Search Results for author: Ling-Yu Duan

Found 45 papers, 18 papers with code

FHDe²Net: Full High Definition Demoireing Network

1 code implementation ECCV 2020 Bin He, Ce Wang, Boxin Shi, Ling-Yu Duan

Frequency aliasing in the digital capture of display screens leads to the moir´e pattern, appearing as stripe-shaped distortions in images.

Vocal Bursts Intensity Prediction

HARD-Net: Hardness-AwaRe Discrimination Network for 3D Early Activity Prediction

no code implementations ECCV 2020 Tianjiao Li, Jun Liu, Wei zhang, Ling-Yu Duan

In this paper, we propose a novel Hardness-AwaRe Discrimination Network (HARD-Net) to specifically investigate the relationships between the similar activity pairs that are hard to be discriminated.

Activity Prediction Skeleton Based Action Recognition

Exploring Model Transferability through the Lens of Potential Energy

1 code implementation ICCV 2023 Xiaotong Li, Zixuan Hu, Yixiao Ge, Ying Shan, Ling-Yu Duan

The experimental results on 10 downstream tasks and 12 self-supervised models demonstrate that our approach can seamlessly integrate into existing ranking techniques and enhance their performances, revealing its effectiveness for the model selection task and its potential for understanding the mechanism in transfer learning.

Model Selection Transfer Learning

Modeling Uncertain Feature Representation for Domain Generalization

1 code implementation16 Jan 2023 Xiaotong Li, Zixuan Hu, Jun Liu, Yixiao Ge, Yongxing Dai, Ling-Yu Duan

In this paper, we improve the network generalization ability by modeling domain shifts with uncertainty (DSU), i. e., characterizing the feature statistics as uncertain distributions during training.

Domain Generalization Image Classification +3

Switchable Representation Learning Framework with Self-compatibility

no code implementations CVPR 2023 Shengsen Wu, Yan Bai, Yihang Lou, Xiongkun Linghu, Jianzhong He, Ling-Yu Duan

Existing research mainly focuses on the one-to-one compatible paradigm, which is limited in learning compatibility among multiple models.

Representation Learning

mc-BEiT: Multi-choice Discretization for Image BERT Pre-training

1 code implementation29 Mar 2022 Xiaotong Li, Yixiao Ge, Kun Yi, Zixuan Hu, Ying Shan, Ling-Yu Duan

Image BERT pre-training with masked image modeling (MIM) becomes a popular practice to cope with self-supervised representation learning.

Instance Segmentation object-detection +5

Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning

1 code implementation CVPR 2022 Lin Zhang, Li Shen, Liang Ding, DaCheng Tao, Ling-Yu Duan

Instead, we propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG), which relieves the issue of direct model aggregation.

Data-free Knowledge Distillation Federated Learning

Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains

1 code implementation3 Mar 2022 Yongxing Dai, Yifan Sun, Jun Liu, Zekun Tong, Yi Yang, Ling-Yu Duan

Instead of directly aligning the source and target domains against each other, we propose to align the source and target domains against their intermediate domains for a smooth knowledge transfer.

Domain Generalization Person Re-Identification +1

Uncertainty Modeling for Out-of-Distribution Generalization

1 code implementation ICLR 2022 Xiaotong Li, Yongxing Dai, Yixiao Ge, Jun Liu, Ying Shan, Ling-Yu Duan

In this paper, we improve the network generalization ability by modeling the uncertainty of domain shifts with synthesized feature statistics during training.

Image Classification Out-of-Distribution Generalization +2

Towards Low Light Enhancement with RAW Images

no code implementations28 Dec 2021 Haofeng Huang, Wenhan Yang, Yueyu Hu, Jiaying Liu, Ling-Yu Duan

In this paper, we make the first benchmark effort to elaborate on the superiority of using RAW images in the low light enhancement and develop a novel alternative route to utilize RAW images in a more flexible and practical way.

Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics

no code implementations18 Oct 2021 Wenhan Yang, Haofeng Huang, Yueyu Hu, Ling-Yu Duan, Jiaying Liu

By keeping in mind the transferability among different machine vision tasks (e. g. high-level semantic and mid-level geometry-related), we aim to support multiple tasks jointly at low bit rates.

Feature Compression Philosophy

Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning

1 code implementation6 Aug 2021 Yan Bai, Jile Jiao, Shengsen Wu, Yihang Lou, Jun Liu, Xuetao Feng, Ling-Yu Duan

It is a heavy workload to re-extract features of the whole database every time. Feature compatibility enables the learned new visual features to be directly compared with the old features stored in the database.


IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID

3 code implementations ICCV 2021 Yongxing Dai, Jun Liu, Yifan Sun, Zekun Tong, Chi Zhang, Ling-Yu Duan

To ensure these two properties to better characterize appropriate intermediate domains, we enforce the bridge losses on intermediate domains' prediction space and feature space, and enforce a diversity loss on the two domain factors.

Domain Adaptive Person Re-Identification Person Re-Identification

Generalizable Person Re-identification with Relevance-aware Mixture of Experts

no code implementations CVPR 2021 Yongxing Dai, Xiaotong Li, Jun Liu, Zekun Tong, Ling-Yu Duan

Specifically, we propose a decorrelation loss to make the source domain networks (experts) keep the diversity and discriminability of individual domains' characteristics.

Generalizable Person Re-identification

Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification

1 code implementation26 Dec 2020 Yongxing Dai, Jun Liu, Yan Bai, Zekun Tong, Ling-Yu Duan

To this end, we propose a novel approach, called Dual-Refinement, that jointly refines pseudo labels at the off-line clustering phase and features at the on-line training phase, to alternatively boost the label purity and feature discriminability in the target domain for more reliable re-ID.

Clustering Domain Adaptive Person Re-Identification +1

Market2Dish: Health-aware Food Recommendation

1 code implementation11 Dec 2020 Wenjie Wang, Ling-Yu Duan, Hao Jiang, Peiguang Jing, Xuemeng Song, Liqiang Nie

With the rising incidence of some diseases, such as obesity and diabetes, a healthy diet is arousing increasing attention.

Food recommendation Nutrition +1

Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation

1 code implementation ECCV 2020 Haoran Wang, Tong Shen, Wei zhang, Ling-Yu Duan, Tao Mei

To fully exploit the supervision in the source domain, we propose a fine-grained adversarial learning strategy for class-level feature alignment while preserving the internal structure of semantics across domains.

Domain Adaptation Semantic Segmentation +1

Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics

no code implementations10 Jan 2020 Ling-Yu Duan, Jiaying Liu, Wenhan Yang, Tiejun Huang, Wen Gao

Meanwhile, we systematically review state-of-the-art techniques in video compression and feature compression from the unique perspective of MPEG standardization, which provides the academic and industrial evidence to realize the collaborative compression of video and feature streams in a broad range of AI applications.

Feature Compression Video Compression

Towards Coding for Human and Machine Vision: A Scalable Image Coding Approach

no code implementations9 Jan 2020 Yueyu Hu, Shuai Yang, Wenhan Yang, Ling-Yu Duan, Jiaying Liu

In this paper, we come up with a novel image coding framework by leveraging both the compressive and the generative models, to support machine vision and human perception tasks jointly.

Facial Landmark Detection Image Reconstruction

An Emerging Coding Paradigm VCM: A Scalable Coding Approach Beyond Feature and Signal

no code implementations9 Jan 2020 Sifeng Xia, Kunchangtai Liang, Wenhan Yang, Ling-Yu Duan, Jiaying Liu

To this end, we make endeavors in leveraging the strength of predictive and generative models to support advanced compression techniques for both machine and human vision tasks simultaneously, in which visual features serve as a bridge to connect signal-level and task-level compact representations in a scalable manner.

Action Recognition Feature Compression +1

Towards Digital Retina in Smart Cities: A Model Generation, Utilization and Communication Paradigm

1 code implementation31 Jul 2019 Yihang Lou, Ling-Yu Duan, Yong Luo, Ziqian Chen, Tongliang Liu, Shiqi Wang, Wen Gao

The digital retina in smart cities is to select what the City Eye tells the City Brain, and convert the acquired visual data from front-end visual sensors to features in an intelligent sensing manner.

Hard-Aware Fashion Attribute Classification

no code implementations25 Jul 2019 Yun Ye, Yixin Li, Bo Wu, Wei zhang, Ling-Yu Duan, Tao Mei

For "hard" attributes with insufficient training data, Deact brings more stable synthetic samples for training and further improve the performance.

Attribute Classification +1

NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding

3 code implementations12 May 2019 Jun Liu, Amir Shahroudy, Mauricio Perez, Gang Wang, Ling-Yu Duan, Alex C. Kot

Research on depth-based human activity analysis achieved outstanding performance and demonstrated the effectiveness of 3D representation for action recognition.

Action Recognition One-Shot 3D Action Recognition +1

SPLINE-Net: Sparse Photometric Stereo through Lighting Interpolation and Normal Estimation Networks

no code implementations ICCV 2019 Qian Zheng, Yiming Jia, Boxin Shi, Xudong Jiang, Ling-Yu Duan, Alex C. Kot

This paper solves the Sparse Photometric stereo through Lighting Interpolation and Normal Estimation using a generative Network (SPLINE-Net).

Exploring Object Relation in Mean Teacher for Cross-Domain Detection

1 code implementation CVPR 2019 Qi Cai, Yingwei Pan, Chong-Wah Ngo, Xinmei Tian, Ling-Yu Duan, Ting Yao

The whole architecture is then optimized with three consistency regularizations: 1) region-level consistency to align the region-level predictions between teacher and student, 2) inter-graph consistency for matching the graph structures between teacher and student, and 3) intra-graph consistency to enhance the similarity between regions of same class within the graph of student.

Relation Unsupervised Domain Adaptation

Towards Accurate One-Stage Object Detection with AP-Loss

1 code implementation CVPR 2019 Kean Chen, Jianguo Li, Weiyao Lin, John See, Ji Wang, Ling-Yu Duan, Zhibo Chen, Changwei He, Junni Zou

For this purpose, we develop a novel optimization algorithm, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks.

Classification General Classification +3

Face Image Reflection Removal

no code implementations3 Mar 2019 Renjie Wan, Boxin Shi, Haoliang Li, Ling-Yu Duan, Alex C. Kot

Face images captured through the glass are usually contaminated by reflections.

Face Recognition Reflection Removal

Skeleton-Based Online Action Prediction Using Scale Selection Network

no code implementations8 Feb 2019 Jun Liu, Amir Shahroudy, Gang Wang, Ling-Yu Duan, Alex C. Kot

Since there are significant temporal scale variations in the observed part of the ongoing action at different time steps, a novel window scale selection method is proposed to make our network focus on the performed part of the ongoing action and try to suppress the possible incoming interference from the previous actions at each step.

Skeleton Based Action Recognition

Feature Boosting Network For 3D Pose Estimation

no code implementations15 Jan 2019 Jun Liu, Henghui Ding, Amir Shahroudy, Ling-Yu Duan, Xudong Jiang, Gang Wang, Alex C. Kot

Learning a set of features that are reliable and discriminatively representative of the pose of a hand (or body) part is difficult due to the ambiguities, texture and illumination variation, and self-occlusion in the real application of 3D pose estimation.

3D Hand Pose Estimation 3D Pose Estimation

Transfer Metric Learning: Algorithms, Applications and Outlooks

no code implementations9 Oct 2018 Yong Luo, Yonggang Wen, Ling-Yu Duan, DaCheng Tao

Distance metric learning (DML) aims to find an appropriate way to reveal the underlying data relationship.

Metric Learning

Intermediate Deep Feature Compression: the Next Battlefield of Intelligent Sensing

no code implementations17 Sep 2018 Zhuo Chen, Weisi Lin, Shiqi Wang, Ling-Yu Duan, Alex C. Kot

The recent advances of hardware technology have made the intelligent analysis equipped at the front-end with deep learning more prevailing and practical.

Data Compression Feature Compression

SSNet: Scale Selection Network for Online 3D Action Prediction

no code implementations CVPR 2018 Jun Liu, Amir Shahroudy, Gang Wang, Ling-Yu Duan, Alex C. Kot

As there are significant temporal scale variations of the observed part of the ongoing action at different progress levels, we propose a novel window scale selection scheme to make our network focus on the performed part of the ongoing action and try to suppress the noise from the previous actions at each time step.

Action Recognition Temporal Action Localization

CRRN: Multi-Scale Guided Concurrent Reflection Removal Network

1 code implementation CVPR 2018 Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, Alex C. Kot

Removing the undesired reflections from images taken through the glass is of broad application to various computer vision tasks.

Reflection Removal

AI Oriented Large-Scale Video Management for Smart City: Technologies, Standards and Beyond

no code implementations5 Dec 2017 Ling-Yu Duan, Yihang Lou, Shiqi Wang, Wen Gao, Yong Rui

To practically facilitate deep neural network models in the large-scale video analysis, there are still unprecedented challenges for the large-scale video data management.


Benchmarking Single-Image Reflection Removal Algorithms

no code implementations ICCV 2017 Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, Alex C. Kot

Removing undesired reflections from a photo taken in front of a glass is of great importance for enhancing the efficiency of visual computing systems.

Benchmarking Reflection Removal

Pruning Convolutional Neural Networks for Image Instance Retrieval

no code implementations18 Jul 2017 Gaurav Manek, Jie Lin, Vijay Chandrasekhar, Ling-Yu Duan, Sateesh Giduthuri, Xiao-Li Li, Tomaso Poggio

In this work, we focus on the problem of image instance retrieval with deep descriptors extracted from pruned Convolutional Neural Networks (CNN).

Image Instance Retrieval Retrieval

Global Context-Aware Attention LSTM Networks for 3D Action Recognition

no code implementations CVPR 2017 Jun Liu, Gang Wang, Ping Hu, Ling-Yu Duan, Alex C. Kot

Hence we propose a new class of LSTM network, Global Context-Aware Attention LSTM (GCA-LSTM), for 3D action recognition, which is able to selectively focus on the informative joints in the action sequence with the assistance of global contextual information.

Action Analysis One-Shot 3D Action Recognition +1

Compact Descriptors for Video Analysis: the Emerging MPEG Standard

no code implementations26 Apr 2017 Ling-Yu Duan, Vijay Chandrasekhar, Shiqi Wang, Yihang Lou, Jie Lin, Yan Bai, Tiejun Huang, Alex ChiChung Kot, Wen Gao

This paper provides an overview of the on-going compact descriptors for video analysis standard (CDVA) from the ISO/IEC moving pictures experts group (MPEG).

Improving Object Detection with Region Similarity Learning

no code implementations1 Mar 2017 Feng Gao, Yihang Lou, Yan Bai, Shiqi Wang, Tiejun Huang, Ling-Yu Duan

Object detection aims to identify instances of semantic objects of a certain class in images or videos.

Multi-Task Learning Object +2

Incorporating Intra-Class Variance to Fine-Grained Visual Recognition

no code implementations1 Mar 2017 Yan Bai, Feng Gao, Yihang Lou, Shiqi Wang, Tiejun Huang, Ling-Yu Duan

In this paper, we propose to leverage intra-class variance in metric learning of triplet network to improve the performance of fine-grained recognition.

Fine-Grained Visual Recognition Metric Learning +1

Compression of Deep Neural Networks for Image Instance Retrieval

no code implementations18 Jan 2017 Vijay Chandrasekhar, Jie Lin, Qianli Liao, Olivier Morère, Antoine Veillard, Ling-Yu Duan, Tomaso Poggio

One major drawback of CNN-based {\it global descriptors} is that uncompressed deep neural network models require hundreds of megabytes of storage making them inconvenient to deploy in mobile applications or in custom hardware.

Image Instance Retrieval Model Compression +2

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