globalization of the representations from shallow to deep layers. With the global view in very shallow layers, the transformer encoder preserves more local representations to recover the spatial details in final saliency maps. Besides, as each layer can capture …

Go to article

Nonfactoid Question Answering As Query-Focused Summarization With Graph-Enhanced Multihop Inference, Yang Deng, Wenxuan Zhang, Weiwen Xu, Ying Shen, Wai Lam Aug 2024

Nonfactoid Question Answering As Query-Focused Summarization With Graph-Enhanced Multihop Inference, Yang Deng, Wenxuan Zhang, Weiwen Xu, Ying Shen, Wai Lam

Research Collection School Of Computing and Information Systems

Nonfactoid question answering (QA) is one of the most extensive yet challenging applications and research areas in natural language processing (NLP). Existing methods fall short of handling the long-distance and complex semantic relations between the question and the document sentences. In this work, we propose a novel query-focused summarization method, namely a graph-enhanced multihop query-focused summarizer (GMQS), to tackle the nonfactoid QA problem. Specifically, we leverage graph-enhanced reasoning techniques to elaborate the multihop inference process in nonfactoid QA. Three types of graphs with different semantic relations, namely semantic relevance, topical coherence, and coreference linking, are constructed for explicitly capturing the …

Go to article

Learning Topological Representations With Bidirectional Graph Attention Network For Solving Job Shop Scheduling Problem, Cong Zhang, Zhiguang Cao, Yaoxin Wu, Wen Song, Jing Sun Jul 2024

Learning Topological Representations With Bidirectional Graph Attention Network For Solving Job Shop Scheduling Problem, Cong Zhang, Zhiguang Cao, Yaoxin Wu, Wen Song, Jing Sun

Research Collection School Of Computing and Information Systems

Existing learning-based methods for solving job shop scheduling problems (JSSP) usually use off-the-shelf GNN models tailored to undirected graphs and neglect the rich and meaningful topological structures of disjunctive graphs (DGs). This paper proposes the topology-aware bidirectional graph attention network (TBGAT), a novel GNN architecture based on the attention mechanism, to embed the DG for solving JSSP in a local search framework. Specifically, TBGAT embeds the DG from a forward and a backward view, respectively, where the messages are propagated by following the different topologies of the views and aggregated via graph attention. Then, we propose a novel operator based …

Go to article

How People Prompt Generative Ai To Create Interactive Vr Scenes, Setareh Aghel Manesh, Tianyi Zhang, Yuki Onishi, Kotaro Hara, Scott Bateman, Jiannan Li, Anthony Tang Jul 2024

How People Prompt Generative Ai To Create Interactive Vr Scenes, Setareh Aghel Manesh, Tianyi Zhang, Yuki Onishi, Kotaro Hara, Scott Bateman, Jiannan Li, Anthony Tang

Research Collection School Of Computing and Information Systems

Generative AI tools can provide people with the ability to create virtual environments and scenes with natural language prompts. Yet, how people will formulate such prompts is unclear---particularly when they inhabit the environment that they are designing. For instance, it is likely that a person might say, "Put a chair here,'' while pointing at a location. If such linguistic and embodied features are common to people's prompts, we need to tune models to accommodate them. In this work, we present a Wizard of Oz elicitation study with 22 participants, where we studied people's implicit expectations when verbally prompting such programming …

Go to article

Certified Robust Accuracy Of Neural Networks Are Bounded Due To Bayes Errors, Ruihan Zhang, Jun Sun Jul 2024

Certified Robust Accuracy Of Neural Networks Are Bounded Due To Bayes Errors, Ruihan Zhang, Jun Sun

Research Collection School Of Computing and Information Systems

Adversarial examples pose a security threat to many critical systems built on neural networks. While certified training improves robustness, it also decreases accuracy noticeably. Despite various proposals for addressing this issue, the significant accuracy drop remains. More importantly, it is not clear whether there is a certain fundamental limit on achieving robustness whilst maintaining accuracy. In this work, we offer a novel perspective based on Bayes errors. By adopting Bayes error to robustness analysis, we investigate the limit of certified robust accuracy, taking into account data distribution uncertainties. We first show that the accuracy inevitably decreases in the pursuit of …

Go to article

An Exploratory Study Of Conventional Machine Learning And Large Language Models For Sentiment Analysis, Cui Zou, Jingyuan Cai, Langtao Chen, Fiona Fui-Hoon Nah Jul 2024

An Exploratory Study Of Conventional Machine Learning And Large Language Models For Sentiment Analysis, Cui Zou, Jingyuan Cai, Langtao Chen, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Sentiment analysis is the use of natural language processing to identify affective states and determine people’s opinions in various analytical applications such as customer reviews and social media analyses. Large language models (LLMs) such as GPT-4o demonstrate impressive performance in text generation tasks. Despite numerous studies in the extant literature, few have compared the performance of conventional machine learning models with LLMs for sentiment analysis. This study aims to fill this gap by conducting an evaluation of these models using a balanced dataset of 2,000 IMDb movie reviews. Our study shows that GPT-4o achieves the highest performance, while GPT-3.5 and …

Go to article

A Computational Aesthetic Design Science Study On Online Video Based On Triple-Dimensional Multimodal Analysis, Zhangguang Kang, Fiona Fui-Hoon Nah, Keng Siau Jul 2024

A Computational Aesthetic Design Science Study On Online Video Based On Triple-Dimensional Multimodal Analysis, Zhangguang Kang, Fiona Fui-Hoon Nah, Keng Siau

Research Collection School Of Computing and Information Systems

Computational video aesthetic prediction refers to using models that automatically evaluate the features of videos to produce their aesthetic scores. Current video aesthetic prediction models are designed based on bimodal frameworks. To address their limitations, we developed the Triple-Dimensional Multimodal Temporal Video Aesthetic neural network (TMTVA-net) model. The Long Short-Term Memory (LSTM) forms the conceptual foundation for the design framework. In the multimodal transformer layer, we employed two distinct transformers: the multimodal transformer and the feature transformer, enabling the acquisition of modality-specific patterns and representational features uniquely adapted to each modality. The fusion layer has also been redesigned to compute …

Go to article

Understanding And Fighting Scams: Media, Language, Appeals And Effects, Shuhua Zhou, Xiao Fan Liu, Fiona Fui-Hoon Nah, S. Harrison, X. Zhang, S. Zhen, D. Yeung, J. Hsiao, R. Lc, A. Chan, X. Wang, C. Jiang, F. Lin, J. Li, A. Wong, L. Chan, B. George, P. Li Jul 2024

Understanding And Fighting Scams: Media, Language, Appeals And Effects, Shuhua Zhou, Xiao Fan Liu, Fiona Fui-Hoon Nah, S. Harrison, X. Zhang, S. Zhen, D. Yeung, J. Hsiao, R. Lc, A. Chan, X. Wang, C. Jiang, F. Lin, J. Li, A. Wong, L. Chan, B. George, P. Li

Research Collection School Of Computing and Information Systems

Scams are fraudulent activities aiming to deceive individuals into relinquishing money, property, or rights, and they have proliferated in the context of widespread misinformation and disinformation. In this paper, we propose strategies and a research plan to address key questions about the exploitation of new communication technologies by scammers, the prevalence and nature of different scam types, and the language characteristics and appeals used in scamming content. We aim to develop a comprehensive taxonomy of scams and identify factors that contribute to their persuasiveness. Additionally, we propose the use of advanced technologies, including artificial intelligence, physiological measures, and brain mapping, …

Go to article

Hierarchical Damage Correlations For Old Photo Restoration, Weiwei Cai, Xuemiao Xu, Jiajia Xu, Huaidong Zhang, Haoxin Yang, Kun Zhang, Shengfeng He Jul 2024

Hierarchical Damage Correlations For Old Photo Restoration, Weiwei Cai, Xuemiao Xu, Jiajia Xu, Huaidong Zhang, Haoxin Yang, Kun Zhang, Shengfeng He

Research Collection School Of Computing and Information Systems

Restoring old photographs can preserve cherished memories. Previous methods handled diverse damages within the same network structure, which proved impractical. In addition, these methods cannot exploit correlations among artifacts, especially in scratches versus patch-misses issues. Hence, a tailored network is particularly crucial. In light of this, we propose a unified framework consisting of two key components: ScratchNet and PatchNet. In detail, ScratchNet employs the parallel Multi-scale Partial Convolution Module to effectively repair scratches, learning from multi-scale local receptive fields. In contrast, the patch-misses necessitate the network to emphasize global information. To this end, we incorporate a transformer-based encoder and decoder …

Go to article

Evilscreen Attack: Smart Tv Hijacking Via Multi-Channel Remote Control Mimicry, Yiwei Zhang, Siqi Ma, Tiancheng Chen, Juanru Li, Robert H. Deng, Elisa Bertino Jul 2024

Evilscreen Attack: Smart Tv Hijacking Via Multi-Channel Remote Control Mimicry, Yiwei Zhang, Siqi Ma, Tiancheng Chen, Juanru Li, Robert H. Deng, Elisa Bertino

Research Collection School Of Computing and Information Systems

Modern smart TVs often communicate with their remote controls (including the smartphone simulated ones) using multiple wireless channels (e.g., Infrared, Bluetooth, and Wi-Fi). However, this multi-channel remote control communication introduces a new attack surface. An inherent security flaw is that remote controls of most smart TVs are designed to work in a benign environment rather than an adversarial one, and thus wireless communications between a smart TV and its remote controls are not strongly protected. Attackers can leverage such a flaw to abuse the remote control communication and compromise smart TV systems. In this paper, we propose EvilScreen, a novel …

Go to article

Jigsaw: Edge-Based Streaming Perception Over Spatially Overlapped Multi-Camera Deployments, Ila Gokarn, Yigong Hu, Tarek Abdelzaher, Archan Misra Jul 2024

Jigsaw: Edge-Based Streaming Perception Over Spatially Overlapped Multi-Camera Deployments, Ila Gokarn, Yigong Hu, Tarek Abdelzaher, Archan Misra

Research Collection School Of Computing and Information Systems

We present JIGSAW, a novel system that performs edge-based streaming perception over multiple video streams, while additionally factoring in the redundancy offered by the spatial overlap often exhibited in urban, multi-camera deployments. To assure high streaming throughput, JIGSAW extracts and spatially multiplexes multiple regions-of-interest from different camera frames into a smaller canvas frame. Moreover, to ensure that perception stays abreast of evolving object kinematics, JIGSAW includes a utility-based weighted scheduler to preferentially prioritize and even skip object-specific tiles extracted from an incoming stream of camera frames. Using the CityflowV2 traffic surveillance dataset, we show that JIGSAW can simultaneously process 25 …

Go to article

Violet: Visual Analytics For Explainable Quantum Neural Networks, Shaolun Ruan, Zhiding Liang, Qiang Guan, Paul Robert Griffin, Xiaolin Wen, Yanna Lin, Yong Wang Jun 2024

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 …

Go to article

Efficient Cross-Modal Video Retrieval With Meta-Optimized Frames, Ning Han, Xun Yang, Ee-Peng Lim, Hao Chen, Qianru Sun Jun 2024

Efficient Cross-Modal Video Retrieval With Meta-Optimized Frames, Ning Han, Xun Yang, Ee-Peng Lim, Hao Chen, Qianru Sun

Research Collection School Of Computing and Information Systems

Cross-modal video retrieval aims to retrieve semantically relevant videos when given a textual query, and is one of the fundamental multimedia tasks. Most top-performing methods primarily leverage Vision Transformer (ViT) to extract video features [1]-[3]. However, they suffer from the high computational complexity of ViT, especially when encoding long videos. A common and simple solution is to uniformly sample a small number (e.g., 4 or 8) of frames from the target video (instead of using the whole video) as ViT inputs. The number of frames has a strong influence on the performance of ViT, e.g., using 8 frames yields better …

Go to article

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 Jun 2024

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, …

Go to article

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 Jun 2024

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 …

Go to article

Improving Interpretable Embeddings For Ad-Hoc Video Search With Generative Captions And Multi-Word Concept Bank, Jiaxin Wu, Chong-Wah Ngo, Wing-Kwong Chan Jun 2024

Improving Interpretable Embeddings For Ad-Hoc Video Search With Generative Captions And Multi-Word Concept Bank, Jiaxin Wu, Chong-Wah Ngo, Wing-Kwong Chan

Research Collection School Of Computing and Information Systems

Aligning a user query and video clips in cross-modal latent space and that with semantic concepts are two mainstream approaches for ad-hoc video search (AVS). However, the effectiveness of existing approaches is bottlenecked by the small sizes of available video-text datasets and the low quality of concept banks, which results in the failures of unseen queries and the out-of-vocabulary problem. This paper addresses these two problems by constructing a new dataset and developing a multi-word concept bank. Specifically, capitalizing on a generative model, we construct a new dataset consisting of 7 million generated text and video pairs for pre-training. To …

Go to article

Generalized Graph Prompt: Toward A Unification Of Pre-Training And Downstream Tasks On Graphs, Xingtong Yu, Zhenghao Liu, Yuan Fang, Et Al. Jun 2024

Generalized Graph Prompt: Toward A Unification Of Pre-Training And Downstream Tasks On Graphs, Xingtong Yu, Zhenghao Liu, Yuan Fang, Et Al.

Research Collection School Of Computing and Information Systems

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks (GNNs) have emerged as a powerful tool for graph representation learning, in an end-to-end supervised setting, their performance heavily relies on a large amount of task-specific supervision. To reduce labeling requirement, the 'pre-train, fine-tune' and 'pre-train, prompt' paradigms have become increasingly common. In particular, prompting is a popular alternative to fine-tuning in natural language processing, which is designed to narrow the gap between pre-training and downstream objectives in a task-specific manner. However, existing study of …

Go to article

Open-Vocabulary Video Anomaly Detection, Peng Wu, Xuerong Zhou, Guansong Pang, Yujia Sun, Jing Liu, Peng Wang, Yanning Zhang Jun 2024

Open-Vocabulary Video Anomaly Detection, Peng Wu, Xuerong Zhou, Guansong Pang, Yujia Sun, Jing Liu, Peng Wang, Yanning Zhang

Research Collection School Of Computing and Information Systems

Current video anomaly detection (VAD) approaches with weak supervisions are inherently limited to a closed-set setting and may struggle in open-world applications where there can be anomaly categories in the test data unseen during training. A few recent studies attempt to tackle a more realistic setting, open-set VAD, which aims to de-tect unseen anomalies given seen anomalies and normal videos. However, such a setting focuses on predicting frame anomaly scores, having no ability to recognize the specific categories of anomalies, despite the fact that this ability is essential for building more informed video surveillance systems. This paper takes a step …

Go to article

Drag Your Noise: Interactive Point-Based Editing Via Diffusion Semantic Propagation, Haofeng Liu, Chenshu Xu, Yifei Yang, Lihua Zeng, Shengfeng He Jun 2024

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 …

Go to article

Beyond Textual Constraints : Learning Novel Diffusion Conditions With Fewer Examples, Yuyang Yu, Bangzhen Liu, Chenxi Zheng, Xuemiao Xu, Huaidong Zhang, Shengfeng He Jun 2024

Beyond Textual Constraints : Learning Novel Diffusion Conditions With Fewer Examples, Yuyang Yu, Bangzhen Liu, Chenxi Zheng, Xuemiao Xu, Huaidong Zhang, Shengfeng He

Research Collection School Of Computing and Information Systems

In this paper, we delve into a novel aspect of learning novel diffusion conditions with datasets an order of magnitude smaller. The rationale behind our approach is the elimination of textual constraints during the few-shot learning process. To that end, we implement two optimization strategies. The first, prompt-free conditional learning, utilizes a prompt-free encoder derived from a pre-trained Stable Diffusion model. This strategy is designed to adapt new conditions to the diffusion process by minimizing the textual-visual cor-relation, thereby ensuring a more precise alignment between the generated content and the specified conditions. The second strategy entails condition-specific negative rectification, which …

Go to article

Learning With Unreliability : Fast Few-Shot Voxel Radiance Fields With Relative Geometric Consistency, Yingjie Xu, Bangzhen Liu, Hao Tang, Bailin Deng, Shengfeng He Jun 2024

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 …

Go to article

D3still : Decoupled Differential Distillation For Asymmetric Image Retrieval, Yi Xie, Yihong Lin, Wenjie Cai, Xuemiao Xu, Huaidong Zhang, Yong Du, Shengfeng He Jun 2024

D3still : Decoupled Differential Distillation For Asymmetric Image Retrieval, Yi Xie, Yihong Lin, Wenjie Cai, Xuemiao Xu, Huaidong Zhang, Yong Du, Shengfeng He

Research Collection School Of Computing and Information Systems

Existing methods for asymmetric image retrieval employ a rigid pairwise similarity constraint between the query network and the larger gallery network. However, these oneto-one constraint approaches often fail to maintain retrieval order consistency, especially when the query network has limited representational capacity. To overcome this problem, we introduce the Decoupled Differential Distillation (D3still) framework. This framework shifts from absolute one-to-one supervision to optimizing the relational differences in pairwise similarities produced by the query and gallery networks, thereby preserving a consistent retrieval order across both networks. Our method involves computing a pairwise similarity differential matrix within the gallery domain, which is …

Go to article

Rethinking Multi-View Representation Learning Via Distilled Disentangling, Guanzhou Ke, Bo Wang, Xiaoli Wang, Shengfeng He Jun 2024

Rethinking Multi-View Representation Learning Via Distilled Disentangling, Guanzhou Ke, Bo Wang, Xiaoli Wang, Shengfeng He

Research Collection School Of Computing and Information Systems

Multi-view representation learning aims to derive robust representations that are both view-consistent and view-specific from diverse data sources. This paper presents an in-depth analysis of existing approaches in this domain, highlighting a commonly overlooked aspect: the redundancy between view-consistent and view-specific representations. To this end, we propose an innovative framework for multi-view representation learning, which incorporates a technique we term 'distilled disentangling'. Our method introduces the concept of masked cross-view prediction, enabling the extraction of compact, high-quality view-consistent representations from various sources without incurring extra computational overhead. Additionally, we develop a distilled disentangling module that efficiently filters out consistency-related information …

Go to article

Inceptionnext: When Inception Meets Convnext, Weihao Yu, Pan Zhou, Shuicheng Yan, Xinchao Wang Jun 2024

Inceptionnext: When Inception Meets Convnext, Weihao Yu, Pan Zhou, Shuicheng Yan, Xinchao Wang

Research Collection School Of Computing and Information Systems

Inspired by the long-range modeling ability of ViTs, large-kernel convolutions are widely studied and adopted recently to enlarge the receptive field and improve model performance, like the remarkable work ConvNeXt which employs 7×7 depthwise convolution. Although such depthwise operator only consumes a few FLOPs, it largely harms the model efficiency on powerful computing devices due to the high memory access costs. For example, ConvNeXtT has similar FLOPs with ResNet-50 but only achieves ∼ 60% throughputs when trained on A100 GPUs with full precision. Although reducing the kernel size of ConvNeXt can improve speed, it results in significant performance degradation, which …

Go to article

Consistent3d: Towards Consistent High-Fidelity Text-To-3d Generation With Deterministic Sampling Prior, Zike Wu, Pan Zhou, Xuanyu Yi, Xiaoding Yuan, Hanwang Zhang Jun 2024

Consistent3d: Towards Consistent High-Fidelity Text-To-3d Generation With Deterministic Sampling Prior, Zike Wu, Pan Zhou, Xuanyu Yi, Xiaoding Yuan, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Score distillation sampling (SDS) and its variants have greatly boosted the development of text-to-3D generation, but are vulnerable to geometry collapse and poor textures yet. To solve this issue, we first deeply analyze the SDS and find that its distillation sampling process indeed corresponds to the trajectory sampling of a stochastic differential equation (SDE): SDS samples along an SDE trajectory to yield a less noisy sample which then serves as a guidance to optimize a 3D model. However, the randomness in SDE sampling often leads to a diverse and unpredictable sample which is not always less noisy, and thus is …

Go to article

Let’S Think Outside The Box: Exploring Leap-Of-Thought In Large Language Models With Multimodal Humor Generation, Shanshan Zhong, Zhongzhan Huang, Shanghua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, Pan Zhou Jun 2024

Let’S Think Outside The Box: Exploring Leap-Of-Thought In Large Language Models With Multimodal Humor Generation, Shanshan Zhong, Zhongzhan Huang, Shanghua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, Pan Zhou

Research Collection School Of Computing and Information Systems

Chain-of-Thought (CoT) [2, 3] guides large language models (LLMs) to reason step-by-step, and can motivate their logical reasoning ability. While effective for logical tasks, CoT is not conducive to creative problem-solving which often requires out-of-box thoughts and is crucial for innovation advancements. In this paper, we explore the Leap-of-Thought (LoT) abilities within LLMs — a nonsequential, creative paradigm involving strong associations and knowledge leaps. To this end, we study LLMs on the popular Oogiri game which needs participants to have good creativity and strong associative thinking for responding unexpectedly and humorously to the given image, text, or both, and thus …

Go to article

Few-Shot Learner Parameterization By Diffusion Time-Steps, Zhongqi Yue, Pan Zhou, Richang Hong, Hanwang Zhang, Sun Qianru Jun 2024

Few-Shot Learner Parameterization By Diffusion Time-Steps, Zhongqi Yue, Pan Zhou, Richang Hong, Hanwang Zhang, Sun Qianru

Research Collection School Of Computing and Information Systems

Even when using large multi-modal foundation models, few-shot learning is still challenging—if there is no proper inductive bias, it is nearly impossible to keep the nuanced class attributes while removing the visually prominent attributes that spuriously correlate with class labels. To this end, we find an inductive bias that the time-steps of a Diffusion Model (DM) can isolate the nuanced class attributes, i.e., as the forward diffusion adds noise to an image at each time-step, nuanced attributes are usually lost at an earlier time-step than the spurious attributes that are visually prominent. Building on this, we propose Time-step Few-shot (TiF) …

Go to article

Diffusion Time-Step Curriculum For One Image To 3d Generation, Xuanyu Yi, Zike Wu, Qingshan Xu, Pan Zhou, Joo Hwee Lim, Hanwang Zhang Jun 2024

Diffusion Time-Step Curriculum For One Image To 3d Generation, Xuanyu Yi, Zike Wu, Qingshan Xu, Pan Zhou, Joo Hwee Lim, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Score distillation sampling (SDS) has been widely adopted to overcome the absence of unseen views in reconstructing 3D objects from a single image. It leverages pretrained 2D diffusion models as teacher to guide the reconstruction of student 3D models. Despite their remarkable success, SDS-based methods often encounter geometric artifacts and texture saturation. We find out the crux is the overlooked indiscriminate treatment of diffusion time-steps during optimization: it unreasonably treats the studentteacher knowledge distillation to be equal at all time-steps and thus entangles coarse-grained and fine-grained modeling. Therefore, we propose the Diffusion Time-step Curriculum one-image-to-3D pipeline (DTC123), which involves both …

Go to article

Jollygesture: Exploring Dual-Purpose Gestures In Vr Presentations, Gun Woo Warren Park, Anthony Tang, Fanny Chevalier Jun 2024

Jollygesture: Exploring Dual-Purpose Gestures In Vr Presentations, Gun Woo Warren Park, Anthony Tang, Fanny Chevalier

Research Collection School Of Computing and Information Systems

Virtual reality (VR) offers new opportunities for presenters to use expressive body language to engage their audience. Yet, most VR presentation systems have adopted control mechanisms that mimic those found in face-to-face presentation systems. We explore the use of gestures that have dual-purpose: first, for the audience, a communicative purpose; second, for the presenter, a control purpose to alter content in slides. To support presenters, we provide guidance on what gestures are available and their effects. We realize our design approach in JollyGesture, a VR technology probe that recognizes dual-purpose gestures in a presentation scenario. We evaluate our approach through …

Go to article

Deep Reinforcement Learning Guided Improvement Heuristic For Job Shop Scheduling, Cong Zhang, Zhiguang Cao, Wen Song, Yaoxin Wu, Jie Zhang May 2024

Deep Reinforcement Learning Guided Improvement Heuristic For Job Shop Scheduling, Cong Zhang, Zhiguang Cao, Wen Song, Yaoxin Wu, Jie Zhang

Research Collection School Of Computing and Information Systems

Recent studies in using deep reinforcement learning (DRL) to solve Job-shop scheduling problems (JSSP) focus on construction heuristics. However, their performance is still far from optimality, mainly because the underlying graph representation scheme is unsuitable for modelling partial solutions at each construction step. This paper proposes a novel DRL-guided improvement heuristic for solving JSSP, where graph representation is employed to encode complete solutions. We design a Graph-Neural-Network-based representation scheme, consisting of two modules to effectively capture the information of dynamic topology and different types of nodes in graphs encountered during the improvement process. To speed up solution evaluation during improvement, …

Go to article

First Prev Next Last