Search Results for author: Jin Xie

Found 32 papers, 16 papers with code

Count- and Similarity-aware R-CNN for Pedestrian Detection

no code implementations ECCV 2020 Jin Xie, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan, Yanwei Pang, Ling Shao, Mubarak Shah

We further introduce a count-and-similarity branch within the two-stage detection framework, which predicts pedestrian count as well as proposal similarity.

Human Instance Segmentation Pedestrian Detection +1

Unsupervised Visible-light Images Guided Cross-Spectrum Depth Estimation from Dual-Modality Cameras

no code implementations30 Apr 2022 Yubin Guo, Haobo Jiang, Xinlei Qi, Jin Xie, Cheng-Zhong Xu, Hui Kong

Meanwhile, we release a large dual-spectrum depth estimation dataset with visible-light and far-infrared stereo images captured in different scenes to the society.

Depth Estimation

PSTR: End-to-End One-Step Person Search With Transformers

1 code implementation CVPR 2022 Jiale Cao, Yanwei Pang, Rao Muhammad Anwer, Hisham Cholakkal, Jin Xie, Mubarak Shah, Fahad Shahbaz Khan

We propose a novel one-step transformer-based person search framework, PSTR, that jointly performs person detection and re-identification (re-id) in a single architecture.

Human Detection Person Search

Action Candidate Driven Clipped Double Q-learning for Discrete and Continuous Action Tasks

1 code implementation22 Mar 2022 Haobo Jiang, Jin Xie, Jian Yang

Finally, we use the maximum value in the second set of estimators to clip the action value of the chosen action in the first set of estimators and the clipped value is used for approximating the maximum expected action value.

Q-Learning

The Design and Implementation of a Broadly Applicable Algorithm for Optimizing Intra-Day Surgical Scheduling

no code implementations14 Mar 2022 Jin Xie, Teng Zhang, Jose Blanchet, Peter Glynn, Matthew Randolph, David Scheinker

In order for an algorithm to see sustained use, it must be compatible with changes to hospital capacity, patient volumes, and scheduling practices.

Domain Disentangled Generative Adversarial Network for Zero-Shot Sketch-Based 3D Shape Retrieval

no code implementations24 Feb 2022 Rui Xu, Zongyan Han, Le Hui, Jianjun Qian, Jin Xie

Then, we develop a generative adversarial network that combines the domain-specific features of the seen categories with the aligned domain-invariant features to synthesize samples, where the synthesized samples of the unseen categories are generated by using the corresponding word embeddings.

3D Shape Retrieval Word Embeddings

Reliable Inlier Evaluation for Unsupervised Point Cloud Registration

1 code implementation23 Feb 2022 Yaqi Shen, Le Hui, Haobo Jiang, Jin Xie, Jian Yang

In this paper, we propose a neighborhood consensus based reliable inlier evaluation method for robust unsupervised point cloud registration.

Point Cloud Registration

3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds

1 code implementation NeurIPS 2021 Le Hui, Lingpeng Wang, Mingmei Cheng, Jin Xie, Jian Yang

The Siamese shape-aware feature learning network can capture 3D shape information of the object to learn the discriminative features of the object so that the potential target from the background in sparse point clouds can be identified.

3D Object Tracking Object Tracking

Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration

1 code implementation ICCV 2021 Haobo Jiang, Yaqi Shen, Jin Xie, Jun Li, Jianjun Qian, Jian Yang

Based on the reward function, for each state, we then construct a fused score function to evaluate the sampled transformations, where we weight the current and future rewards of the transformations.

Point Cloud Registration

A new neighborhood structure for job shop scheduling problems

no code implementations7 Sep 2021 Jin Xie, Xinyu Li, Liang Gao, Lin Gui

According to the above finding, this paper proposes a new N8 neighborhood structure considering the movement of critical operations within a critical block and the movement of critical operations outside the critical block.

Combinatorial Optimization

UnDeepLIO: Unsupervised Deep Lidar-Inertial Odometry

no code implementations3 Sep 2021 Yiming Tu, Jin Xie

Nonetheless, few efforts are made on the unsupervised deep lidar odometry.

Translation

Planning with Learned Dynamic Model for Unsupervised Point Cloud Registration

no code implementations5 Aug 2021 Haobo Jiang, Jin Xie, Jianjun Qian, Jian Yang

By modeling the point cloud registration process as a Markov decision process (MDP), we develop a latent dynamic model of point clouds, consisting of a transformation network and evaluation network.

Computer Vision Point Cloud Registration

SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Rendering

1 code implementation1 Aug 2021 Yifan Zhao, Le Hui, Jin Xie

To achieve this, we exploit the consistency between the input sparse point cloud and generated dense point cloud for the shapes and rendered images.

Action Candidate Based Clipped Double Q-learning for Discrete and Continuous Action Tasks

1 code implementation3 May 2021 Haobo Jiang, Jin Xie, Jian Yang

Finally, we use the maximum value in the second set of estimators to clip the action value of the chosen action in the first set of estimators and the clipped value is used for approximating the maximum expected action value.

Q-Learning

SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network

1 code implementation16 Apr 2021 Mingmei Cheng, Le Hui, Jin Xie, Jian Yang

In order to reduce the number of annotated labels, we propose a semi-supervised semantic point cloud segmentation network, named SSPC-Net, where we train the semantic segmentation network by inferring the labels of unlabeled points from the few annotated 3D points.

Point Cloud Segmentation Scene Understanding +1

SIENet: Spatial Information Enhancement Network for 3D Object Detection from Point Cloud

1 code implementation29 Mar 2021 Ziyu Li, Yuncong Yao, Zhibin Quan, Wankou Yang, Jin Xie

Specifically, we design the Spatial Information Enhancement (SIE) module to predict the spatial shapes of the foreground points within proposals, and extract the structure information to learn the representative features for further box refinement.

3D Object Detection Autonomous Vehicles +2

MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation

no code implementations24 Mar 2021 Guangwei Gao, Guoan Xu, Yi Yu, Jin Xie, Jian Yang, Dong Yue

In recent years, how to strike a good trade-off between accuracy and inference speed has become the core issue for real-time semantic segmentation applications, which plays a vital role in real-world scenarios such as autonomous driving systems and drones.

Autonomous Driving Real-Time Semantic Segmentation

Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition

1 code implementation7 Jan 2021 Le Hui, Mingmei Cheng, Jin Xie, Jian Yang

In this paper, we develop an efficient point cloud learning network (EPC-Net) to form a global descriptor for visual place recognition, which can obtain good performance and reduce computation memory and inference time.

Point Cloud Retrieval Visual Place Recognition

Superpoint Network for Point Cloud Oversegmentation

1 code implementation ICCV 2021 Le Hui, Jia Yuan, Mingmei Cheng, Jin Xie, Xiaoya Zhang, Jian Yang

Specifically, in our clustering network, we first jointly learn a soft point-superpoint association map from the coordinate and feature spaces of point clouds, where each point is assigned to the superpoint with a learned weight.

Semantic Segmentation

Pyramid Point Cloud Transformer for Large-Scale Place Recognition

1 code implementation ICCV 2021 Le Hui, Hang Yang, Mingmei Cheng, Jin Xie, Jian Yang

In order to obtain discriminative global descriptors, we construct a pyramid VLAD module to aggregate the multi-scale feature maps of point clouds into the global descriptors.

Point Cloud Retrieval

From Handcrafted to Deep Features for Pedestrian Detection: A Survey

2 code implementations1 Oct 2020 Jiale Cao, Yanwei Pang, Jin Xie, Fahad Shahbaz Khan, Ling Shao

In addition to single-spectral pedestrian detection, we also review multi-spectral pedestrian detection, which provides more robust features for illumination variance.

Computer Vision Pedestrian Detection

Progressive Point Cloud Deconvolution Generation Network

1 code implementation ECCV 2020 Le Hui, Rui Xu, Jin Xie, Jianjun Qian, Jian Yang

Starting from the low-resolution point clouds, with the bilateral interpolation and max-pooling operations, the deconvolution network can progressively output high-resolution local and global feature maps.

Point Cloud Generation

PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection

no code implementations25 Jan 2020 Jin Xie, Yanwei Pang, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan, Ling Shao

On the heavy occluded (\textbf{HO}) set of CityPerosns test set, our PSC-Net obtains an absolute gain of 4. 0\% in terms of log-average miss rate over the state-of-the-art with same backbone, input scale and without using additional VBB supervision.

Computer Vision Pedestrian Detection

A Two-stream End-to-End Deep Learning Network for Recognizing Atypical Visual Attention in Autism Spectrum Disorder

no code implementations26 Nov 2019 Jin Xie, Longfei Wang, Paula Webster, Yang Yao, Jiayao Sun, Shuo Wang, Huihui Zhou

In this study, we developed a novel two-stream deep learning network for this recognition based on 700 images and corresponding eye movement patterns of ASD and TD, and obtained an accuracy of 0. 95, which was higher than the previous state-of-the-art.

Classification General Classification

Mask-Guided Attention Network for Occluded Pedestrian Detection

1 code implementation ICCV 2019 Yanwei Pang, Jin Xie, Muhammad Haris Khan, Rao Muhammad Anwer, Fahad Shahbaz Khan, Ling Shao

Our approach obtains an absolute gain of 9. 5% in log-average miss rate, compared to the best reported results on the heavily occluded (HO) pedestrian set of CityPersons test set.

Pedestrian Detection

A Method to Facilitate Cancer Detection and Type Classification from Gene Expression Data using a Deep Autoencoder and Neural Network

no code implementations20 Dec 2018 Xi Chen, Jin Xie, Qingcong Yuan

Here we present models of deep learning (DL) and apply them to gene expression data for the diagnosis and categorization of cancer.

General Classification

Learning Barycentric Representations of 3D Shapes for Sketch-Based 3D Shape Retrieval

no code implementations CVPR 2017 Jin Xie, Guoxian Dai, Fan Zhu, Yi Fang

For 3D shapes, we then compute the Wasserstein barycenters of deep features of multiple projections to form a barycentric representation.

3D Shape Classification 3D Shape Retrieval

Learned Binary Spectral Shape Descriptor for 3D Shape Correspondence

no code implementations CVPR 2016 Jin Xie, Meng Wang, Yi Fang

Different from these real-valued local shape descriptors, in this paper, we propose to learn a novel binary spectral shape descriptor with the deep neural network for 3D shape correspondence.

Computer Vision

DeepShape: Deep Learned Shape Descriptor for 3D Shape Matching and Retrieval

no code implementations CVPR 2015 Jin Xie, Yi Fang, Fan Zhu, Edward Wong

Then, by imposing the Fisher discrimination criterion on the neurons in the hidden layer, we developed a novel discriminative deep auto-encoder for shape feature learning.

Benchmark

3D Deep Shape Descriptor

no code implementations CVPR 2015 Yi Fang, Jin Xie, Guoxian Dai, Meng Wang, Fan Zhu, Tiantian Xu, Edward Wong

Shape descriptor is a concise yet informative representation that provides a 3D object with an identification as a member of some category.

3D Shape Classification 3D Shape Retrieval

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