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 541 - 570 of 933

Full-Text Articles in Graphics and Human Computer Interfaces

Neighbourhood Structure Preserving Cross-Modal Embedding For Video Hyperlinking, Yanbin Hao, Chong-Wah Ngo, Benoit Huet Jan 2020

Neighbourhood Structure Preserving Cross-Modal Embedding For Video Hyperlinking, Yanbin Hao, Chong-Wah Ngo, Benoit Huet

Research Collection School Of Computing and Information Systems

Video hyperlinking is a task aiming to enhance the accessibility of large archives, by establishing links between fragments of videos. The links model the aboutness between fragments for efficient traversal of video content. This paper addresses the problem of link construction from the perspective of cross-modal embedding. To this end, a generalized multi-modal auto-encoder is proposed.& x00A0;The encoder learns two embeddings from visual and speech modalities, respectively, whereas each of the embeddings performs self-modal and cross-modal translation of modalities. Furthermore, to preserve the neighbourhood structure of fragments, which is important for video hyperlinking, the auto-encoder is devised to model data …

Go to article

Vireo @ Video Browser Showdown 2020, Phuong Anh Nguyen, Jiaxin Wu, Chong-Wah Ngo, Danny Francis, Benoit Huet Jan 2020

Vireo @ Video Browser Showdown 2020, Phuong Anh Nguyen, Jiaxin Wu, Chong-Wah Ngo, Danny Francis, Benoit Huet

Research Collection School Of Computing and Information Systems

In this paper, we present the features implemented in the 4th version of the VIREO Video Search System (VIREO-VSS). In this version, we propose a sketch-based retrieval model, which allows the user to specify a video scene with objects and their basic properties, including color, size, and location. We further utilize the temporal relation between video frames to strengthen this retrieval model. For text-based retrieval module, we supply speech and on-screen text for free-text search and upgrade the concept bank for concept search. The search interface is also re-designed targeting the novice user. With the introduced system, we expect that …

Go to article

Efficient Meta Learning Via Minibatch Proximal Update, Pan Zhou, Xiao-Tong Yuan, Huan Xu, Shuicheng Yan, Jiashi Feng Dec 2019

Efficient Meta Learning Via Minibatch Proximal Update, Pan Zhou, Xiao-Tong Yuan, Huan Xu, Shuicheng Yan, Jiashi Feng

Research Collection School Of Computing and Information Systems

We address the problem of meta-learning which learns a prior over hypothesis from a sample of meta-training tasks for fast adaptation on meta-testing tasks. A particularly simple yet successful paradigm for this research is model-agnostic meta-learning (MAML). Implementation and analysis of MAML, however, can be tricky; first-order approximation is usually adopted to avoid directly computing Hessian matrix but as a result the convergence and generalization guarantees remain largely mysterious for MAML. To remedy this deficiency, in this paper we propose a minibatch proximal update based meta-learning approach for learning to efficient hypothesis transfer. The principle is to learn a prior …

Go to article

Improved Generalisation Bounds For Deep Learning Through L∞ Covering Numbers, Antoine Ledent, Yunwen Lei, Marius Kloft Dec 2019

Improved Generalisation Bounds For Deep Learning Through L∞ Covering Numbers, Antoine Ledent, Yunwen Lei, Marius Kloft

Research Collection School Of Computing and Information Systems

Using proof techniques involving L∞ covering numbers, we show generalisation error bounds for deep learning with two main improvements over the state of the art. First, our bounds have no explicit dependence on the number of classes except for logarithmic factors. This holds even when formulating the bounds in terms of the L 2 norm of the weight matrices, while previous bounds exhibit at least a square-root dependence on the number of classes in this case. Second, we adapt the Rademacher analysis of DNNs to incorporate weight sharing—a task of fundamental theoretical importance which was previously attempted only under very …

Go to article

Eurecom At Trecvid Avs 2019, Danny Francis, Phuong Anh Nguyen, Benoit Huet, Chong-Wah Ngo Nov 2019

Eurecom At Trecvid Avs 2019, Danny Francis, Phuong Anh Nguyen, Benoit Huet, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

This notebook reports the model and results of the EURECOM runs at TRECVID AVS 2019.

Go to article

Special Issue On Multimedia Recommendation And Multi-Modal Data Analysis, Xiangnan He, Zhenguang Liu, Hanwang Zhang, Chong-Wah Ngo, Svebor Karaman, Yongfeng Zhang Nov 2019

Special Issue On Multimedia Recommendation And Multi-Modal Data Analysis, Xiangnan He, Zhenguang Liu, Hanwang Zhang, Chong-Wah Ngo, Svebor Karaman, Yongfeng Zhang

Research Collection School Of Computing and Information Systems

Rich multimedia contents are dominating the Web. In popular social media platforms such as FaceBook, Twitter, and Instagram, there are over millions of multimedia contents being created by users on a daily basis. In the meantime, multimedia data consist of data in multiple modalities, such as text, images, audio, and so on. Users are heavily overloaded by the massive multi-modal data, and it becomes critical to explore advanced techniques for heterogeneous big data analytics and multimedia recommendation. Traditional multimedia recommendation and data analysis technologies cannot well address the problem of understanding users’ preference in the feature-rich multimedia contents, and have …

Go to article

Semi-Supervised Entity Alignment Via Joint Knowledge Embedding Model And Cross-Graph Model, Chengjiang Li, Yixin Cao, Lei Hou, Jiaxin Shi, Juanzi Li, Tat-Seng Chua Nov 2019

Semi-Supervised Entity Alignment Via Joint Knowledge Embedding Model And Cross-Graph Model, Chengjiang Li, Yixin Cao, Lei Hou, Jiaxin Shi, Juanzi Li, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Entity alignment aims at integrating complementary knowledge graphs (KGs) from different sources or languages, which may benefit many knowledge-driven applications. It is challenging due to the heterogeneity of KGs and limited seed alignments. In this paper, we propose a semi-supervised entity alignment method by joint Knowledge Embedding model and Cross-Graph model (KECG). It can make better use of seed alignments to propagate over the entire graphs with KG-based constraints. Specifically, as for the knowledge embedding model, we utilize TransE to implicitly complete two KGs towards consistency and learn relational constraints between entities. As for the cross-graph model, we extend Graph …

Go to article

Shellnet: Efficient Point Cloud Convolutional Neural Networks Using Concentric Shells Statistics, Zhiyuan Zhang, Binh-Son Hua, Sai-Kit Yeung Nov 2019

Shellnet: Efficient Point Cloud Convolutional Neural Networks Using Concentric Shells Statistics, Zhiyuan Zhang, Binh-Son Hua, Sai-Kit Yeung

Research Collection School Of Computing and Information Systems

Deep learning with 3D data has progressed significantly since the introduction of convolutional neural networks that can handle point order ambiguity in point cloud data. While being able to achieve good accuracies in various scene understanding tasks, previous methods often have low training speed and complex network architecture. In this paper, we address these problems by proposing an efficient end-to-end permutation invariant convolution for point cloud deep learning. Our simple yet effective convolution operator named ShellConv uses statistics from concentric spherical shells to define representative features and resolve the point order ambiguity, allowing traditional convolution to perform on such features. …

Go to article

Gender And Racial Diversity In Commercial Brands' Advertising Images On Social Media, Jisun An, Haewoon Kwak Nov 2019

Gender And Racial Diversity In Commercial Brands' Advertising Images On Social Media, Jisun An, Haewoon Kwak

Research Collection School Of Computing and Information Systems

Gender and racial diversity in the mediated images from the media shape our perception of different demographic groups. In this work, we investigate gender and racial diversity of 85,957 advertising images shared by the 73 top international brands on Instagram and Facebook. We hope that our analyses give guidelines on how to build a fully automated watchdog for gender and racial diversity in online advertisements.

Go to article

Revisiting Collaboration Through Mixed Reality: The Evolution Of Groupware, Barrett Ens, Joel Lanir, Anthony Tang, Scott Bateman, Gun Lee, Thammathip Piumsomboon, Mark Billinghurst Nov 2019

Revisiting Collaboration Through Mixed Reality: The Evolution Of Groupware, Barrett Ens, Joel Lanir, Anthony Tang, Scott Bateman, Gun Lee, Thammathip Piumsomboon, Mark Billinghurst

Research Collection School Of Computing and Information Systems

Collaborative Mixed Reality (MR) systems are at a critical point in time as they are soon to become more commonplace. However, MR technology has only recently matured to the point where researchers can focus deeply on the nuances of supporting collaboration, rather than needing to focus on creating the enabling technology. In parallel, but largely independently, the field of Computer Supported Cooperative Work (CSCW) has focused on the fundamental concerns that underlie human communication and collaboration over the past 30-plus years. Since MR research is now on the brink of moving into the real world, we reflect on three decades …

Go to article

Vireo-Eurecom @ Trecvid 2019: Ad-Hoc Video Search (Avs), Phuong Anh Nguyen, Jiaxin Wu, Chong-Wah Ngo, Francis Danny, Benoit Huet Nov 2019

Vireo-Eurecom @ Trecvid 2019: Ad-Hoc Video Search (Avs), Phuong Anh Nguyen, Jiaxin Wu, Chong-Wah Ngo, Francis Danny, Benoit Huet

Research Collection School Of Computing and Information Systems

In this paper, we describe the systems developed for Ad-hoc Video Search (AVS) task at TRECVID 2019[1] and the achieved results.

Go to article

Vireojd-Mm @ Trecvid 2019: Activities In Extended Video (Actev), Zhijian Hou, Ying-Wei Pan, Ting Yao, Chong-Wah Ngo Nov 2019

Vireojd-Mm @ Trecvid 2019: Activities In Extended Video (Actev), Zhijian Hou, Ying-Wei Pan, Ting Yao, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

In this paper, we describe the system developed for Activities in Extended Video(ActEV) task at TRECVid 2019 [1] and the achieved results. Activities in Extended Video(ActEV): The goal of Activities in Extended Video is to spatially and temporally localize the action instances in a surveillance setting. We have participated in previous ActEV prize challenge. Since the only difference between the two challenges is evaluation metric, we maintain previous pipeline [2] for this challenge. The pipeline has three stages: object detection, tubelet generation and temporal action localization. This time we extend the system for two aspects separately: better object detection and …

Go to article

Low-Resource Name Tagging Learned With Weakly Labeled Data, Yixin Cao, Zikun Hu, Tat-Seng Chua, Zhiyuan Liu, Heng Ji Nov 2019

Low-Resource Name Tagging Learned With Weakly Labeled Data, Yixin Cao, Zikun Hu, Tat-Seng Chua, Zhiyuan Liu, Heng Ji

Research Collection School Of Computing and Information Systems

Name tagging in low-resource languages or domains suffers from inadequate training data. Existing work heavily relies on additional information, while leaving those noisy annotations unexplored that extensively exist on the web. In this paper, we propose a novel neural model for name tagging solely based on weakly labeled (WL) data, so that it can be applied in any low-resource settings. To take the best advantage of all WL sentences, we split them into high-quality and noisy portions for two modules, respectively: (1) a classification module focusing on the large portion of noisy data can efficiently and robustly pretrain the tag …

Go to article

Mixed-Dish Recognition With Contextual Relation Networks, Lixi Deng, Jingjing Chen, Qianru Sun, Xiangnan He, Sheng Tang, Zhaoyan Ming, Yongdong Zhang, Tat-Seng Chua Oct 2019

Mixed-Dish Recognition With Contextual Relation Networks, Lixi Deng, Jingjing Chen, Qianru Sun, Xiangnan He, Sheng Tang, Zhaoyan Ming, Yongdong Zhang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Mixed dish is a food category that contains different dishes mixed in one plate, and is popular in Eastern and Southeast Asia. Recognizing individual dishes in a mixed dish image is important for health related applications, e.g. calculating the nutrition values. However, most existing methods that focus on single dish classification are not applicable to mixed-dish recognition. The new challenge in recognizing mixed-dish images are the complex ingredient combination and severe overlap among different dishes. In order to tackle these problems, we propose a novel approach called contextual relation networks (CR-Nets) that encodes the implicit and explicit contextual relations among …

Go to article

Multi-Label Thoracic Disease Image Classification With Cross-Attention Networks, Congbo Ma, Hu Wang, Steven C. H. Hoi Oct 2019

Multi-Label Thoracic Disease Image Classification With Cross-Attention Networks, Congbo Ma, Hu Wang, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Automated disease classification of radiology images has been emerging as a promising technique to support clinical diagnosis and treatment planning. Unlike generic image classification tasks, a real-world radiology image classification task is significantly more challenging as it is far more expensive to collect the training data where the labeled data is in nature multi-label; and more seriously samples from easy classes often dominate; training data is highly class-imbalanced problem exists in practice as well. To overcome these challenges, in this paper, we propose a novel scheme of Cross-Attention Networks (CAN) for automated thoracic disease classification from chest x-ray images, which …

Go to article

Fusion Of Multimodal Embeddings For Ad-Hoc Video Search, Danny Francis, Phuong Anh Nguyen, Benoit Huet, Chong-Wah Ngo Oct 2019

Fusion Of Multimodal Embeddings For Ad-Hoc Video Search, Danny Francis, Phuong Anh Nguyen, Benoit Huet, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

The challenge of Ad-Hoc Video Search (AVS) originates from free-form (i.e., no pre-defined vocabulary) and freestyle (i.e., natural language) query description. Bridging the semantic gap between AVS queries and videos becomes highly difficult as evidenced from the low retrieval accuracy of AVS benchmarking in TRECVID. In this paper, we study a new method to fuse multimodal embeddings which have been derived based on completely disjoint datasets. This method is tested on two datasets for two distinct tasks: on MSR-VTT for unique video retrieval and on V3C1 for multiple videos retrieval.

Go to article

Semi-Supervised Deep Quantization For Cross-Modal Search, Xin Wang, Wenwu Zhu, Chenghao Liu Oct 2019

Semi-Supervised Deep Quantization For Cross-Modal Search, Xin Wang, Wenwu Zhu, Chenghao Liu

Research Collection School Of Computing and Information Systems

The problem of cross-modal similarity search, which aims at making efficient and accurate queries across multiple domains, has become a significant and important research topic. Composite quantization, a compact coding solution superior to hashing techniques, has shown its effectiveness for similarity search. However, most existing works utilizing composite quantization to search multi-domain content only consider either pairwise similarity information or class label information across different domains, which fails to tackle the semi-supervised problem in composite quantization. In this paper, we address the semi-supervised quantization problem by considering: (i) pairwise similarity information (without class label information) across different domains, which captures …

Go to article

Nonuniform Timeslicing Of Dynamic Graphs Based On Visual Complexity, Yong Wang, Daniel Archambault, Hammad Haleem, Torsten Moeller, Yanhong Wu, Huamin Qu Oct 2019

Nonuniform Timeslicing Of Dynamic Graphs Based On Visual Complexity, Yong Wang, Daniel Archambault, Hammad Haleem, Torsten Moeller, Yanhong Wu, Huamin Qu

Research Collection School Of Computing and Information Systems

Uniform timeslicing of dynamic graphs has been used due to its convenience and uniformity across the time dimension. However, uniform timeslicing does not take the data set into account, which can generate cluttered timeslices with edge bursts and empty timeslices with few interactions. The graph mining filed has explored nonuniform timeslicing methods specifically designed to preserve graph features for mining tasks. In this paper, we propose a nonuni-form timeslicing approach for dynamic graph visualization. Our goal is to create timeslices of equal visual complexity. To this end, we adapt histogram equalization to create timeslices with a similar number of events, …

Go to article

Rotation Invariant Convolutions For 3d Point Clouds Deep Learning, Zhiyuan Zhang, Binh-Son Hua, David W. Rosen, Sai-Kit Yeung Sep 2019

Rotation Invariant Convolutions For 3d Point Clouds Deep Learning, Zhiyuan Zhang, Binh-Son Hua, David W. Rosen, Sai-Kit Yeung

Research Collection School Of Computing and Information Systems

Recent progresses in 3D deep learning has shown that it is possible to design special convolution operators to consume point cloud data. However, a typical drawback is that rotation invariance is often not guaranteed, resulting in networks that generalizes poorly to arbitrary rotations. In this paper, we introduce a novel convolution operator for point clouds that achieves rotation invariance. Our core idea is to use low-level rotation invariant geometric features such as distances and angles to design a convolution operator for point cloud learning. The well-known point ordering problem is also addressed by a binning approach seamlessly built into the …

Go to article

Multimodal Transformer Networks For End-To-End Video-Grounded Dialogue Systems, Hung Le, Doyen Sahoo, Nancy F. Chen, Steven C. H. Hoi Aug 2019

Multimodal Transformer Networks For End-To-End Video-Grounded Dialogue Systems, Hung Le, Doyen Sahoo, Nancy F. Chen, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Developing Video-Grounded Dialogue Systems (VGDS), where a dialogue is conducted based on visual and audio aspects of a given video, is significantly more challenging than traditional image or text-grounded dialogue systems because (1) feature space of videos span across multiple picture frames, making it difficult to obtain semantic information; and (2) a dialogue agent must perceive and process information from different modalities (audio, video, caption, etc.) to obtain a comprehensive understanding. Most existing work is based on RNNs and sequence-to-sequence architectures, which are not very effective for capturing complex long-term dependencies (like in videos). To overcome this, we propose Multimodal …

Go to article

Generalized Majorization-Minimization For Non-Convex Optimization, Hu Zhang, Pan Zhou, Yi Yang, Jiashi Feng Aug 2019

Generalized Majorization-Minimization For Non-Convex Optimization, Hu Zhang, Pan Zhou, Yi Yang, Jiashi Feng

Research Collection School Of Computing and Information Systems

Majorization-Minimization (MM) algorithms optimize an objective function by iteratively minimizing its majorizing surrogate and offer attractively fast convergence rate for convex problems. However, their convergence behaviors for non-convex problems remain unclear. In this paper, we propose a novel MM surrogate function from strictly upper bounding the objective to bounding the objective in expectation. With this generalized surrogate conception, we develop a new optimization algorithm, termed SPI-MM, that leverages the recent proposed SPIDER for more efficient non-convex optimization. We prove that for finite-sum problems, the SPI-MM algorithm converges to an stationary point within deterministic and lower stochastic gradient complexity. To our …

Go to article

Bidding Mechanisms In Graph Games, Guy Avni, Thomas A. Henzinger, Dorde Zikelic Aug 2019

Bidding Mechanisms In Graph Games, Guy Avni, Thomas A. Henzinger, Dorde Zikelic

Research Collection School Of Computing and Information Systems

In two-player games on graphs, the players move a token through a graph to produce a finite or infinite path, which determines the qualitative winner or quantitative payoff of the game. We study bidding games in which the players bid for the right to move the token. Several bidding rules were studied previously. In Richman bidding, in each round, the players simultaneously submit bids, and the higher bidder moves the token and pays the other player. Poorman bidding is similar except that the winner of the bidding pays the “bank” rather than the other player. Taxman bidding spans the spectrum …

Go to article

Kgat: Knowledge Graph Attention Network For Recommendation, Xiang Wang, Xiangnan He, Yixin Cao, Meng Liu, Tat-Seng Chua Aug 2019

Kgat: Knowledge Graph Attention Network For Recommendation, Xiang Wang, Xiangnan He, Yixin Cao, Meng Liu, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

To provide more accurate, diverse, and explainable recommendation, it is compulsory to go beyond modeling user-item interactions and take side information into account. Traditional methods like factorization machine (FM) cast it as a supervised learning problem, which assumes each interaction as an independent instance with side information encoded. Due to the overlook of the relations among instances or items (e.g., the director of a movie is also an actor of another movie), these methods are insufficient to distill the collaborative signal from the collective behaviors of users. In this work, we investigate the utility of knowledge graph (KG), which breaks …

Go to article

Personalized Fashion Recommendation With Visual Explanations Based On Multimodal Attention Network: Towards Visually Explainable Recommendation, Xu Chen, Hanxiong Chen, Hongteng Xu, Yongfeng Zhang, Yixin Cao, Zheng Qin, Hongyuan Zha Jul 2019

Personalized Fashion Recommendation With Visual Explanations Based On Multimodal Attention Network: Towards Visually Explainable Recommendation, Xu Chen, Hanxiong Chen, Hongteng Xu, Yongfeng Zhang, Yixin Cao, Zheng Qin, Hongyuan Zha

Research Collection School Of Computing and Information Systems

Fashion recommendation has attracted increasing attention from both industry and academic communities. This paper proposes a novel neural architecture for fashion recommendation based on both image region-level features and user review information. Our basic intuition is that: for a fashion image, not all the regions are equally important for the users, i.e., people usually care about a few parts of the fashion image. To model such human sense, we learn an attention model over many pre-segmented image regions, based on which we can understand where a user is really interested in on the image, and correspondingly, represent the image in …

Go to article

Evaluating The Readability Of Force Directed Graph Layouts: A Deep Learning Approach, Hammad Haleem, Yong Wang, Abishek Puri, Sahil Wadhwa, Huamin Qu Jul 2019

Evaluating The Readability Of Force Directed Graph Layouts: A Deep Learning Approach, Hammad Haleem, Yong Wang, Abishek Puri, Sahil Wadhwa, Huamin Qu

Research Collection School Of Computing and Information Systems

Existing graph layout algorithms are usually not able to optimize all the aesthetic properties desired in a graph layout. To evaluate how well the desired visual features are reflected in a graph layout, many readability metrics have been proposed in the past decades. However, the calculation of these readability metrics often requires access to the node and edge coordinates and is usually computationally inefficient, especially for dense graphs. Importantly, when the node and edge coordinates are not accessible, it becomes impossible to evaluate the graph layouts quantitatively. In this paper, we present a novel deep learning-based approach to evaluate the …

Go to article

Multi-Channel Graph Neural Network For Entity Alignment, Yixin Cao, Zhiyuan Liu, Chengjiang Li, Zhiyuan Liu, Juanzi Li, Tat-Seng Chua Jul 2019

Multi-Channel Graph Neural Network For Entity Alignment, Yixin Cao, Zhiyuan Liu, Chengjiang Li, Zhiyuan Liu, Juanzi Li, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Entity alignment typically suffers from the issues of structural heterogeneity and limited seed alignments. In this paper, we propose a novel Multi-channel Graph Neural Network model (MuGNN) to learn alignment-oriented knowledge graph (KG) embeddings by robustly encoding two KGs via multiple channels. Each channel encodes KGs via different relation weighting schemes with respect to self-attention towards KG completion and cross-KG attention for pruning exclusive entities respectively, which are further combined via pooling techniques. Moreover, we also infer and transfer rule knowledge for completing two KGs consistently. MuGNN is expected to reconcile the structural differences of two KGs, and thus make …

Go to article

Learning Spatio-Temporal Representation With Local And Global Diffusion, Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Xinmei Tian, Tao Mei Jun 2019

Learning Spatio-Temporal Representation With Local And Global Diffusion, Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Xinmei Tian, Tao Mei

Research Collection School Of Computing and Information Systems

Convolutional Neural Networks (CNN) have been regarded as a powerful class of models for visual recognition problems. Nevertheless, the convolutional filters in these networks are local operations while ignoring the large-range dependency. Such drawback becomes even worse particularly for video recognition, since video is an information-intensive media with complex temporal variations. In this paper, we present a novel framework to boost the spatio-temporal representation learning by Local and Global Diffusion (LGD). Specifically, we construct a novel neural network architecture that learns the local and global representations in parallel. The architecture is composed of LGD blocks, where each block updates local …

Go to article

Mixed Dish Recognition Through Multi-Label Learning, Yunan Wang, Jing-Jing Chen, Chong-Wah Ngo, Tat-Seng Chua, Wanli Zuo, Zhaoyan Ming Jun 2019

Mixed Dish Recognition Through Multi-Label Learning, Yunan Wang, Jing-Jing Chen, Chong-Wah Ngo, Tat-Seng Chua, Wanli Zuo, Zhaoyan Ming

Research Collection School Of Computing and Information Systems

Mix dish recognition, whose goal is to identify each of the dish type presented on one plate, is generally regarded as a difficult problem. The major challenge of this problem is that different dishes presented in one plate may overlap with each other and there may be no clear boundaries among them. Therefore, labeling the bounding box of each dish type is difficult and not necessarily leading to good results. This paper studies the problem from the perspective of multi-label learning. Specially, we propose to perform dish recognition on region level with multiple granularities. For experimental purpose, we collect two …

Go to article

Exploring Object Relation In Mean Teacher For Cross-Domain Detection, Qi Cai, Yingwei Pan, Chong-Wah Ngo, Xinmei Tian, Lingyu Duan, Ting Yao Jun 2019

Exploring Object Relation In Mean Teacher For Cross-Domain Detection, Qi Cai, Yingwei Pan, Chong-Wah Ngo, Xinmei Tian, Lingyu Duan, Ting Yao

Research Collection School Of Computing and Information Systems

Rendering synthetic data (e.g., 3D CAD-rendered images) to generate annotations for learning deep models in vision tasks has attracted increasing attention in recent years. However, simply applying the models learnt on synthetic images may lead to high generalization error on real images due to domain shift. To address this issue, recent progress in cross-domain recognition has featured the Mean Teacher, which directly simulates unsupervised domain adaptation as semi-supervised learning. The domain gap is thus naturally bridged with consistency regularization in a teacher-student scheme. In this work, we advance this Mean Teacher paradigm to be applicable for crossdomain detection. Specifically, we …

Go to article

Sliced Wasserstein Generative Models, Jiqing Wu, Zhiwu Huang, Dinesh Acharya, Wen Li, Janine Thoma, Danda Pani Paudel, Luc Van Gool Jun 2019

Sliced Wasserstein Generative Models, Jiqing Wu, Zhiwu Huang, Dinesh Acharya, Wen Li, Janine Thoma, Danda Pani Paudel, Luc Van Gool

Research Collection School Of Computing and Information Systems

In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions. Unfortunately, it is challenging to approximate the WD of high-dimensional distributions. In contrast, the sliced Wasserstein distance (SWD) factorizes high-dimensional distributions into their multiple one-dimensional marginal distributions and is thus easier to approximate. In this paper, we introduce novel approximations of the primal and dual SWD. Instead of using a large number of random projections, as it is done by conventional SWD approximation methods, we propose to approximate SWDs with a small number of parameterized orthogonal projections …

Go to article

First Prev Next Last