Open Access. Powered by Scholars. Published by Universities.®
- Institution
-
- Singapore Management University (942)
- University of Dayton (114)
- Old Dominion University (99)
- Air Force Institute of Technology (98)
- California Polytechnic State University, San Luis Obispo (96)
-
- University of Arkansas, Fayetteville (89)
- University of Nebraska - Lincoln (51)
- City University of New York (CUNY) (48)
- Technological University Dublin (48)
- University of Malaya (43)
- San Jose State University (37)
- Dartmouth College (35)
- Embry-Riddle Aeronautical University (24)
- Clemson University (23)
- Purdue University (23)
- Rochester Institute of Technology (23)
- The University of Akron (22)
- Chapman University (20)
- Edith Cowan University (20)
- University of Kentucky (18)
- Michigan Technological University (16)
- University of Central Florida (15)
- Southern Adventist University (13)
- California State University, San Bernardino (12)
- Kennesaw State University (12)
- St. Mary's University (12)
- Nova Southeastern University (11)
- University of Minnesota Morris Digital Well (11)
- Louisiana State University (10)
- University of Nevada, Las Vegas (10)
- Keyword
-
- Virtual reality (62)
- Visualization (46)
- Computer graphics (38)
- Computer vision (37)
- Accessibility (36)
-
- Human-computer interaction (35)
- Augmented reality (33)
- Usability (31)
- Machine learning (29)
- Machine Learning (26)
- Artificial intelligence (25)
- Computer Science (25)
- Data visualization (25)
- Deep learning (24)
- Virtual Reality (23)
- HCI (22)
- Computer science (21)
- Eye tracking (20)
- Human computer interaction (20)
- User experience (20)
- Design (19)
- Deep Learning (16)
- Education (16)
- Feature extraction (15)
- Graph Neural Networks (15)
- Graphics (15)
- VR (15)
- Artificial Intelligence (14)
- Gamification (14)
- Image processing (14)
- Publication Year
- Publication
-
- Research Collection School Of Computing and Information Systems (916)
- Computer Science Faculty Publications (135)
- Theses and Dissertations (98)
- Master's Theses (50)
- Graduate Theses and Dissertations (43)
-
- Student Works (2000-2009) (33)
- Computer Science and Computer Engineering Undergraduate Honors Theses (31)
- 3-D Printed Model Structural Files (29)
- Publications and Research (28)
- Dartmouth College Master’s Theses (24)
- Williams Honors College, Honors Research Projects (22)
- Master's Projects (20)
- Conference papers (19)
- Frameless (19)
- Computer Science and Software Engineering (18)
- All Dissertations (17)
- Dissertations and Theses Collection (Open Access) (16)
- Dissertations, Master's Theses and Master's Reports (16)
- H-Workload 2017: Models and Applications (Works in Progress) (15)
- Computer Engineering (14)
- Electronic Theses and Dissertations (14)
- Theses : Honours (14)
- Honors Theses (13)
- MAICS: The Modern Artificial Intelligence and Cognitive Science Conference (12)
- AFIT Patents (11)
- CCAC Theses and Dissertations (11)
- Engineering Faculty Articles and Research (11)
- Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal (10)
- Student Works (2020-2029) (10)
- Inquiry: The University of Arkansas Undergraduate Research Journal (9)
- Publication Type
- File Type
Articles 691 - 720 of 2371
Full-Text Articles in Computer Sciences
Transfer Of Personality Through Text Style, Michael O'Mahony, Robert Ross
Transfer Of Personality Through Text Style, Michael O'Mahony, Robert Ross
Other resources
The style of generated text is how something is said rather than what is said. We hypothesize that changing the style of generated text can change the perceived personality of the text generation agent. Dialogue systems that aim to imitate a human agent can appear to have a consistent personality through a consistent, controllable style of conversation. Some recent work on the style of generated text [1] performs impressively in the small number of domains selected for their experiments using transformer and LSTM-based models. Lin et al. [1] used weak supervised learning as their data set lacks parallel data. The …
Make Your Own Sprites: Aliasing-Aware And Cell-Controllable Pixelization, Zongwei Wu, Liangyu Chai, Nanxuan Zhao, Bailin Deng, Yongtuo Liu, Qiang Wen, Junle Wang, Shengfeng He
Make Your Own Sprites: Aliasing-Aware And Cell-Controllable Pixelization, Zongwei Wu, Liangyu Chai, Nanxuan Zhao, Bailin Deng, Yongtuo Liu, Qiang Wen, Junle Wang, Shengfeng He
Research Collection School Of Computing and Information Systems
Pixel art is a unique art style with the appearance of low resolution images. In this paper, we propose a data-driven pixelization method that can produce sharp and crisp cell effects with controllable cell sizes. Our approach overcomes the limitation of existing learning-based methods in cell size control by introducing a reference pixel art to explicitly regularize the cell structure. In particular, the cell structure features of the reference pixel art are used as an auxiliary input for the pixelization process, and for measuring the style similarity between the generated result and the reference pixel art. Furthermore, we disentangle the …
Disease Recognition In X-Ray Images With Doctor Consultation-Inspired Model, Kim Anh Phung, Thuan Trong Nguyen, Nileshkumar Wangad, Samah Baraheem, Nguyen D. Vo, Khang Nguyen
Disease Recognition In X-Ray Images With Doctor Consultation-Inspired Model, Kim Anh Phung, Thuan Trong Nguyen, Nileshkumar Wangad, Samah Baraheem, Nguyen D. Vo, Khang Nguyen
Computer Science Faculty Publications
The application of chest X-ray imaging for early disease screening is attracting interest from the computer vision and deep learning community. To date, various deep learning models have been applied in X-ray image analysis. However, models perform inconsistently depending on the dataset. In this paper, we consider each individual model as a medical doctor. We then propose a doctor consultation-inspired method that fuses multiple models. In particular, we consider both early and late fusion mechanisms for consultation. The early fusion mechanism combines the deep learned features from multiple models, whereas the late fusion method combines the confidence scores of all …
Movie Reviews Sentiment Analysis Using Bert, Gibson Nkhata
Movie Reviews Sentiment Analysis Using Bert, Gibson Nkhata
Graduate Theses and Dissertations
Sentiment analysis (SA) or opinion mining is analysis of emotions and opinions from texts. It is one of the active research areas in Natural Language Processing (NLP). Various approaches have been deployed in the literature to address the problem. These techniques devise complex and sophisticated frameworks in order to attain optimal accuracy with their focus on polarity classification or binary classification. In this paper, we aim to fine-tune BERT in a simple but robust approach for movie reviews sentiment analysis to provide better accuracy than state-of-the-art (SOTA) methods. We start by conducting sentiment classification for every review, followed by computing …
Design And Comparison Of Asynchronous Fft Implementations, Julie Bigot
Design And Comparison Of Asynchronous Fft Implementations, Julie Bigot
Graduate Theses and Dissertations
Fast Fourier Transform (FFT) is a widely used digital signal processing technology in a large variety of applications. For battery-powered embedded systems incorporating FFT, its physical implementation is constrained by strict power consumption, especially during idle periods. Compared to the prevailing clocked synchronous counterpart, quasi-delay insensitive asynchronous circuits offer a series of advantages including flexible timing requirement and lower leakage power, making them ideal choices for these systems. In this thesis work, various FFT configurations were implemented in the low-power Multi-Threshold NULL Convention Logic (MTNCL) paradigm. Analysis illustrates the area and power consumption trends along the changing of the number …
Multivariate Fairness For Paper Selection, Reem Alsaffar
Multivariate Fairness For Paper Selection, Reem Alsaffar
Graduate Theses and Dissertations
Peer review is the process by which publishers select the best publications for inclusion in a journal or a conference. Bias in the peer review process can impact which papers are selected for inclusion in conferences and journals. Although often implicit, race, gender and other demographics can prevent members of underrepresented groups from presenting at major conferences. To try to avoid bias, many conferences use a double-blind review process to increase fairness during reviewing. However, recent studies argue that the bias has not been removed completely. Our research focuses on developing fair algorithms that correct for these biases and select …
Developing And Facilitating Temporary Team Mental Models Through An Information-Sharing Recommender System, Geoffrey Musick
Developing And Facilitating Temporary Team Mental Models Through An Information-Sharing Recommender System, Geoffrey Musick
All Dissertations
It is well understood that teams are essential and common in many aspects of life, both work and leisure. Due to the importance of teams, much research attention has focused on how to improve team processes and outcomes. Of particular interest are the cognitive aspects of teamwork including team mental models (TMMs). Among many other benefits, TMMs involve team members forming a compatible understanding of the task and team in order to more efficiently make decisions. This understanding is sometimes classified using four TMM domains: equipment (e.g., operating procedures), task (e.g., strategies), team interactions (e.g., interdependencies) and teammates (e.g., tendencies). …
Electrical Modeling For Dynamic Performance Prediction And Optimization Of Mcpms Layout, Quang Minh Le
Electrical Modeling For Dynamic Performance Prediction And Optimization Of Mcpms Layout, Quang Minh Le
Graduate Theses and Dissertations
In recent years, the fast development of Multichip Power Modules (MCPM) packaging and Wide Bandgap (WBG) technology has enabled higher voltage and current ratings, better thermal performance, lower parasitic parameters, and higher mechanical reliability. However, the design of the MCPM layout is a multidisciplinary problem leading to many time-consuming analyses and tedious design processes. Because of these challenges, the design automation tool for MCPM layout has become an emerging research area and gained much attention from the power electronics community. The two critical objectives of a design automation tool for MCPM layout are fast and accurate models for design insights …
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
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 …
Segment-Wise Time-Varying Dynamic Bayesian Network With Graph Regularization, Xing Yang, Chen Zhang, Baihua Zheng
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 …
Vr Computing Lab: An Immersive Classroom For Computing Learning, Shawn Pang, Kyong Jin Shim, Yi Meng Lau, Swapna Gottipati
Vr Computing Lab: An Immersive Classroom For Computing Learning, Shawn Pang, Kyong Jin Shim, Yi Meng Lau, Swapna Gottipati
Research Collection School Of Computing and Information Systems
In recent years, virtual reality (VR) is gaining popularity amongst educators and learners. If a picture is worth a thousand words, a VR session is worth a trillion words. VR technology completely immerses users with an experience that transports them into a simulated world. Universities across the United States, United Kingdom, and other countries have already started using VR for higher education in areas such as medicine, business, architecture, vocational training, social work, virtual field trips, virtual campuses, helping students with special needs, and many more. In this paper, we propose a novel VR platform learning framework which maps elements …
Prompting For Multimodal Hateful Meme Classification, Rui Cao, Roy Ka-Wei Lee, Wen-Haw Chong, Jing Jiang
Prompting For Multimodal Hateful Meme Classification, Rui Cao, Roy Ka-Wei Lee, Wen-Haw Chong, Jing Jiang
Research Collection School Of Computing and Information Systems
Hateful meme classification is a challenging multimodal task that requires complex reasoning and contextual background knowledge. Ideally, we could leverage an explicit external knowledge base to supplement contextual and cultural information in hateful memes. However, there is no known explicit external knowledge base that could provide such hate speech contextual information. To address this gap, we propose PromptHate, a simple yet effective prompt-based model that prompts pre-trained language models (PLMs) for hateful meme classification. Specifically, we construct simple prompts and provide a few in-context examples to exploit the implicit knowledge in the pretrained RoBERTa language model for hateful meme classification. …
Enabling The Human Perception Of A Working Camera In Web Conferences Via Its Movement, Anish Shrestha
Enabling The Human Perception Of A Working Camera In Web Conferences Via Its Movement, Anish Shrestha
LSU Master's Theses
In recent years, video conferencing has seen a significant increase in its usage due to the COVID-19 pandemic. When casting user’s video to other participants, the videoconference applications (e.g. Zoom, FaceTime, Skype, etc.) mainly leverage 1) webcam’s LED-light indicator, 2) user’s video feedback in the software and 3) the software’s video on/off icons to remind the user whether the camera is being used. However, these methods all impose the responsibility on the user itself to check the camera status, and there have been numerous cases reported when users expose their privacy inadvertently due to not realizing that their camera is …
Hapticpuppet: A Kinesthetic Mid-Air Multidirectional Force-Feedback Drone-Based Interface, Martin Feick, Anthony Tang, Antonio Kruger
Hapticpuppet: A Kinesthetic Mid-Air Multidirectional Force-Feedback Drone-Based Interface, Martin Feick, Anthony Tang, Antonio Kruger
Research Collection School Of Computing and Information Systems
Providing kinesthetic force-feedback for human-scale interactions is challenging due to the relatively large forces needed. Therefore, robotic actuators are predominantly used to deliver this kind of haptic feedback; however, they offer limited flexibility and spatial resolution. In this work, we introduce HapticPuppet, a drone-based force-feedback interface which can exert multidirectional forces onto the human body. This can be achieved by attaching strings to different parts of the human body such as fingers, hands or ankles, which can then be affixed to multiple coordinated drones - puppeteering the user. HapticPuppet opens up a wide range of potential applications in virtual, augmented …
Cscw 2022 Chairs' Welcome, Gary Hsieh, Anthony Tang
Cscw 2022 Chairs' Welcome, Gary Hsieh, Anthony Tang
Research Collection School Of Computing and Information Systems
We are excited to bring you the 25th ACM Conference on Computer-Supported Cooperative Work and Social Computing – CSCW 2022 – virtually. We were initially poised to hold CSCW 2022 in Taiwan to help strengthen the CSCW community’s relationship with Asia, but the uncertainty around COVID-19 pandemic restrictions made this an impractical idea. Yet, as designers, we view challenges as learning opportunities and know learning opportunities lead to new ideas and approaches. From the online and virtual conferences experiences of the past few years, we considered questions like: what makes conferences interesting, what makes conferences worth attending, how can we …
Vfirm: Verifiable Fine-Grained Encrypted Image Retrieval In Multi-Owner Multi-User Settings, Qiuyun Tong, Yinbin Miao, Lei Chen, Jian Weng, Kim-Kwang Raymond Choo, Ximeng Liu, Robert H. Deng
Vfirm: Verifiable Fine-Grained Encrypted Image Retrieval In Multi-Owner Multi-User Settings, Qiuyun Tong, Yinbin Miao, Lei Chen, Jian Weng, Kim-Kwang Raymond Choo, Ximeng Liu, Robert H. Deng
Research Collection School Of Computing and Information Systems
To ensure the security of images outsourced to the malicious cloud without affecting searchability on such outsourced (typically encrypted) images, one could use privacy-preserving Content-Based Image Retrieval (CBIR) primitive. However, conventional privacy-preserving CBIR schemes based on Searchable Symmetric Encryption (SSE) are not capable of supporting efficient fine-grained access control and result verification simultaneously. Therefore, in this article, we propose a Verifiable Fine-grained encrypted Image Retrieval scheme in the Multi-owner multi-user settings (VFIRM). VFIRM first utilizes a novel polynomial-based access strategy to provide efficient fine-grained access control. Then, it employs the dual secure kk-nearest neighbor technique to distribute distinct keys to …
Graph Neural Network With Self-Attention And Multi-Task Learning For Credit Default Risk Prediction, Zihao Li, Xianzhi Wang, Lina Yao, Yakun Chen, Guandong Xu, Ee-Peng Lim
Graph Neural Network With Self-Attention And Multi-Task Learning For Credit Default Risk Prediction, Zihao Li, Xianzhi Wang, Lina Yao, Yakun Chen, Guandong Xu, Ee-Peng Lim
Research Collection School Of Computing and Information Systems
We propose a graph neural network with self-attention and multi-task learning (SaM-GNN) to leverage the advantages of deep learning for credit default risk prediction. Our approach incorporates two parallel tasks based on shared intermediate vectors for input vector reconstruction and credit default risk prediction, respectively. To better leverage supervised data, we use self-attention layers for feature representation of categorical and numeric data; we further link raw data into a graph and use a graph convolution module to aggregate similar information and cope with missing values during constructing intermediate vectors. Our method does not heavily rely on feature engineering work and …
Daot: Domain-Agnostically Aligned Optimal Transport For Domain-Adaptive Crowd Counting, Huilin Zhu, Jingling Yuan, Xian Zhong, Zhengwei Yang, Zheng Wang, Shengfeng He
Daot: Domain-Agnostically Aligned Optimal Transport For Domain-Adaptive Crowd Counting, Huilin Zhu, Jingling Yuan, Xian Zhong, Zhengwei Yang, Zheng Wang, Shengfeng He
Research Collection School Of Computing and Information Systems
Domain adaptation is commonly employed in crowd counting to bridge the domain gaps between different datasets. However, existing domain adaptation methods tend to focus on inter-dataset differences while overlooking the intra-differences within the same dataset, leading to additional learning ambiguities. These domain-agnostic factors,e.g., density, surveillance perspective, and scale, can cause significant in-domain variations, and the misalignment of these factors across domains can lead to a drop in performance in cross-domain crowd counting. To address this issue, we propose a Domain-agnostically Aligned Optimal Transport (DAOT) strategy that aligns domain-agnostic factors between domains. The DAOT consists of three steps. First, individual-level differences …
A Cognitive-Emotional Model From Mobile Short-Form Video Addiction To Intermittent Discontinuance: The Moderating Role Of Neutralization, Yafei Feng, Lifu Li, Anqi Zhao
A Cognitive-Emotional Model From Mobile Short-Form Video Addiction To Intermittent Discontinuance: The Moderating Role Of Neutralization, Yafei Feng, Lifu Li, Anqi Zhao
Research Collection School Of Computing and Information Systems
Discontinuance is considered very effective in the treatment of IT addiction. However, prior literature on the mechanism from IT addiction to discontinuance has reached inconsistent conclusions. Also, scholars cannot explain why some individuals do not make any changes after becoming addicted, even when they realize that their behavior is not in line with the norms. To fill the gaps, our research developed a cognitive-emotional model, with neutralization as a moderator, to understand the internal mechanism from mobile short-form video addiction to intermittent discontinuance. Based on the online survey of 493 Chinese mobile short-form video users, this study used partial least …
Tourgether360: Collaborative Exploration Of 360° Videos Using Pseudo-Spatial Navigation, Kartikaeya Kumar, Lev Poretski, Jianan Li, Anthony Tang
Tourgether360: Collaborative Exploration Of 360° Videos Using Pseudo-Spatial Navigation, Kartikaeya Kumar, Lev Poretski, Jianan Li, Anthony Tang
Research Collection School Of Computing and Information Systems
Collaborative exploration of 360 videos with contemporary interfaces is challenging because collaborators do not have awareness of one another's viewing activities. Tourgether360 enhances social exploration of 360° tour videos using a pseudo-spatial navigation technique that provides both an overhead "context" view of the environment as a minimap, as well as a shared pseudo-3D environment for exploring the video. Collaborators are embodied as avatars along a track depending on their position in the video timeline and can point and synchronize their playback. We evaluated the Tourgether360 concept through two studies: first, a comparative study with a simplified version of Tourgether360 with …
Epic-Kitchens Visor Benchmark: Video Segmentations And Object Relations, Ahmad Ak Dar Khalil, Dandan Shan, Bin Zhu, Jian Ma, Amlan Kar, Richard Higgins, David Fouhey, Sanja Fidler, Dima Damen
Epic-Kitchens Visor Benchmark: Video Segmentations And Object Relations, Ahmad Ak Dar Khalil, Dandan Shan, Bin Zhu, Jian Ma, Amlan Kar, Richard Higgins, David Fouhey, Sanja Fidler, Dima Damen
Research Collection School Of Computing and Information Systems
We introduce VISOR, a new dataset of pixel annotations and a benchmark suite for segmenting hands and active objects in egocentric video. VISOR annotates videos from EPIC-KITCHENS, which comes with a new set of challenges not encountered in current video segmentation datasets. Specifically, we need to ensure both short- and long-term consistency of pixel-level annotations as objects undergo transformative interactions, e.g. an onion is peeled, diced and cooked - where we aim to obtain accurate pixel-level annotations of the peel, onion pieces, chopping board, knife, pan, as well as the acting hands. VISOR introduces an annotation pipeline, AI-powered in parts, …
Ideating Xai: An Exploration Of User’S Mental Models Of An Ai-Driven Recruitment System Using A Design Thinking Approach, Helen Sheridan, Dympna O'Sullivan, Emma Murphy
Ideating Xai: An Exploration Of User’S Mental Models Of An Ai-Driven Recruitment System Using A Design Thinking Approach, Helen Sheridan, Dympna O'Sullivan, Emma Murphy
Conference Papers
Artificial Intelligence (AI) is playing an important role in society including how vital, often life changing decisions are made. For this reason, interest in Explainable Artificial Intelligence (XAI) has grown in recent years as a means of revealing the processes and operations contained within what is often described as a black box, an often-opaque system whose decisions are difficult to understand by the end user. This paper presents the results of a design thinking workshop with 20 participants (computer science and graphic design students) where we sought to investigate users' mental models when interacting with AI systems. Using two personas, …
Supporting Prosocial Behaviour In Online Communities Through Social Media Affordances, Dominique Kelly, Liu Yifan, Alex Mayhew, Sarah Cornwell, Yimin Chen, Nicole Delellis, Victoria Rubin
Supporting Prosocial Behaviour In Online Communities Through Social Media Affordances, Dominique Kelly, Liu Yifan, Alex Mayhew, Sarah Cornwell, Yimin Chen, Nicole Delellis, Victoria Rubin
Data and Test Instruments
Affordances are action possibilities that emerge from the relationship between the properties of an object and an interacting agent’s capabilities. This poster examines how one type of affordance—anonymity—is enabled or constrained by six features of social media platforms. Our work is one step in a broader agenda to: (1) identify affordances that influence users’ behaviour in online communities; (2) outline the social media features that enable or constrain those affordances; and, (3) experimentally determine whether certain affordances, or combinations of affordances, support prosocial behaviour. Prosocial behaviour in information and communication technologies (ICTs) is broadly viewed here as benefiting other individuals …
Tgdm: Target Guided Dynamic Mixup For Cross-Domain Few-Shot Learning, Linhai Zhuo, Yuqian Fu, Jingjing Chen, Yixin Cao, Yu-Gang Jiang
Tgdm: Target Guided Dynamic Mixup For Cross-Domain Few-Shot Learning, Linhai Zhuo, Yuqian Fu, Jingjing Chen, Yixin Cao, Yu-Gang Jiang
Research Collection School Of Computing and Information Systems
Given sufficient training data on the source domain, cross-domain few-shot learning (CD-FSL) aims at recognizing new classes with a small number of labeled examples on the target domain. The key to addressing CD-FSL is to narrow the domain gap and transferring knowledge of a network trained on the source domain to the target domain. To help knowledge transfer, this paper introduces an intermediate domain generated by mixing images in the source and the target domain. Specifically, to generate the optimal intermediate domain for different target data, we propose a novel target guided dynamic mixup (TGDM) framework that leverages the target …
Long-Term Leap Attention, Short-Term Periodic Shift For Video Classification, Hao Zhang, Lechao Cheng, Yanbin Hao, Chong-Wah Ngo
Long-Term Leap Attention, Short-Term Periodic Shift For Video Classification, Hao Zhang, Lechao Cheng, Yanbin Hao, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Video transformer naturally incurs a heavier computation burden than a static vision transformer, as the former processes �� times longer sequence than the latter under the current attention of quadratic complexity (�� 2�� 2 ). The existing works treat the temporal axis as a simple extension of spatial axes, focusing on shortening the spatio-temporal sequence by either generic pooling or local windowing without utilizing temporal redundancy. However, videos naturally contain redundant information between neighboring frames; thereby, we could potentially suppress attention on visually similar frames in a dilated manner. Based on this hypothesis, we propose the LAPS, a long-term “Leap …
Dualformer: Local-Global Stratified Transformer For Efficient Video Recognition, Yuxuan Liang, Pan Zhou, Roger Zimmermann, Shuicheng Yan
Dualformer: Local-Global Stratified Transformer For Efficient Video Recognition, Yuxuan Liang, Pan Zhou, Roger Zimmermann, Shuicheng Yan
Research Collection School Of Computing and Information Systems
While transformers have shown great potential on video recognition with their strong capability of capturing long-range dependencies, they often suffer high computational costs induced by the self-attention to the huge number of 3D tokens. In this paper, we present a new transformer architecture termed DualFormer, which can efficiently perform space-time attention for video recognition. Concretely, DualFormer stratifies the full space-time attention into dual cascaded levels, i.e., to first learn fine-grained local interactions among nearby 3D tokens, and then to capture coarse-grained global dependencies between the query token and global pyramid contexts. Different from existing methods that apply space-time factorization or …
Learning Discriminative Representations Via Variational Self-Distillation For Cross-View Geo-Localization, Qian Hu, Wansi Li, Xing Xu, Ning Liu, Lei Wang
Learning Discriminative Representations Via Variational Self-Distillation For Cross-View Geo-Localization, Qian Hu, Wansi Li, Xing Xu, Ning Liu, Lei Wang
Research Collection School Of Computing and Information Systems
Cross-view geo-localization is to localize the same geographic target in images from different perspectives, e.g., satellite-view and drone-view. The primary challenge faced by existing methods is the large visual appearance changes across views. Most previous work utilizes the deep neural network to obtain the discriminative representations and directly uses them to accomplish the geo-localization task. However, these approaches ignore that the redundancy retained in the extracted features negatively impacts the result. In this paper, we argue that the information bottleneck (IB) can retain the most relevant information while removing as much redundancy as possible. The variational self-distillation (VSD) strategy provides …
Interactive Contrastive Learning For Self-Supervised Entity Alignment, Kaisheng Zeng, Zhenhao Dong, Lei Hou, Yixin Cao, Minghao Hu, Jifan Yu, Xin Lv, Lei Cao, Xin Wang, Haozhuang Liu, Yi Huang, Jing Wan, Juanzi Li
Interactive Contrastive Learning For Self-Supervised Entity Alignment, Kaisheng Zeng, Zhenhao Dong, Lei Hou, Yixin Cao, Minghao Hu, Jifan Yu, Xin Lv, Lei Cao, Xin Wang, Haozhuang Liu, Yi Huang, Jing Wan, Juanzi Li
Research Collection School Of Computing and Information Systems
Self-supervised entity alignment (EA) aims to link equivalent entities across different knowledge graphs (KGs) without the use of pre-aligned entity pairs. The current state-of-the-art (SOTA) selfsupervised EA approach draws inspiration from contrastive learning, originally designed in computer vision based on instance discrimination and contrastive loss, and suffers from two shortcomings. Firstly, it puts unidirectional emphasis on pushing sampled negative entities far away rather than pulling positively aligned pairs close, as is done in the well-established supervised EA. Secondly, it advocates the minimum information requirement for self-supervised EA, while we argue that self-described KG’s side information (e.g., entity name, relation name, …
Ergo: Event Relational Graph Transformer For Document-Level Event Causality Identification, Meiqi Chen, Yixin Cao, Kunquan Deng, Mukai Li, Kun Wang, Jing Shao, Yan Zhang
Ergo: Event Relational Graph Transformer For Document-Level Event Causality Identification, Meiqi Chen, Yixin Cao, Kunquan Deng, Mukai Li, Kun Wang, Jing Shao, Yan Zhang
Research Collection School Of Computing and Information Systems
Document-level Event Causality Identification (DECI) aims to identify event-event causal relations in a document. Existing works usually build an event graph for global reasoning across multiple sentences. However, the edges between events have to be carefully designed through heuristic rules or external tools. In this paper, we propose a novel Event Relational Graph TransfOrmer (ERGO) framework1 for DECI, to ease the graph construction and improve it over the noisy edge issue. Different from conventional event graphs, we define a pair of events as a node and build a complete event relational graph without any prior knowledge or tools. This naturally …
Wave-Vit: Unifying Wavelet And Transformers For Visual Representation Learning, Ting Yao, Yingwei Pan, Yehao Li, Chong-Wah Ngo, Tao Mei
Wave-Vit: Unifying Wavelet And Transformers For Visual Representation Learning, Ting Yao, Yingwei Pan, Yehao Li, Chong-Wah Ngo, Tao Mei
Research Collection School Of Computing and Information Systems
Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales quadratically w.r.t. the input patch number. Thus, existing solutions commonly employ down-sampling operations (e.g., average pooling) over keys/values to dramatically reduce the computational cost. In this work, we argue that such over-aggressive down-sampling design is not invertible and inevitably causes information dropping especially for high-frequency components in objects (e.g., texture details). Motivated by the wavelet theory, we construct a new Wavelet Vision Transformer (Wave-ViT) that formulates the invertible down-sampling with wavelet transforms and self-attention learning in a unified way. …