Search Results for author: Dit-yan Yeung

Found 63 papers, 19 papers with code

Controlled Text Generation Using Dictionary Prior in Variational Autoencoders

no code implementations Findings (ACL) 2022 Xianghong Fang, Jian Li, Lifeng Shang, Xin Jiang, Qun Liu, Dit-yan Yeung

While variational autoencoders (VAEs) have been widely applied in text generation tasks, they are troubled by two challenges: insufficient representation capacity and poor controllability.

Contrastive Learning Language Modelling +2

SCAT: Robust Self-supervised Contrastive Learning via Adversarial Training for Text Classification

no code implementations4 Jul 2023 Junjie Wu, Dit-yan Yeung

Specifically, SCAT modifies random augmentations of the data in a fully labelfree manner to generate adversarial examples.

Contrastive Learning text-classification +1

Integrating Geometric Control into Text-to-Image Diffusion Models for High-Quality Detection Data Generation via Text Prompt

no code implementations7 Jun 2023 Kai Chen, Enze Xie, Zhe Chen, Lanqing Hong, Zhenguo Li, Dit-yan Yeung

However, the usage of diffusion models to generate high-quality object detection data remains an underexplored area, where not only the image-level perceptual quality but also geometric conditions such as bounding boxes and camera views are essential.

Image Classification Layout-to-Image Generation +2

Mixed Autoencoder for Self-supervised Visual Representation Learning

no code implementations CVPR 2023 Kai Chen, Zhili Liu, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-yan Yeung

Specifically, our MixedAE outperforms MAE by +0. 3% accuracy, +1. 7 mIoU and +0. 9 AP on ImageNet-1K, ADE20K and COCO respectively with a standard ViT-Base.

Contrastive Learning Data Augmentation +1

CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data

no code implementations22 Mar 2023 Yihan Zeng, Chenhan Jiang, Jiageng Mao, Jianhua Han, Chaoqiang Ye, Qingqiu Huang, Dit-yan Yeung, Zhen Yang, Xiaodan Liang, Hang Xu

Contrastive Language-Image Pre-training, benefiting from large-scale unlabeled text-image pairs, has demonstrated great performance in open-world vision understanding tasks.

Deep COVID-19 Forecasting for Multiple States with Data Augmentation

no code implementations2 Feb 2023 Chung Yan Fong, Dit-yan Yeung

As such, it has a two-fold advantage: 1) more actual observations can be used for training, and 2) the model can be validated on data which has distribution closer to the expected situation.

Data Augmentation Time Series +1

Learning 3D-aware Image Synthesis with Unknown Pose Distribution

no code implementations CVPR 2023 Zifan Shi, Yujun Shen, Yinghao Xu, Sida Peng, Yiyi Liao, Sheng Guo, Qifeng Chen, Dit-yan Yeung

Existing methods for 3D-aware image synthesis largely depend on the 3D pose distribution pre-estimated on the training set.

3D-Aware Image Synthesis

CLIP2: Contrastive Language-Image-Point Pretraining From Real-World Point Cloud Data

no code implementations CVPR 2023 Yihan Zeng, Chenhan Jiang, Jiageng Mao, Jianhua Han, Chaoqiang Ye, Qingqiu Huang, Dit-yan Yeung, Zhen Yang, Xiaodan Liang, Hang Xu

Contrastive Language-Image Pre-training, benefiting from large-scale unlabeled text-image pairs, has demonstrated great performance in open-world vision understanding tasks.

SongRewriter: A Chinese Song Rewriting System with Controllable Content and Rhyme Scheme

1 code implementation28 Nov 2022 Yusen Sun, Liangyou Li, Qun Liu, Dit-yan Yeung

Although lyrics generation has achieved significant progress in recent years, it has limited practical applications because the generated lyrics cannot be performed without composing compatible melodies.

Improving 3D-aware Image Synthesis with A Geometry-aware Discriminator

no code implementations30 Sep 2022 Zifan Shi, Yinghao Xu, Yujun Shen, Deli Zhao, Qifeng Chen, Dit-yan Yeung

We argue that, considering the two-player game in the formulation of GANs, only making the generator 3D-aware is not enough.

3D-Aware Image Synthesis Novel View Synthesis

Trading off Quality for Efficiency of Community Detection: An Inductive Method across Graphs

no code implementations29 Sep 2022 Meng Qin, Chaorui Zhang, Bo Bai, Gong Zhang, Dit-yan Yeung

The trained model is then directly generalized to new unseen graphs for online CD without additional optimization, where a better trade-off between quality and efficiency can be achieved.

Combinatorial Optimization Community Detection

Earthformer: Exploring Space-Time Transformers for Earth System Forecasting

1 code implementation12 Jul 2022 Zhihan Gao, Xingjian Shi, Hao Wang, Yi Zhu, Yuyang Wang, Mu Li, Dit-yan Yeung

With the explosive growth of the spatiotemporal Earth observation data in the past decade, data-driven models that apply Deep Learning (DL) are demonstrating impressive potential for various Earth system forecasting tasks.

Earth Surface Forecasting Weather Forecasting

Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker

1 code implementation2 May 2022 Jeongseok Hyun, Myunggu Kang, Dongyoon Wee, Dit-yan Yeung

The strong edge features allow SGT to track targets with tracking candidates selected by top-K scored detections with large K. As a result, even low-scored detections can be tracked, and the missed detections are also recovered.

motion prediction Multi-Object Tracking +3

CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving

no code implementations15 Mar 2022 Kaican Li, Kai Chen, Haoyu Wang, Lanqing Hong, Chaoqiang Ye, Jianhua Han, Yukuai Chen, Wei zhang, Chunjing Xu, Dit-yan Yeung, Xiaodan Liang, Zhenguo Li, Hang Xu

One main reason that impedes the development of truly reliably self-driving systems is the lack of public datasets for evaluating the performance of object detectors on corner cases.

Autonomous Driving object-detection +1

3D-Aware Indoor Scene Synthesis with Depth Priors

no code implementations17 Feb 2022 Zifan Shi, Yujun Shen, Jiapeng Zhu, Dit-yan Yeung, Qifeng Chen

In this way, the discriminator can take the spatial arrangement into account and advise the generator to learn an appropriate depth condition.

3D-Aware Image Synthesis Indoor Scene Synthesis

Aug-ILA: More Transferable Intermediate Level Attacks with Augmented References

no code implementations29 Sep 2021 Chiu Wai Yan, Dit-yan Yeung

We start by looking into the effect of common image augmentation techniques and exploring novel augmentation with the aid of adversarial perturbations.

Adversarial Attack Image Augmentation

AdaAug: Learning Class- and Instance-adaptive Data Augmentation Policies

1 code implementation ICLR 2022 Tsz-Him Cheung, Dit-yan Yeung

However, the augmentation policies found are not adaptive to the dataset used, hindering the effectiveness of these AutoDA methods.

Data Augmentation

Trading Quality for Efficiency of Graph Partitioning: An Inductive Method across Graphs

no code implementations29 Sep 2021 Meng Qin, Chaorui Zhang, Bo Bai, Gong Zhang, Dit-yan Yeung

IGP is also a generic framework that can capture the permutation invariant partitioning ground-truth of historical snapshots in the offline training and tackle the online GP on graphs with non-fixed number of nodes and clusters.

Combinatorial Optimization graph partitioning

MultiSiam: Self-supervised Multi-instance Siamese Representation Learning for Autonomous Driving

1 code implementation ICCV 2021 Kai Chen, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-yan Yeung

By pre-training on SODA10M, a large-scale autonomous driving dataset, MultiSiam exceeds the ImageNet pre-trained MoCo-v2, demonstrating the potential of domain-specific pre-training.

Autonomous Driving Image Clustering +2

Stereo Waterdrop Removal with Row-wise Dilated Attention

1 code implementation7 Aug 2021 Zifan Shi, Na Fan, Dit-yan Yeung, Qifeng Chen

Thus, we propose a learning-based model for waterdrop removal with stereo images.

Autonomous Driving

Probing Toxic Content in Large Pre-Trained Language Models

1 code implementation ACL 2021 Nedjma Ousidhoum, Xinran Zhao, Tianqing Fang, Yangqiu Song, Dit-yan Yeung

Large pre-trained language models (PTLMs) have been shown to carry biases towards different social groups which leads to the reproduction of stereotypical and toxic content by major NLP systems.

Probing Language Models

Knowledge Query Network: How Knowledge Interacts with Skills

no code implementations3 Aug 2019 Jinseok Lee, Dit-yan Yeung

This involves abstract concepts of students' states of knowledge and the interactions between those states and skills.

Clustering Knowledge Tracing

Movable-Object-Aware Visual SLAM via Weakly Supervised Semantic Segmentation

no code implementations9 Jun 2019 Ting Sun, Yuxiang Sun, Ming Liu, Dit-yan Yeung

Moving objects can greatly jeopardize the performance of a visual simultaneous localization and mapping (vSLAM) system which relies on the static-world assumption.

Simultaneous Localization and Mapping Weakly supervised Semantic Segmentation +1

Effective Feature Learning with Unsupervised Learning for Improving the Predictive Models in Massive Open Online Courses

no code implementations12 Dec 2018 Mucong Ding, Kai Yang, Dit-yan Yeung, Ting-Chuen Pong

A major challenge that has to be addressed when building such models is to design handcrafted features that are effective for the prediction task at hand.

Semi-Semantic Line-Cluster Assisted Monocular SLAM for Indoor Environments

no code implementations5 Nov 2018 Ting Sun, Dezhen Song, Dit-yan Yeung, Ming Liu

In the back end, we optimize the map imposing the constraint that the line segments of the same cluster should be the same.

Simultaneous Localization and Mapping

Point-cloud-based place recognition using CNN feature extraction

no code implementations23 Oct 2018 Ting Sun, Ming Liu, Haoyang Ye, Dit-yan Yeung

This paper proposes a novel point-cloud-based place recognition system that adopts a deep learning approach for feature extraction.

Machine Learning for Spatiotemporal Sequence Forecasting: A Survey

no code implementations21 Aug 2018 Xingjian Shi, Dit-yan Yeung

Forecasting the multi-step future of these spatiotemporal systems based on the past observations, or, Spatiotemporal Sequence Forecasting (STSF), is a significant and challenging problem.

BIG-bench Machine Learning Trajectory Forecasting

Incorporating Features Learned by an Enhanced Deep Knowledge Tracing Model for STEM/Non-STEM Job Prediction

1 code implementation6 Jun 2018 Chun-kit Yeung, Zizheng Lin, Kai Yang, Dit-yan Yeung

The 2017 ASSISTments Data Mining competition aims to use data from a longitudinal study for predicting a brand-new outcome of students which had never been studied before by the educational data mining research community.

Job Prediction Knowledge Tracing

Addressing Two Problems in Deep Knowledge Tracing via Prediction-Consistent Regularization

2 code implementations6 Jun 2018 Chun-kit Yeung, Dit-yan Yeung

In recent years, a recurrent neural network model called deep knowledge tracing (DKT) has been proposed to handle the knowledge tracing task and literature has shown that DKT generally outperforms traditional methods.

Knowledge Tracing Vocal Bursts Valence Prediction

Robust path-based spectral clustering

no code implementations1 Jan 2018 Hong Chang, Dit-yan Yeung

In this paper, based on M-estimation from robust statistics, we develop a robust path-based spectral clustering method by defining a robust path-based similarity measure for spectral clustering under both unsupervised and semi-supervised settings.

Clustering Image Segmentation +1

Learning Unmanned Aerial Vehicle Control for Autonomous Target Following

no code implementations24 Sep 2017 Siyi Li, Tianbo Liu, Chi Zhang, Dit-yan Yeung, Shaojie Shen

While deep reinforcement learning (RL) methods have achieved unprecedented successes in a range of challenging problems, their applicability has been mainly limited to simulation or game domains due to the high sample complexity of the trial-and-error learning process.

reinforcement-learning Reinforcement Learning (RL)

Temporal Dynamic Graph LSTM for Action-driven Video Object Detection

no code implementations ICCV 2017 Yuan Yuan, Xiaodan Liang, Xiaolong Wang, Dit-yan Yeung, Abhinav Gupta

A common issue, however, is that objects of interest that are not involved in human actions are often absent in global action descriptions known as "missing label".

object-detection Object Recognition +2

Spatiotemporal Modeling for Crowd Counting in Videos

no code implementations ICCV 2017 Feng Xiong, Xingjian Shi, Dit-yan Yeung

To exploit the otherwise very useful temporal information in video sequences, we propose a variant of a recent deep learning model called convolutional LSTM (ConvLSTM) for crowd counting.

Crowd Counting Transfer Learning

Fine-Grained Categorization via CNN-Based Automatic Extraction and Integration of Object-Level and Part-Level Features

no code implementations22 Jun 2017 Ting Sun, Lin Sun, Dit-yan Yeung

Fine-grained categorization can benefit from part-based features which reveal subtle visual differences between object categories.

ZM-Net: Real-time Zero-shot Image Manipulation Network

no code implementations21 Mar 2017 Hao Wang, Xiaodan Liang, Hao Zhang, Dit-yan Yeung, Eric P. Xing

We cast this problem as manipulating an input image according to a parametric model whose key parameters can be conditionally generated from any guiding signal (even unseen ones).

Colorization Descriptive +2

Dynamic Key-Value Memory Networks for Knowledge Tracing

1 code implementation24 Nov 2016 Jiani Zhang, Xingjian Shi, Irwin King, Dit-yan Yeung

Knowledge Tracing (KT) is a task of tracing evolving knowledge state of students with respect to one or more concepts as they engage in a sequence of learning activities.

Knowledge Tracing

Natural-Parameter Networks: A Class of Probabilistic Neural Networks

1 code implementation NeurIPS 2016 Hao Wang, Xingjian Shi, Dit-yan Yeung

Another shortcoming of NN is the lack of flexibility to customize different distributions for the weights and neurons according to the data, as is often done in probabilistic graphical models.

Decision Making Under Uncertainty Link Prediction

Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks

no code implementations NeurIPS 2016 Hao Wang, Xingjian Shi, Dit-yan Yeung

To address this problem, we develop a collaborative recurrent autoencoder (CRAE) which is a denoising recurrent autoencoder (DRAE) that models the generation of content sequences in the collaborative filtering (CF) setting.

Collaborative Filtering Denoising +1

Sparse Boltzmann Machines with Structure Learning as Applied to Text Analysis

no code implementations17 Sep 2016 Zhourong Chen, Nevin L. Zhang, Dit-yan Yeung, Peixian Chen

We are interested in exploring the possibility and benefits of structure learning for deep models.

Towards Bayesian Deep Learning: A Framework and Some Existing Methods

no code implementations24 Aug 2016 Hao Wang, Dit-yan Yeung

While perception tasks such as visual object recognition and text understanding play an important role in human intelligence, the subsequent tasks that involve inference, reasoning and planning require an even higher level of intelligence.

Object Recognition Recommendation Systems +1

A Survey on Bayesian Deep Learning

1 code implementation6 Apr 2016 Hao Wang, Dit-yan Yeung

The past decade has seen major advances in many perception tasks such as visual object recognition and speech recognition using deep learning models.

Object Recognition Recommendation Systems +3

Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks

no code implementations ICCV 2015 Lin Sun, Kui Jia, Dit-yan Yeung, Bertram E. Shi

Human actions in video sequences are three-dimensional (3D) spatio-temporal signals characterizing both the visual appearance and motion dynamics of the involved humans and objects.

Action Recognition Image Classification +1

DevNet: A Deep Event Network for Multimedia Event Detection and Evidence Recounting

no code implementations CVPR 2015 Chuang Gan, Naiyan Wang, Yi Yang, Dit-yan Yeung, Alex G. Hauptmann

Taking key frames of videos as input, we first detect the event of interest at the video level by aggregating the CNN features of the key frames.

Action Recognition Event Detection +2

Bayesian Adaptive Matrix Factorization With Automatic Model Selection

no code implementations CVPR 2015 Peixian Chen, Naiyan Wang, Nevin L. Zhang, Dit-yan Yeung

Low-rank matrix factorization has long been recognized as a fundamental problem in many computer vision applications.

Model Selection

Understanding and Diagnosing Visual Tracking Systems

no code implementations ICCV 2015 Naiyan Wang, Jianping Shi, Dit-yan Yeung, Jiaya Jia

Surprisingly, our findings are discrepant with some common beliefs in the visual tracking research community.

Visual Tracking

Transferring Rich Feature Hierarchies for Robust Visual Tracking

no code implementations19 Jan 2015 Naiyan Wang, Siyi Li, Abhinav Gupta, Dit-yan Yeung

To fit the characteristics of object tracking, we first pre-train the CNN to recognize what is an object, and then propose to generate a probability map instead of producing a simple class label.

Image Classification object-detection +3

Collaborative Deep Learning for Recommender Systems

1 code implementation10 Sep 2014 Hao Wang, Naiyan Wang, Dit-yan Yeung

(CF-based) input and propose in this paper a hierarchical Bayesian model called collaborative deep learning (CDL), which jointly performs deep representation learning for the content information and collaborative filtering for the ratings (feedback) matrix.

Collaborative Filtering Recommendation Systems +1

Learning a Deep Compact Image Representation for Visual Tracking

no code implementations NeurIPS 2013 Naiyan Wang, Dit-yan Yeung

In this paper, we study the challenging problem of tracking the trajectory of a moving object in a video with possibly very complex background.

Denoising General Classification +2

Co-Regularized Hashing for Multimodal Data

no code implementations NeurIPS 2012 Yi Zhen, Dit-yan Yeung

Hashing-based methods provide a very promising approach to large-scale similarity search.

A Convex Formulation for Learning Task Relationships in Multi-Task Learning

no code implementations15 Mar 2012 Yu Zhang, Dit-yan Yeung

In this paper, we propose a regularization formulation for learning the relationships between tasks in multi-task learning.

Multi-Task Learning

Probabilistic Multi-Task Feature Selection

no code implementations NeurIPS 2010 Yu Zhang, Dit-yan Yeung, Qian Xu

In this paper, we unify the $l_{1, 2}$ and $l_{1,\infty}$ norms by considering a family of $l_{1, q}$ norms for $1 < q\le\infty$ and study the problem of determining the most appropriate sparsity enforcing norm to use in the context of multi-task feature selection.

feature selection Multi-Task Learning

Worst-Case Linear Discriminant Analysis

no code implementations NeurIPS 2010 Yu Zhang, Dit-yan Yeung

In this paper, we first analyze the scatter measures used in the conventional linear discriminant analysis~(LDA) model and note that the formulation is based on the average-case view.

Dimensionality Reduction Metric Learning

Posterior Consistency of the Silverman g-prior in Bayesian Model Choice

no code implementations NeurIPS 2008 Zhihua Zhang, Michael. I. Jordan, Dit-yan Yeung

The duality between regularization and prior leads to interpreting regularization methods in terms of maximum a posteriori estimation and has motivated Bayesian interpretations of kernel methods.

Cannot find the paper you are looking for? You can Submit a new open access paper.