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

Graphics and Human Computer Interfaces Commons™

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

Singapore Management University

Discipline
Keyword
Publication Year
Publication
Publication Type

Articles 241 - 270 of 959

Full-Text Articles in Graphics and Human Computer Interfaces

From Canteen Food To Daily Meals: Generalizing Food Recognition To More Practical Scenarios, Guoshan Liu, Yang Jiao, Jingjing Chen, Bin Zhu, Yu-Gang Jiang Feb 2024

From Canteen Food To Daily Meals: Generalizing Food Recognition To More Practical Scenarios, Guoshan Liu, Yang Jiao, Jingjing Chen, Bin Zhu, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

The precise recognition of food categories plays a pivotal role for intelligent health management, attracting significant research attention in recent years. Prominent benchmarks, such as Food-101 and VIREO Food-172, provide abundant food image resources that catalyze the prosperity of research in this field. Nevertheless, these datasets are well-curated from canteen scenarios and thus deviate from food appearances in daily life. This discrepancy poses great challenges in effectively transferring classifiers trained on these canteen datasets to broader daily-life scenarios encountered by humans. Toward this end, we present two new benchmarks, namely DailyFood-172 and DailyFood-16, specifically designed to curate food images from …

Go to article

Out-Of-Distribution Detection In Long-Tailed Recognition With Calibrated Outlier Class Learning, Wenjun Miao, Guansong Pang, Xiao Bai, Tianqi Li, Jin Zheng Feb 2024

Out-Of-Distribution Detection In Long-Tailed Recognition With Calibrated Outlier Class Learning, Wenjun Miao, Guansong Pang, Xiao Bai, Tianqi Li, Jin Zheng

Research Collection School Of Computing and Information Systems

Existing out-of-distribution (OOD) methods have shown great success on balanced datasets but become ineffective in long-tailed recognition (LTR) scenarios where 1) OOD samples are often wrongly classified into head classes and/or 2) tail-class samples are treated as OOD samples. To address these issues, current studies fit a prior distribution of auxiliary/pseudo OOD data to the long-tailed in-distribution (ID) data. However, it is difficult to obtain such an accurate prior distribution given the unknowingness of real OOD samples and heavy class imbalance in LTR. A straightforward solution to avoid the requirement of this prior is to learn an outlier class to …

Go to article

Vadclip: Adapting Vision-Language Models For Weakly Supervised Video Anomaly Detection, Peng Wu, Xuerong Zhou, Guansong Pang, Lingru Zhou, Qingsen Yan, Peng Wang, Yanning Zhang Feb 2024

Vadclip: Adapting Vision-Language Models For Weakly Supervised Video Anomaly Detection, Peng Wu, Xuerong Zhou, Guansong Pang, Lingru Zhou, Qingsen Yan, Peng Wang, Yanning Zhang

Research Collection School Of Computing and Information Systems

The recent contrastive language-image pre-training (CLIP) model has shown great success in a wide range of image-level tasks, revealing remarkable ability for learning powerful visual representations with rich semantics. An open and worthwhile problem is efficiently adapting such a strong model to the video domain and designing a robust video anomaly detector. In this work, we propose VadCLIP, a new paradigm for weakly supervised video anomaly detection (WSVAD) by leveraging the frozen CLIP model directly without any pre-training and fine-tuning process. Unlike current works that directly feed extracted features into the weakly supervised classifier for frame-level binary classification, VadCLIP makes …

Go to article

Hackles: Simulating And Visually Representing The Anxiety Of Walking Alone, Sydney Pratte, Anthony Tang, Shannon Hoover, Lora Oehlberg Feb 2024

Hackles: Simulating And Visually Representing The Anxiety Of Walking Alone, Sydney Pratte, Anthony Tang, Shannon Hoover, Lora Oehlberg

Research Collection School Of Computing and Information Systems

In this work, we compare the designs of two fashion-tech garments that communicate the anxiety felt when walking alone. While the two garments share a common vision, they are designed to be worn in two radically different settings and to communicate to different audiences: one directly communicates an empathetic experience to its wearer; the other a model wears at a runway show and must share its story to a general audience. We used Research Through Design (RtD) methods to design both fashion-tech garments. Then, we recorded and analyzed the design process for both garments via an annotated portfolio to compare …

Go to article

Foodmask: Real-Time Food Instance Counting, Segmentation And Recognition, Huu-Thanh Nguyen, Yu Cao, Chong-Wah Ngo, Wing-Kwong Chan Feb 2024

Foodmask: Real-Time Food Instance Counting, Segmentation And Recognition, Huu-Thanh Nguyen, Yu Cao, Chong-Wah Ngo, Wing-Kwong Chan

Research Collection School Of Computing and Information Systems

Food computing has long been studied and deployed to several applications. Understanding a food image at the instance level, including recognition, counting and segmentation, is essential to quantifying nutrition and calorie consumption. Nevertheless, existing techniques are limited to either category-specific instance detection, which does not reflect precisely the instance size at the pixel level, or category-agnostic instance segmentation, which is insufficient for dish recognition. This paper presents a compact and fast multi-task network, namely FoodMask, for clustering-based food instance counting, segmentation and recognition. The network learns a semantic space simultaneously encoding food category distribution and instance height at pixel basis. …

Go to article

Catnet: Cross-Modal Fusion For Audio-Visual Speech Recognition, Xingmei Wang, Jianchen Mi, Boquan Li, Yixu Zhao, Jiaxiang Meng Feb 2024

Catnet: Cross-Modal Fusion For Audio-Visual Speech Recognition, Xingmei Wang, Jianchen Mi, Boquan Li, Yixu Zhao, Jiaxiang Meng

Research Collection School Of Computing and Information Systems

Automatic speech recognition (ASR) is a typical pattern recognition technology that converts human speeches into texts. With the aid of advanced deep learning models, the performance of speech recognition is significantly improved. Especially, the emerging Audio–Visual Speech Recognition (AVSR) methods achieve satisfactory performance by combining audio-modal and visual-modal information. However, various complex environments, especially noises, limit the effectiveness of existing methods. In response to the noisy problem, in this paper, we propose a novel cross-modal audio–visual speech recognition model, named CATNet. First, we devise a cross-modal bidirectional fusion model to analyze the close relationship between audio and visual modalities. Second, …

Go to article

Delving Into Multimodal Prompting For Fine-Grained Visual Classification, Xin Jiang, Hao Tang, Junyao Gao, Xiaoyu Du, Shengfeng He, Zechao Li Feb 2024

Delving Into Multimodal Prompting For Fine-Grained Visual Classification, Xin Jiang, Hao Tang, Junyao Gao, Xiaoyu Du, Shengfeng He, Zechao Li

Research Collection School Of Computing and Information Systems

Fine-grained visual classification (FGVC) involves categorizing fine subdivisions within a broader category, which poses challenges due to subtle inter-class discrepancies and large intra-class variations. However, prevailing approaches primarily focus on uni-modal visual concepts. Recent advancements in pre-trained vision-language models have demonstrated remarkable performance in various high-level vision tasks, yet the applicability of such models to FGVC tasks remains uncertain. In this paper, we aim to fully exploit the capabilities of cross-modal description to tackle FGVC tasks and propose a novel multimodal prompting solution, denoted as MP-FGVC, based on the contrastive language-image pertaining (CLIP) model. Our MP-FGVC comprises a multimodal prompts …

Go to article

Learning From Machines: How Negative Feedback From Machines Improves Learning Between Humans, Tengjian Zou, Gokhan Ertug, Thomas Roulet Feb 2024

Learning From Machines: How Negative Feedback From Machines Improves Learning Between Humans, Tengjian Zou, Gokhan Ertug, Thomas Roulet

Research Collection Lee Kong Chian School Of Business

Prior studies on learning from failure primarily focus on how individuals learn from failure feedback given by other individuals. It is unclear whether and how the advent of machine feedback may influence individuals’ learning from failures. We suggest that failure feedback provided by machines facilitates learning in two ways. First, it focuses individuals’ attention on their failures, leading them to learn from these failures. Second, it serves as a catalyzer, motivating individuals to learn more from failure feedback given to them by other individuals as well. In addition, this catalyzing effect is stronger if the failure feedback from machines and …

Go to article

Leveraging Llms And Generative Models For Interactive Known-Item Video Search, Zhixin Ma, Jiaxin Wu, Chong-Wah Ngo Feb 2024

Leveraging Llms And Generative Models For Interactive Known-Item Video Search, Zhixin Ma, Jiaxin Wu, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

While embedding techniques such as CLIP have considerably boosted search performance, user strategies in interactive video search still largely operate on a trial-and-error basis. Users are often required to manually adjust their queries and carefully inspect the search results, which greatly rely on the users’ capability and proficiency. Recent advancements in large language models (LLMs) and generative models offer promising avenues for enhancing interactivity in video retrieval and reducing the personal bias in query interpretation, particularly in the known-item search. Specifically, LLMs can expand and diversify the semantics of the queries while avoiding grammar mistakes or the language barrier. In …

Go to article

Simple Image-Level Classification Improves Open-Vocabulary Object Detection, Ruohuan Fang, Guansong Pang, Xiao Bai Feb 2024

Simple Image-Level Classification Improves Open-Vocabulary Object Detection, Ruohuan Fang, Guansong Pang, Xiao Bai

Research Collection School Of Computing and Information Systems

Open-Vocabulary Object Detection (OVOD) aims to detect novel objects beyond a given set of base categories on which the detection model is trained. Recent OVOD methods focus on adapting the image-level pre-trained vision-language models (VLMs), such as CLIP, to a region-level object detection task via, eg., region-level knowledge distillation, regional prompt learning, or region-text pre-training, to expand the detection vocabulary. These methods have demonstrated remarkable performance in recognizing regional visual concepts, but they are weak in exploiting the VLMs' powerful global scene understanding ability learned from the billion-scale image-level text descriptions. This limits their capability in detecting hard objects of …

Go to article

Predicting Viral Rumors And Vulnerable Users With Graph-Based Neural Multi-Task Learning For Infodemic Surveillance, Xuan Zhang, Wei Gao Jan 2024

Predicting Viral Rumors And Vulnerable Users With Graph-Based Neural Multi-Task Learning For Infodemic Surveillance, Xuan Zhang, Wei Gao

Research Collection School Of Computing and Information Systems

In the age of the infodemic, it is crucial to have tools for effectively monitoring the spread of rampant rumors that can quickly go viral, as well as identifying vulnerable users who may be more susceptible to spreading such misinformation. This proactive approach allows for timely preventive measures to be taken, mitigating the negative impact of false information on society. We propose a novel approach to predict viral rumors and vulnerable users using a unified graph neural network model. We pre-train network-based user embeddings and leverage a cross-attention mechanism between users and posts, together with a community-enhanced vulnerability propagation (CVP) …

Go to article

Tracking People Across Ultra Populated Indoor Spaces By Matching Unreliable Wi-Fi Signals With Disconnected Video Feeds, Quang Hai Truong, Dheryta Jaisinghani, Shubham Jain, Arunesh Sinha, Jeong Gil Ko, Rajesh Krishna Balan Jan 2024

Tracking People Across Ultra Populated Indoor Spaces By Matching Unreliable Wi-Fi Signals With Disconnected Video Feeds, Quang Hai Truong, Dheryta Jaisinghani, Shubham Jain, Arunesh Sinha, Jeong Gil Ko, Rajesh Krishna Balan

Research Collection School Of Computing and Information Systems

Tracking in dense indoor environments where several thousands of people move around is an extremely challenging problem. In this paper, we present a system — DenseTrack for tracking people in such environments. DenseTrack leverages data from the sensing modalities that are already present in these environments — Wi-Fi (from enterprise network deployments) and Video (from surveillance cameras). We combine Wi-Fi information with video data to overcome the individual errors induced by these modalities. More precisely, the locations derived from video are used to overcome the localization errors inherent in using Wi-Fi signals where precise Wi-Fi MAC IDs are used to …

Go to article

Demonstrating Canvas-Based Processing Of Multiple Camera Streams At The Edge, Ila Gokarn, Hemanth Sabbella, Yigong Hu, Tarek Abdelzaher, Archan Misra Jan 2024

Demonstrating Canvas-Based Processing Of Multiple Camera Streams At The Edge, Ila Gokarn, Hemanth Sabbella, Yigong Hu, Tarek Abdelzaher, Archan Misra

Research Collection School Of Computing and Information Systems

We demonstrate criticality-aware canvas-based processing of multiple concurrent camera streams at the resource constrained edge to show substantial improvement in the accuracy-throughput trade-off. The proposed system focuses the available computation resources on select Regions of Interest (RoI) across all the camera streams by (i) extracting RoI from the input camera stream (ii) 2D bin packing the RoI on a canvas frame and (iii) batching and inferring upon these constructed composite canvas frames with a YOLOv5 object detection model. Our experiments show that such canvas-based processing can (i) sustain real-time processing throughput of 23 FPS per camera across 6 concurrent input …

Go to article

Effects Of Mindfulness And Emotion Regulation On Aesthetics: A Theoretical Model From Hedonic Perspective Of Processing Fluency, Geng-Bao Lin, Fiona Fui-Hoon Nah, Choon Ling Sia Jan 2024

Effects Of Mindfulness And Emotion Regulation On Aesthetics: A Theoretical Model From Hedonic Perspective Of Processing Fluency, Geng-Bao Lin, Fiona Fui-Hoon Nah, Choon Ling Sia

Research Collection School Of Computing and Information Systems

Research has shown that processing fluency positively impacts perceived aesthetics, with pleasure mediating the relationship. Considering the important role of pleasure, we propose studying the role of emotion regulation in moderating the mediated relationship from processing fluency to perceived aesthetics. Based on our hypotheses, individuals’ emotion regulation strategies are expected to have moderating effects on the relationship between processing fluency and perceived aesthetics such that cognitive reappraisal positively moderates the relationship from processing fluency to pleasure, and expressive suppression negatively moderates the relationship from pleasure to perceived aesthetics. Trait mindfulness is also expected to influence perceived aesthetics through emotion regulation …

Go to article

Trust: The Feature That Vending Machines And Atms Share, But Simplygo Lacks, Sun Sun Lim Jan 2024

Trust: The Feature That Vending Machines And Atms Share, But Simplygo Lacks, Sun Sun Lim

Research Collection College of Integrative Studies

The article discussed the intricacies of trust in the SimplyGo debacle and highlighted how the design of physical interfaces like vending machines and ATMs and digital interfaces from apps like Grab, Parking.sg and ShopBack have critical features to instil trust. People need to be reassured that their transactions have proceeded as they should, and thay have not been short-changed.

Go to article

Glance To Count: Learning To Rank With Anchors For Weakly-Supervised Crowd Counting, Zheng Xiong, Liangyu Chai, Wenxi Liu, Yongtuo Liu, Sucheng Ren, Shengfeng He Jan 2024

Glance To Count: Learning To Rank With Anchors For Weakly-Supervised Crowd Counting, Zheng Xiong, Liangyu Chai, Wenxi Liu, Yongtuo Liu, Sucheng Ren, Shengfeng He

Research Collection School Of Computing and Information Systems

Crowd image is arguably one of the most laborious data to annotate. In this paper, we devote to reduce the massive demand of densely labeled crowd data, and propose a novel weakly-supervised setting, in which we leverage the binary ranking of two images with highcontrast crowd counts as training guidance. To enable training under this new setting, we convert the crowd count regression problem to a ranking potential prediction problem. In particular, we tailor a Siamese Ranking Network that predicts the potential scores of two images indicating the ordering of the counts. Hence, the ultimate goal is to assign appropriate …

Go to article

Dynamic Meta-Path Guided Temporal Heterogeneous Graph Neural Networks, Yugang Ji, Chuan Shi, Yuan Fang Jan 2024

Dynamic Meta-Path Guided Temporal Heterogeneous Graph Neural Networks, Yugang Ji, Chuan Shi, Yuan Fang

Research Collection School Of Computing and Information Systems

Graph Neural Networks (GNNs) have become the de facto standard for representation learning on topological graphs, which usually derive effective node representations via message passing from neighborhoods. Although GNNs have achieved great success, previous models are mostly confined to static and homogeneous graphs. However, there are multiple dynamic interactions between different-typed nodes in real-world scenarios like academic networks and e-commerce platforms, forming temporal heterogeneous graphs (THGs). Limited work has been done for representation learning on THGs and the challenges are in two aspects. First, there are abundant dynamic semantics between nodes while traditional techniques like meta-paths can only capture static …

Go to article

Video Sentiment Analysis For Child Safety, Yee Sen Tan, Nicole Anne Huiying Teo, Ezekiel En Zhe Ghe, Jolie Zhi Yi Fong, Zhaoxia Wang Dec 2023

Video Sentiment Analysis For Child Safety, Yee Sen Tan, Nicole Anne Huiying Teo, Ezekiel En Zhe Ghe, Jolie Zhi Yi Fong, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

The proliferation of online video content underscores the critical need for effective sentiment analysis, particularly in safeguarding children from potentially harmful material. This research addresses this concern by presenting a multimodal analysis method for assessing video sentiment, categorizing it as either positive (child-friendly) or negative (potentially harmful). This method leverages three key components: text analysis, facial expression analysis, and audio analysis, including music mood analysis, resulting in a comprehensive sentiment assessment. Our evaluation results validate the effectiveness of this approach, making significant contributions to the field of video sentiment analysis and bolstering child safety measures. This research serves as a …

Go to article

Mermaid: A Dataset And Framework For Multimodal Meme Semantic Understanding, Shaun Toh, Adriel Kuek, Wen Haw Chong, Roy Ka Wei Lee Dec 2023

Mermaid: A Dataset And Framework For Multimodal Meme Semantic Understanding, Shaun Toh, Adriel Kuek, Wen Haw Chong, Roy Ka Wei Lee

Research Collection School Of Computing and Information Systems

Memes are widely used to convey cultural and societal issues and have a significant impact on public opinion. However, little work has been done on understanding and explaining the semantics expressed in multimodal memes. To fill this research gap, we introduce MERMAID, a dataset consisting of 3,633 memes annotated with their entities and relations, and propose a novel MERF pipeline that extracts entities and their relationships in memes. Our framework combines state-of-the-art techniques from natural language processing and computer vision to extract text and image features and infer relationships between entities in memes. We evaluate the proposed framework on a …

Go to article

Depwignn: A Depth-Wise Graph Neural Network For Multi-Hop Spatial Reasoning In Text, Shuaiyi Li, Yang Deng, Wai Lam Dec 2023

Depwignn: A Depth-Wise Graph Neural Network For Multi-Hop Spatial Reasoning In Text, Shuaiyi Li, Yang Deng, Wai Lam

Research Collection School Of Computing and Information Systems

Spatial reasoning in text plays a crucial role in various real-world applications. Existing approaches for spatial reasoning typically infer spatial relations from pure text, which overlook the gap between natural language and symbolic structures. Graph neural networks (GNNs) have showcased exceptional proficiency in inducing and aggregating symbolic structures. However, classical GNNs face challenges in handling multi-hop spatial reasoning due to the over-smoothing issue, i.e., the performance decreases substantially as the number of graph layers increases. To cope with these challenges, we propose a novel Depth-Wise Graph Neural Network (DepWiGNN). Specifically, we design a novel node memory scheme and aggregate the …

Go to article

Unifying Text, Tables, And Images For Multimodal Question Answering, Haohao Luo, Ying Shen, Yang Deng Dec 2023

Unifying Text, Tables, And Images For Multimodal Question Answering, Haohao Luo, Ying Shen, Yang Deng

Research Collection School Of Computing and Information Systems

Multimodal question answering (MMQA), which aims to derive the answer from multiple knowledge modalities (e.g., text, tables, and images), has received increasing attention due to its board applications. Current approaches to MMQA often rely on single-modal or bi-modal QA models, which limits their ability to effectively integrate information across all modalities and leverage the power of pre-trained language models. To address these limitations, we propose a novel framework called UniMMQA, which unifies three different input modalities into a text-to-text format by employing position-enhanced table linearization and diversified image captioning techniques. Additionally, we enhance cross-modal reasoning by incorporating a multimodal rationale …

Go to article

Self-Supervised Pseudo Multi-Class Pre-Training For Unsupervised Anomaly Detection And Segmentation In Medical Images, Yu Tian, Fengbei Liu, Guansong Pang, Yuanhong Chen, Yuyuan Liu, Johan W. Verjans, Rajvinder Singh, Gustavo Carneiro Dec 2023

Self-Supervised Pseudo Multi-Class Pre-Training For Unsupervised Anomaly Detection And Segmentation In Medical Images, Yu Tian, Fengbei Liu, Guansong Pang, Yuanhong Chen, Yuyuan Liu, Johan W. Verjans, Rajvinder Singh, Gustavo Carneiro

Research Collection School Of Computing and Information Systems

Unsupervised anomaly detection (UAD) methods are trained with normal (or healthy) images only, but during testing, they are able to classify normal and abnormal (or disease) images. UAD is an important medical image analysis (MIA) method to be applied in disease screening problems because the training sets available for those problems usually contain only normal images. However, the exclusive reliance on normal images may result in the learning of ineffective low-dimensional image representations that are not sensitive enough to detect and segment unseen abnormal lesions of varying size, appearance, and shape. Pre-training UAD methods with self-supervised learning, based on computer …

Go to article

Graph Contrastive Learning With Stable And Scalable Spectral Encoding, Deyu Bo, Yuan Fang, Yang Liu, Chuan Shi Dec 2023

Graph Contrastive Learning With Stable And Scalable Spectral Encoding, Deyu Bo, Yuan Fang, Yang Liu, Chuan Shi

Research Collection School Of Computing and Information Systems

Graph contrastive learning (GCL) aims to learn representations by capturing the agreements between different graph views. Traditional GCL methods generate views in the spatial domain, but it has been recently discovered that the spectral domain also plays a vital role in complementing spatial views. However, existing spectral-based graph views either ignore the eigenvectors that encode valuable positional information, or suffer from high complexity when trying to address the instability of spectral features. To tackle these challenges, we first design an informative, stable, and scalable spectral encoder, termed EigenMLP, to learn effective representations from the spectral features. Theoretically, EigenMLP is invariant …

Go to article

Mrim: Lightweight Saliency-Based Mixed-Resolution Imaging For Low-Power Pervasive Vision, Jiyan Wu, Vithurson Subasharan, Minh Anh Tuan Tran, Kasun Pramuditha Gamlath, Archan Misra Dec 2023

Mrim: Lightweight Saliency-Based Mixed-Resolution Imaging For Low-Power Pervasive Vision, Jiyan Wu, Vithurson Subasharan, Minh Anh Tuan Tran, Kasun Pramuditha Gamlath, Archan Misra

Research Collection School Of Computing and Information Systems

While many pervasive computing applications increasingly utilize real-time context extracted from a vision sensing infrastructure, the high energy overhead of DNN-based vision sensing pipelines remains a challenge for sustainable in-the-wild deployment. One common approach to reducing such energy overheads is the capture and transmission of lower-resolution images to an edge node (where the DNN inferencing task is executed), but this results in an accuracy-vs-energy tradeoff, as the DNN inference accuracy typically degrades with a drop in resolution. In this work, we introduce MRIM, a simple but effective framework to tackle this tradeoff. Under MRIM, the vision sensor platform first executes …

Go to article

Metaformer Baselines For Vision, Weihao Yu, Chenyang Si, Pan Zhou, Mi Luo, Yichen Zhou, Jiashi Feng, Shuicheng Yan, Xinchao Wang Nov 2023

Metaformer Baselines For Vision, Weihao Yu, Chenyang Si, Pan Zhou, Mi Luo, Yichen Zhou, Jiashi Feng, Shuicheng Yan, Xinchao Wang

Research Collection School Of Computing and Information Systems

Abstract—MetaFormer, the abstracted architecture of Transformer, has been found to play a significant role in achieving competitive performance. In this paper, we further explore the capacity of MetaFormer, again, by migrating our focus away from the token mixer design: we introduce several baseline models under MetaFormer using the most basic or common mixers, and demonstrate their gratifying performance. We summarize our observations as follows: (1) MetaFormer ensures solid lower bound of performance. By merely adopting identity mapping as the token mixer, the MetaFormer model, termed IdentityFormer, achieves >80% accuracy on ImageNet-1K. (2) MetaFormer works well with arbitrary token mixers. When …

Go to article

Disentangling Multi-View Representations Beyond Inductive Bias, Guanzhou Ke, Yang Yu, Guoqing Chao, Xiaoli Wang, Chenyang Xu, Shengfeng He Nov 2023

Disentangling Multi-View Representations Beyond Inductive Bias, Guanzhou Ke, Yang Yu, Guoqing Chao, Xiaoli Wang, Chenyang Xu, Shengfeng He

Research Collection School Of Computing and Information Systems

Multi-view (or -modality) representation learning aims to understand the relationships between different view representations. Existing methods disentangle multi-view representations into consistent and view-specific representations by introducing strong inductive biases, which can limit their generalization ability. In this paper, we propose a novel multi-view representation disentangling method that aims to go beyond inductive biases, ensuring both interpretability and generalizability of the resulting representations. Our method is based on the observation that discovering multi-view consistency in advance can determine the disentangling information boundary, leading to a decoupled learning objective. We also found that the consistency can be easily extracted by maximizing the …

Go to article

Cgt-Gan: Clip-Guided Text Gan For Image Captioning, Jiarui Yu, Haoran Li, Yanbin Hao, Bin Zhu, Tong Xu, Xiangnan He Nov 2023

Cgt-Gan: Clip-Guided Text Gan For Image Captioning, Jiarui Yu, Haoran Li, Yanbin Hao, Bin Zhu, Tong Xu, Xiangnan He

Research Collection School Of Computing and Information Systems

The large-scale visual-language pre-trained model, Contrastive Language-Image Pre-training (CLIP), has significantly improved image captioning for scenarios without human-annotated image-caption pairs. Recent advanced CLIP-based image captioning without human annotations follows a text-only training paradigm, i.e., reconstructing text from shared embedding space. Nevertheless, these approaches are limited by the training/inference gap or huge storage requirements for text embeddings. Given that it is trivial to obtain images in the real world, we propose CLIP-guided text GAN (CgT-GAN), which incorporates images into the training process to enable the model to "see" real visual modality. Particularly, we use adversarial training to teach CgT-GAN to mimic …

Go to article

Constructing Holistic Spatio-Temporal Scene Graph For Video Semantic Role Labeling, Yu Zhao, Hao Fei, Yixin Cao, Bobo Li, Meishan Zhang, Jianguo Wei, Min Zhang, Tat-Seng Chua Nov 2023

Constructing Holistic Spatio-Temporal Scene Graph For Video Semantic Role Labeling, Yu Zhao, Hao Fei, Yixin Cao, Bobo Li, Meishan Zhang, Jianguo Wei, Min Zhang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

As one of the core video semantic understanding tasks, Video Semantic Role Labeling (VidSRL) aims to detect the salient events from given videos, by recognizing the predict-argument event structures and the interrelationships between events. While recent endeavors have put forth methods for VidSRL, they can be mostly subject to two key drawbacks, including the lack of fine-grained spatial scene perception and the insufficiently modeling of video temporality. Towards this end, this work explores a novel holistic spatio-temporal scene graph (namely HostSG) representation based on the existing dynamic scene graph structures, which well model both the fine-grained spatial semantics and temporal …

Go to article

Revisiting Disentanglement And Fusion On Modality And Context In Conversational Multimodal Emotion Recognition, Bobo Li, Hao Fei, Lizi Liao, Yu Zhao, Chong Teng, Tat-Seng Chua, Donghong Ji, Fei Li Nov 2023

Revisiting Disentanglement And Fusion On Modality And Context In Conversational Multimodal Emotion Recognition, Bobo Li, Hao Fei, Lizi Liao, Yu Zhao, Chong Teng, Tat-Seng Chua, Donghong Ji, Fei Li

Research Collection School Of Computing and Information Systems

It has been a hot research topic to enable machines to understand human emotions in multimodal contexts under dialogue scenarios, which is tasked with multimodal emotion analysis in conversation (MM-ERC). MM-ERC has received consistent attention in recent years, where a diverse range of methods has been proposed for securing better task performance. Most existing works treat MM-ERC as a standard multimodal classification problem and perform multimodal feature disentanglement and fusion for maximizing feature utility. Yet after revisiting the characteristic of MM-ERC, we argue that both the feature multimodality and conversational contextualization should be properly modeled simultaneously during the feature disentanglement …

Go to article

Pro-Cap: Leveraging A Frozen Vision-Language Model For Hateful Meme Detection, Rui Cao, Ming Shan Hee, Adriel Kuek, Wen Haw Chong, Roy Ka-Wei Lee, Jing Jiang Nov 2023

Pro-Cap: Leveraging A Frozen Vision-Language Model For Hateful Meme Detection, Rui Cao, Ming Shan Hee, Adriel Kuek, Wen Haw Chong, Roy Ka-Wei Lee, Jing Jiang

Research Collection School Of Computing and Information Systems

Hateful meme detection is a challenging multimodal task that requires comprehension of both vision and language, as well as cross-modal interactions. Recent studies have tried to fine-tune pre-trained vision-language models (PVLMs) for this task. However, with increasing model sizes, it becomes important to leverage powerful PVLMs more efficiently, rather than simply fine-tuning them. Recently, researchers have attempted to convert meme images into textual captions and prompt language models for predictions. This approach has shown good performance but suffers from non-informative image captions. Considering the two factors mentioned above, we propose a probing-based captioning approach to leverage PVLMs in a zero-shot …

Go to article

First Prev Next Last