Search Results for author: Xuecheng Nie

Found 24 papers, 4 papers with code

Generative Partition Networks for Multi-Person Pose Estimation

1 code implementation21 May 2017 Xuecheng Nie, Jiashi Feng, Junliang Xing, Shuicheng Yan

This paper proposes a new Generative Partition Network (GPN) to address the challenging multi-person pose estimation problem.

 Ranked #1 on Multi-Person Pose Estimation on WAF (AP metric)

Human Detection Keypoint Detection +1

Recurrent 3D-2D Dual Learning for Large-Pose Facial Landmark Detection

no code implementations ICCV 2017 Shengtao Xiao, Jiashi Feng, Luoqi Liu, Xuecheng Nie, Wei Wang, Shuicheng Yan, Ashraf Kassim

To address these challenging issues, we introduce a novel recurrent 3D-2D dual learning model that alternatively performs 2D-based 3D face model refinement and 3D-to-2D projection based 2D landmark refinement to reliably reason about self-occluded landmarks, precisely capture the subtle landmark displacement and accurately detect landmarks even in presence of extremely large poses.

Face Model Facial Landmark Detection

Human Pose Estimation With Parsing Induced Learner

no code implementations CVPR 2018 Xuecheng Nie, Jiashi Feng, Yiming Zuo, Shuicheng Yan

Comprehensive experiments on benchmarks LIP and extended PASCAL-Person-Part show that the proposed Parsing Induced Learner can improve performance of both single- and multi-person pose estimation to new state-of-the-art.

Human Parsing Multi-Person Pose Estimation

Pose Partition Networks for Multi-Person Pose Estimation

no code implementations ECCV 2018 Xuecheng Nie, Jiashi Feng, Junliang Xing, Shuicheng Yan

This paper proposes a novel Pose Partition Network (PPN) to address the challenging multi-person pose estimation problem.

Human Detection Multi-Person Pose Estimation

Dynamic Kernel Distillation for Efficient Pose Estimation in Videos

no code implementations ICCV 2019 Xuecheng Nie, Yuncheng Li, Linjie Luo, Ning Zhang, Jiashi Feng

Existing video-based human pose estimation methods extensively apply large networks onto every frame in the video to localize body joints, which suffer high computational cost and hardly meet the low-latency requirement in realistic applications.

2D Human Pose Estimation Pose Estimation

Single-Stage Multi-Person Pose Machines

1 code implementation ICCV 2019 Xuecheng Nie, Jianfeng Zhang, Shuicheng Yan, Jiashi Feng

Based on SPR, we develop the SPM model that can directly predict structured poses for multiple persons in a single stage, and thus offer a more compact pipeline and attractive efficiency advantage over two-stage methods.

3D Pose Estimation Keypoint Detection +1

Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation

no code implementations NeurIPS 2020 Jianfeng Zhang, Xuecheng Nie, Jiashi Feng

In this work, we propose a novel framework, Inference Stage Optimization (ISO), for improving the generalizability of 3D pose models when source and target data come from different pose distributions.

Ranked #119 on 3D Human Pose Estimation on 3DPW (PA-MPJPE metric)

3D Human Pose Estimation Self-Supervised Learning

Toward Accurate Person-level Action Recognition in Videos of Crowded Scenes

no code implementations16 Oct 2020 Li Yuan, Yichen Zhou, Shuning Chang, Ziyuan Huang, Yunpeng Chen, Xuecheng Nie, Tao Wang, Jiashi Feng, Shuicheng Yan

Prior works always fail to deal with this problem in two aspects: (1) lacking utilizing information of the scenes; (2) lacking training data in the crowd and complex scenes.

Action Recognition In Videos Semantic Segmentation

Towards Accurate Human Pose Estimation in Videos of Crowded Scenes

no code implementations16 Oct 2020 Li Yuan, Shuning Chang, Xuecheng Nie, Ziyuan Huang, Yichen Zhou, Yunpeng Chen, Jiashi Feng, Shuicheng Yan

In this paper, we focus on improving human pose estimation in videos of crowded scenes from the perspectives of exploiting temporal context and collecting new data.

Optical Flow Estimation Pose Estimation

A Simple Baseline for Pose Tracking in Videos of Crowded Scenes

no code implementations16 Oct 2020 Li Yuan, Shuning Chang, Ziyuan Huang, Yichen Zhou, Yunpeng Chen, Xuecheng Nie, Francis E. H. Tay, Jiashi Feng, Shuicheng Yan

This paper presents our solution to ACM MM challenge: Large-scale Human-centric Video Analysis in Complex Events\cite{lin2020human}; specifically, here we focus on Track3: Crowd Pose Tracking in Complex Events.

Multi-Object Tracking Optical Flow Estimation +1

DFS: A Diverse Feature Synthesis Model for Generalized Zero-Shot Learning

no code implementations19 Mar 2021 Bonan Li, Xuecheng Nie, Congying Han

In this paper, we propose to enhance the generalizability of GZSL models via improving feature diversity of unseen classes.

Generalized Zero-Shot Learning

Body Meshes as Points

1 code implementation CVPR 2021 Jianfeng Zhang, Dongdong Yu, Jun Hao Liew, Xuecheng Nie, Jiashi Feng

In this work, we present a single-stage model, Body Meshes as Points (BMP), to simplify the pipeline and lift both efficiency and performance.

3D Human Shape Estimation 3D Multi-Person Pose Estimation +1

Single-Stage Is Enough: Multi-Person Absolute 3D Pose Estimation

no code implementations CVPR 2022 Lei Jin, Chenyang Xu, Xiaojuan Wang, Yabo Xiao, Yandong Guo, Xuecheng Nie, Jian Zhao

The existing multi-person absolute 3D pose estimation methods are mainly based on two-stage paradigm, i. e., top-down or bottom-up, leading to redundant pipelines with high computation cost.

3D Pose Estimation Depth Estimation +1

DropKey

no code implementations4 Aug 2022 Bonan Li, Yinhan Hu, Xuecheng Nie, Congying Han, Xiangjian Jiang, Tiande Guo, Luoqi Liu

Given exploration on the above three questions, we present the novel DropKey method that regards Key as the drop unit and exploits decreasing schedule for drop ratio, improving ViTs in a general way.

Human-Object Interaction Detection Image Classification +2

Multi-view Human Body Mesh Translator

no code implementations4 Oct 2022 Xiangjian Jiang, Xuecheng Nie, Zitian Wang, Luoqi Liu, Si Liu

Existing methods for human mesh recovery mainly focus on single-view frameworks, but they often fail to produce accurate results due to the ill-posed setup.

Human Mesh Recovery

Masked Reconstruction Contrastive Learning with Information Bottleneck Principle

no code implementations15 Nov 2022 Ziwen Liu, Bonan Li, Congying Han, Tiande Guo, Xuecheng Nie

In order to alleviate the discriminative information overfitting problem effectively, we employ the reconstruction task to regularize the discriminative task.

Contrastive Learning Self-Supervised Image Classification +2

DropKey for Vision Transformer

no code implementations CVPR 2023 Bonan Li, Yinhan Hu, Xuecheng Nie, Congying Han, Xiangjian Jiang, Tiande Guo, Luoqi Liu

Given exploration on the above three questions, we present the novel DropKey method that regards Key as the drop unit and exploits decreasing schedule for drop ratio, improving ViTs in a general way.

Human-Object Interaction Detection Image Classification +2

StyO: Stylize Your Face in Only One-Shot

no code implementations6 Mar 2023 Bonan Li, ZiCheng Zhang, Xuecheng Nie, Congying Han, Yinhan Hu, Tiande Guo

And it introduces a novel triple reconstruction loss to fine-tune the pre-trained LDM for encoding style and content into corresponding identifiers; 2) Fine-grained Content Controller (FCC) for the recombination phase.

Disentanglement One-Shot Face Stylization

DiffBFR: Bootstrapping Diffusion Model Towards Blind Face Restoration

no code implementations8 May 2023 Xinmin Qiu, Congying Han, ZiCheng Zhang, Bonan Li, Tiande Guo, Xuecheng Nie

This design is implemented with two key components: 1) Identity Restoration Module (IRM) for preserving the face details in results.

Blind Face Restoration Denoising

Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training

no code implementations4 Dec 2023 Runze He, Shaofei Huang, Xuecheng Nie, Tianrui Hui, Luoqi Liu, Jiao Dai, Jizhong Han, Guanbin Li, Si Liu

In this paper, we target the adaptive source driven 3D scene editing task by proposing a CustomNeRF model that unifies a text description or a reference image as the editing prompt.

3D scene Editing

BlazeBVD: Make Scale-Time Equalization Great Again for Blind Video Deflickering

no code implementations10 Mar 2024 Xinmin Qiu, Congying Han, ZiCheng Zhang, Bonan Li, Tiande Guo, Pingyu Wang, Xuecheng Nie

Developing blind video deflickering (BVD) algorithms to enhance video temporal consistency, is gaining importance amid the flourish of image processing and video generation.

Video Generation Video Temporal Consistency

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