Search Results for author: Jin Xie

Found 55 papers, 28 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

Active Simultaneously Transmitting and Reflecting Surface Assisted NOMA Networks

no code implementations25 Jan 2024 Xinwei Yue, Jin Xie, Chongjun Ouyang, Yuanwei Liu, Xia Shen, Zhiguo Ding

The numerical results are presented and show that: 1) ASTARS-NOMA with pSIC outperforms ASTARS assisted-orthogonal multiple access (ASTARS-OMA) in terms of outage probability and ergodic data rate; 2) The outage probability of ASTARS-NOMA can be further reduced within a certain range by increasing the power amplification factors; 3) The system throughputs of ASTARS-NOMA are superior to that of ASTARS-OMA in both delay-limited and delay-tolerant transmission modes.

SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection

1 code implementation21 Dec 2023 Yun Zhu, Le Hui, Yaqi Shen, Jin Xie

To this end, we propose a novel superpoint grouping network for indoor anchor-free one-stage 3D object detection.

3D Object Detection object-detection

SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation

1 code implementation27 Nov 2023 Bin Xie, Jiale Cao, Jin Xie, Fahad Shahbaz Khan, Yanwei Pang

In this paper, we propose a simple encoder-decoder, named SED, for open-vocabulary semantic segmentation, which comprises a hierarchical encoder-based cost map generation and a gradual fusion decoder with category early rejection.

Open Vocabulary Semantic Segmentation Segmentation +1

SGNet: Salient Geometric Network for Point Cloud Registration

no code implementations12 Sep 2023 Qianliang Wu, Yaqing Ding, Lei Luo, Shuo Gu, Chuanwei Zhou, Jin Xie, Jian Yang

These high-order features are then propagated to dense points and utilized by a Sinkhorn matching module to identify key correspondences for successful registration.

Point Cloud Registration

Implicit Obstacle Map-driven Indoor Navigation Model for Robust Obstacle Avoidance

1 code implementation24 Aug 2023 Wei Xie, Haobo Jiang, Shuo Gu, Jin Xie

Robust obstacle avoidance is one of the critical steps for successful goal-driven indoor navigation tasks. Due to the obstacle missing in the visual image and the possible missed detection issue, visual image-based obstacle avoidance techniques still suffer from unsatisfactory robustness.

DFormer: Diffusion-guided Transformer for Universal Image Segmentation

1 code implementation6 Jun 2023 Hefeng Wang, Jiale Cao, Rao Muhammad Anwer, Jin Xie, Fahad Shahbaz Khan, Yanwei Pang

Our DFormer outperforms the recent diffusion-based panoptic segmentation method Pix2Seq-D with a gain of 3. 6% on MS COCO val2017 set.

Denoising Image Segmentation +3

Self-Supervised 3D Scene Flow Estimation Guided by Superpoints

1 code implementation CVPR 2023 Yaqi Shen, Le Hui, Jin Xie, Jian Yang

In our superpoint generation module, we utilize the bidirectional flow information at the previous iteration to obtain the matching points of points and superpoint centers for soft point-to-superpoint association construction, in which the superpoints are generated for pairwise point clouds.

Scene Flow Estimation

Transformer-based stereo-aware 3D object detection from binocular images

no code implementations24 Apr 2023 Hanqing Sun, Yanwei Pang, Jiale Cao, Jin Xie, Xuelong Li

In this paper, we explore the model design of Transformers in binocular 3D object detection, focusing particularly on extracting and encoding the task-specific image correspondence information.

3D Object Detection Object +1

Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning

1 code implementation CVPR 2023 Kaiyou Song, Jin Xie, Shan Zhang, Zimeng Luo

Different from existing SSL-KD methods that transfer knowledge from a static pre-trained teacher to a student, in MOKD, two different models learn collaboratively in a self-supervised manner.

Knowledge Distillation Representation Learning +1

Hard Patches Mining for Masked Image Modeling

1 code implementation CVPR 2023 Haochen Wang, Kaiyou Song, Junsong Fan, Yuxi Wang, Jin Xie, Zhaoxiang Zhang

We observe that the reconstruction loss can naturally be the metric of the difficulty of the pre-training task.

Robust Outlier Rejection for 3D Registration with Variational Bayes

1 code implementation CVPR 2023 Haobo Jiang, Zheng Dang, Zhen Wei, Jin Xie, Jian Yang, Mathieu Salzmann

Embedded with the inlier/outlier label, the posterior feature distribution is label-dependent and discriminative.

Bayesian Inference

LEAPS: End-to-End One-Step Person Search With Learnable Proposals

no code implementations21 Mar 2023 Zhiqiang Dong, Jiale Cao, Rao Muhammad Anwer, Jin Xie, Fahad Khan, Yanwei Pang

Given a set of sparse and learnable proposals, LEAPS employs a dynamic person search head to directly perform person detection and corresponding re-id feature generation without non-maximum suppression post-processing.

Human Detection Person Search

Efficient LiDAR Point Cloud Oversegmentation Network

no code implementations ICCV 2023 Le Hui, Linghua Tang, Yuchao Dai, Jin Xie, Jian Yang

Then, to generate homogeneous superpoints from the sparse LiDAR point cloud, we propose a LiDAR point grouping algorithm that simultaneously considers the similarity of point embeddings and the Euclidean distance of points in 3D space.

LIDAR Semantic Segmentation Semantic Segmentation

Center-Based Decoupled Point-cloud Registration for 6D Object Pose Estimation

no code implementations ICCV 2023 Haobo Jiang, Zheng Dang, Shuo Gu, Jin Xie, Mathieu Salzmann, Jian Yang

Our method decouples the translation from the entire transformation by predicting the object center and estimating the rotation in a center-aware manner.

6D Pose Estimation using RGB Object +2

Semantics-Consistent Feature Search for Self-Supervised Visual Representation Learning

no code implementations ICCV 2023 Kaiyou Song, Shan Zhang, Zihao An, Zimeng Luo, Tong Wang, Jin Xie

In contrastive self-supervised learning, the common way to learn discriminative representation is to pull different augmented "views" of the same image closer while pushing all other images further apart, which has been proven to be effective.

Representation Learning Self-Supervised Learning

Learning Inter-Superpoint Affinity for Weakly Supervised 3D Instance Segmentation

1 code implementation11 Oct 2022 Linghua Tang, Le Hui, Jin Xie

Due to the few annotated labels of 3D point clouds, how to learn discriminative features of point clouds to segment object instances is a challenging problem.

3D Instance Segmentation Segmentation +1

Point Cloud Registration-Driven Robust Feature Matching for 3D Siamese Object Tracking

no code implementations14 Sep 2022 Haobo Jiang, Kaihao Lan, Le Hui, Guangyu Li, Jin Xie, Jian Yang

The core of Siamese feature matching is how to assign high feature similarity on the corresponding points between the template and search area for precise object localization.

Object Localization Object Tracking +1

Unsupervised Domain Adaptation for Point Cloud Semantic Segmentation via Graph Matching

no code implementations9 Aug 2022 Yikai Bian, Le Hui, Jianjun Qian, Jin Xie

Unsupervised domain adaptation for point cloud semantic segmentation has attracted great attention due to its effectiveness in learning with unlabeled data.

Graph Matching Semantic Segmentation +1

Generative Subgraph Contrast for Self-Supervised Graph Representation Learning

1 code implementation25 Jul 2022 Yuehui Han, Le Hui, Haobo Jiang, Jianjun Qian, Jin Xie

To this end, in this paper, we propose a novel adaptive subgraph generation based contrastive learning framework for efficient and robust self-supervised graph representation learning, and the optimal transport distance is utilized as the similarity metric between the subgraphs.

Contrastive Learning Graph Representation Learning +1

3D Siamese Transformer Network for Single Object Tracking on Point Clouds

1 code implementation25 Jul 2022 Le Hui, Lingpeng Wang, Linghua Tang, Kaihao Lan, Jin Xie, Jian Yang

Siamese network based trackers formulate 3D single object tracking as cross-correlation learning between point features of a template and a search area.

3D Single Object Tracking Object Tracking

RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation

1 code implementation25 Jul 2022 Mu He, Le Hui, Yikai Bian, Jian Ren, Jin Xie, Jian Yang

In this paper, we propose a resolution adaptive self-supervised monocular depth estimation method (RA-Depth) by learning the scale invariance of the scene depth.

Data Augmentation Monocular Depth Estimation

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.

Scheduling

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 Generative Adversarial Network +2

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.

Model Optimization 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 Job Shop Scheduling +1

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.

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 +2

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 +3

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 +1

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 Retrieval +1

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.

3D Place Recognition Point Cloud Retrieval +1

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.

Clustering Semantic Segmentation

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.

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.

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

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 +1

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.

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 +1

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.

Retrieval

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