Yi Yang

SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation

One-shot semantic segmentation poses a challenging task of recognizing t...
10/22/2018 ∙ by Xiaolin Zhang, et al. ∙ 46 ∙ share

read it
PointRNN: Point Recurrent Neural Network for Moving Point Cloud Processing

Point cloud is attracting more and more attention in the community. Howe...
10/18/2019 ∙ by Hehe Fan, et al. ∙ 31 ∙ share

read it
Self-Correction for Human Parsing

Labeling pixel-level masks for fine-grained semantic segmentation tasks,...
10/22/2019 ∙ by Peike Li, et al. ∙ 26 ∙ share

read it
Lane Detection in Low-light Conditions Using an Efficient Data Enhancement : Light Conditions Style Transfer

Nowadays, deep learning techniques are widely used for lane detection, b...
02/04/2020 ∙ by Tong Liu, et al. ∙ 25 ∙ share

read it
Joint Discriminative and Generative Learning for Person Re-identification

Person re-identification (re-id) remains challenging due to significant ...
04/15/2019 ∙ by Zhedong Zheng, et al. ∙ 20 ∙ share

read it
Searching for A Robust Neural Architecture in Four GPU Hours

Conventional neural architecture search (NAS) approaches are based on re...
10/10/2019 ∙ by Xuanyi Dong, et al. ∙ 18 ∙ share

read it
Cubic LSTMs for Video Prediction

Predicting future frames in videos has become a promising direction of r...
04/20/2019 ∙ by Hehe Fan, et al. ∙ 14 ∙ share

read it
Unsupervised Scene Adaptation with Memory Regularization in vivo

We consider the unsupervised scene adaptation problem of learning from b...
12/24/2019 ∙ by Zhedong Zheng, et al. ∙ 13 ∙ share

read it
Deploy Large-Scale Deep Neural Networks in Resource Constrained IoT Devices with Local Quantization Region

Implementing large-scale deep neural networks with high computational co...
05/24/2018 ∙ by Yi Yang, et al. ∙ 12 ∙ share

read it
Instance-Invariant Adaptive Object Detection via Progressive Disentanglement

Most state-of-the-art methods of object detection suffer from poor gener...
11/20/2019 ∙ by Aming Wu, et al. ∙ 11 ∙ share

read it
Learning to Transfer Learn

We propose a novel framework, learning to transfer learn (L2TL), to impr...
08/29/2019 ∙ by Linchao Zhu, et al. ∙ 10 ∙ share

read it
Learning to Adapt Invariance in Memory for Person Re-identification

This work considers the problem of unsupervised domain adaptation in per...
08/01/2019 ∙ by Zhun Zhong, et al. ∙ 7 ∙ share

read it
LSMI-Sinkhorn: Semi-supervised Squared-Loss Mutual Information Estimation with Optimal Transport

Estimating mutual information is an important machine learning and stati...
09/05/2019 ∙ by Yanbin Liu, et al. ∙ 6 ∙ share

read it
Very Long Natural Scenery Image Prediction by Outpainting

Comparing to image inpainting, image outpainting receives less attention...
12/29/2019 ∙ by Zongxin Yang, et al. ∙ 6 ∙ share

read it
Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection

Facial landmark detection aims to localize the anatomically defined poin...
08/06/2019 ∙ by Xuanyi Dong, et al. ∙ 5 ∙ share

read it
Multi-scale discriminative Region Discovery for Weakly-Supervised Object Localization

Localizing objects with weak supervision in an image is a key problem of...
09/24/2019 ∙ by Pei Lv, et al. ∙ 5 ∙ share

read it
Self-produced Guidance for Weakly-supervised Object Localization

Weakly supervised methods usually generate localization results based on...
07/24/2018 ∙ by Xiaolin Zhang, et al. ∙ 4 ∙ share

read it
Deep Unfolded Robust PCA with Application to Clutter Suppression in Ultrasound

Contrast enhanced ultrasound is a radiation-free imaging modality which ...
11/20/2018 ∙ by Oren Solomon, et al. ∙ 4 ∙ share

read it
Cascaded Revision Network for Novel Object Captioning

Image captioning, a challenging task where the machine automatically des...
08/06/2019 ∙ by Qianyu Feng, et al. ∙ 3 ∙ share

read it
3D Pose Estimation for Fine-Grained Object Categories

Existing object pose estimation datasets are related to generic object t...
06/12/2018 ∙ by Yaming Wang, et al. ∙ 2 ∙ share

read it
Revisiting EmbodiedQA: A Simple Baseline and Beyond

In Embodied Question Answering (EmbodiedQA), an agent interacts with an ...
04/08/2019 ∙ by Yu Wu, et al. ∙ 1 ∙ share

read it
Camera Style Adaptation for Person Re-identification

Being a cross-camera retrieval task, person re-identification suffers fr...
11/28/2017 ∙ by Zhun Zhong, et al. ∙ 0 ∙ share

read it
Beyond Part Models: Person Retrieval with Refined Part Pooling

Employing part-level features for pedestrian image description offers fi...
11/26/2017 ∙ by Yifan Sun, et al. ∙ 0 ∙ share

read it
Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification

Person re-identification (re-ID) models trained on one domain often fail...
11/19/2017 ∙ by Weijian Deng, et al. ∙ 0 ∙ share

read it
Occlusion Aware Unsupervised Learning of Optical Flow

It has been recently shown that a convolutional neural network can learn...
11/16/2017 ∙ by Yang Wang, et al. ∙ 0 ∙ share

read it
EraseReLU: A Simple Way to Ease the Training of Deep Convolution Neural Networks

For most state-of-the-art architectures, Rectified Linear Unit (ReLU) be...
09/22/2017 ∙ by Xuanyi Dong, et al. ∙ 0 ∙ share

read it
PatchShuffle Regularization

This paper focuses on regularizing the training of the convolutional neu...
07/22/2017 ∙ by Guoliang Kang, et al. ∙ 0 ∙ share

read it
UTS submission to Google YouTube-8M Challenge 2017

In this paper, we present our solution to Google YouTube-8M Video Classi...
07/13/2017 ∙ by Linchao Zhu, et al. ∙ 0 ∙ share

read it
Pedestrian Alignment Network for Large-scale Person Re-identification

Person re-identification (person re-ID) is mostly viewed as an image ret...
07/03/2017 ∙ by Zhedong Zheng, et al. ∙ 0 ∙ share

read it
Few-shot Object Detection

In this paper, we study object detection using a large pool of unlabeled...
06/26/2017 ∙ by Xuanyi Dong, et al. ∙ 0 ∙ share

read it
Unsupervised Person Re-identification: Clustering and Fine-tuning

The superiority of deeply learned pedestrian representations has been re...
05/30/2017 ∙ by Hehe Fan, et al. ∙ 0 ∙ share

read it
Unsupervised Learning Layers for Video Analysis

This paper presents two unsupervised learning layers (UL layers) for lab...
05/24/2017 ∙ by Liang Zhao, et al. ∙ 0 ∙ share

read it
Dynamic Computational Time for Visual Attention

We propose a dynamic computational time model to accelerate the average ...
03/30/2017 ∙ by Zhichao Li, et al. ∙ 0 ∙ share

read it
More is Less: A More Complicated Network with Less Inference Complexity

In this paper, we present a novel and general network structure towards ...
03/25/2017 ∙ by Xuanyi Dong, et al. ∙ 0 ∙ share

read it
An End-to-End Approach to Natural Language Object Retrieval via Context-Aware Deep Reinforcement Learning

We propose an end-to-end approach to the natural language object retriev...
03/22/2017 ∙ by Fan Wu, et al. ∙ 0 ∙ share

read it
Improving Person Re-identification by Attribute and Identity Learning

Person re-identification (re-ID) and attribute recognition share a commo...
03/21/2017 ∙ by Yutian Lin, et al. ∙ 0 ∙ share

read it
Twitter100k: A Real-world Dataset for Weakly Supervised Cross-Media Retrieval

This paper contributes a new large-scale dataset for weakly supervised c...
03/20/2017 ∙ by Yuting Hu, et al. ∙ 0 ∙ share

read it
A New Evaluation Protocol and Benchmarking Results for Extendable Cross-media Retrieval

This paper proposes a new evaluation protocol for cross-media retrieval ...
03/10/2017 ∙ by Ruoyu Liu, et al. ∙ 0 ∙ share

read it
Pose Invariant Embedding for Deep Person Re-identification

Pedestrian misalignment, which mainly arises from detector errors and po...
01/26/2017 ∙ by Liang Zheng, et al. ∙ 0 ∙ share

read it
Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro

The main contribution of this paper is a simple semi-supervised pipeline...
01/26/2017 ∙ by Zhedong Zheng, et al. ∙ 0 ∙ share

read it
Few-Shot Object Recognition from Machine-Labeled Web Images

With the tremendous advances of Convolutional Neural Networks (ConvNets)...
12/19/2016 ∙ by Zhongwen Xu, et al. ∙ 0 ∙ share

read it
Bidirectional Multirate Reconstruction for Temporal Modeling in Videos

Despite the recent success of neural networks in image feature learning,...
11/28/2016 ∙ by Linchao Zhu, et al. ∙ 0 ∙ share

read it
A Discriminatively Learned CNN Embedding for Person Re-identification

We revisit two popular convolutional neural networks (CNN) in person re-...
11/17/2016 ∙ by Zhedong Zheng, et al. ∙ 0 ∙ share

read it
Person Re-identification: Past, Present and Future

Person re-identification (re-ID) has become increasingly popular in the ...
10/10/2016 ∙ by Liang Zheng, et al. ∙ 0 ∙ share

read it
SIFT Meets CNN: A Decade Survey of Instance Retrieval

In the early days, content-based image retrieval (CBIR) was studied with...
08/05/2016 ∙ by Liang Zheng, et al. ∙ 0 ∙ share

read it
Strategies for Searching Video Content with Text Queries or Video Examples

The large number of user-generated videos uploaded on to the Internet ev...
06/17/2016 ∙ by Shoou-I Yu, et al. ∙ 0 ∙ share

read it
Long-Term Identity-Aware Multi-Person Tracking for Surveillance Video Summarization

Multi-person tracking plays a critical role in the analysis of surveilla...
04/25/2016 ∙ by Shoou-I Yu, et al. ∙ 0 ∙ share

read it
CNN-RNN: A Unified Framework for Multi-label Image Classification

While deep convolutional neural networks (CNNs) have shown a great succe...
04/15/2016 ∙ by Jiang Wang, et al. ∙ 0 ∙ share

read it
Person Re-identification in the Wild

We present a novel large-scale dataset and comprehensive baselines for e...
04/09/2016 ∙ by Liang Zheng, et al. ∙ 0 ∙ share

read it
Fully Convolutional Attention Networks for Fine-Grained Recognition

Fine-grained recognition is challenging due to its subtle local inter-cl...
03/22/2016 ∙ by Xiao Liu, et al. ∙ 0 ∙ share

read it

Yi Yang

Featured Co-authors