Search Results for author: Ziyan Wu

Found 50 papers, 14 papers with code

Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images

no code implementations12 Jul 2024 Tianyu Luan, Zhongpai Gao, Luyuan Xie, Abhishek Sharma, Hao Ding, Benjamin Planche, Meng Zheng, Ange Lou, Terrence Chen, Junsong Yuan, Ziyan Wu

Traditional top-down methods, relying on whole-body parametric models like SMPL, falter when only a small part of the human is visible, as they require visibility of most of the human body for accurate mesh reconstruction.

DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Rendering

no code implementations4 Jun 2024 Zhongpai Gao, Benjamin Planche, Meng Zheng, Xiao Chen, Terrence Chen, Ziyan Wu

Digitally reconstructed radiographs (DRRs) are simulated 2D X-ray images generated from 3D CT volumes, widely used in preoperative settings but limited in intraoperative applications due to computational bottlenecks, especially for accurate but heavy physics-based Monte Carlo methods.

Self-learning Canonical Space for Multi-view 3D Human Pose Estimation

no code implementations19 Mar 2024 Xiaoben Li, Mancheng Meng, Ziyan Wu, Terrence Chen, Fan Yang, Dinggang Shen

To facilitate the aggregation of the intra- and inter-view, we define a canonical parameter space, depicted by per-view camera pose and human pose and shape parameters ($\theta$ and $\beta$) of SMPL model, and propose a two-stage learning procedure.

3D Human Pose Estimation Multi-view 3D Human Pose Estimation +1

Human Mesh Recovery from Arbitrary Multi-view Images

1 code implementation19 Mar 2024 Xiaoben Li, Mancheng Meng, Ziyan Wu, Terrence Chen, Fan Yang, Dinggang Shen

Human mesh recovery from arbitrary multi-view images involves two characteristics: the arbitrary camera poses and arbitrary number of camera views.

Camera Pose Estimation Decoder +2

Automating Catheterization Labs with Real-Time Perception

no code implementations9 Mar 2024 Fan Yang, Benjamin Planche, Meng Zheng, Cheng Chen, Terrence Chen, Ziyan Wu

For decades, three-dimensional C-arm Cone-Beam Computed Tomography (CBCT) imaging system has been a critical component for complex vascular and nonvascular interventional procedures.

Self-supervised 3D Patient Modeling with Multi-modal Attentive Fusion

no code implementations5 Mar 2024 Meng Zheng, Benjamin Planche, Xuan Gong, Fan Yang, Terrence Chen, Ziyan Wu

3D patient body modeling is critical to the success of automated patient positioning for smart medical scanning and operating rooms.

Keypoint Detection

DaReNeRF: Direction-aware Representation for Dynamic Scenes

no code implementations CVPR 2024 Ange Lou, Benjamin Planche, Zhongpai Gao, Yamin Li, Tianyu Luan, Hao Ding, Terrence Chen, Jack Noble, Ziyan Wu

However, the straightforward decomposition of 4D dynamic scenes into multiple 2D plane-based representations proves insufficient for re-rendering high-fidelity scenes with complex motions.

Novel View Synthesis

PBADet: A One-Stage Anchor-Free Approach for Part-Body Association

no code implementations12 Feb 2024 Zhongpai Gao, Huayi Zhou, Abhishek Sharma, Meng Zheng, Benjamin Planche, Terrence Chen, Ziyan Wu

The detection of human parts (e. g., hands, face) and their correct association with individuals is an essential task, e. g., for ubiquitous human-machine interfaces and action recognition.

Action Recognition

Federated Learning via Input-Output Collaborative Distillation

1 code implementation22 Dec 2023 Xuan Gong, Shanglin Li, Yuxiang Bao, Barry Yao, Yawen Huang, Ziyan Wu, Baochang Zhang, Yefeng Zheng, David Doermann

Federated learning (FL) is a machine learning paradigm in which distributed local nodes collaboratively train a central model without sharing individually held private data.

Federated Learning Image Classification

Implicit Modeling of Non-rigid Objects with Cross-Category Signals

no code implementations15 Dec 2023 Yuchun Liu, Benjamin Planche, Meng Zheng, Zhongpai Gao, Pierre Sibut-Bourde, Fan Yang, Terrence Chen, Ziyan Wu

To effectively capture the interrelation between these entities and ensure precise, collision-free representations, our approach facilitates signaling between category-specific fields to adequately rectify shapes.


IBAFormer: Intra-batch Attention Transformer for Domain Generalized Semantic Segmentation

no code implementations12 Sep 2023 Qiyu Sun, Huilin Chen, Meng Zheng, Ziyan Wu, Michael Felsberg, Yang Tang

Domain generalized semantic segmentation (DGSS) is a critical yet challenging task, where the model is trained only on source data without access to any target data.

Semantic Segmentation

CMDA: Cross-Modality Domain Adaptation for Nighttime Semantic Segmentation

1 code implementation ICCV 2023 Ruihao Xia, Chaoqiang Zhao, Meng Zheng, Ziyan Wu, Qiyu Sun, Yang Tang

However, limited by the low dynamic range of conventional cameras, images fail to capture structural details and boundary information in low-light conditions.

Domain Adaptation Segmentation +1

Disguise without Disruption: Utility-Preserving Face De-Identification

no code implementations23 Mar 2023 Zikui Cai, Zhongpai Gao, Benjamin Planche, Meng Zheng, Terrence Chen, M. Salman Asif, Ziyan Wu

We extensively evaluate our method using multiple datasets, demonstrating a higher de-identification rate and superior consistency compared to prior approaches in various downstream tasks.

De-identification Ensemble Learning

Exploring Cycle Consistency Learning in Interactive Volume Segmentation

1 code implementation11 Mar 2023 Qin Liu, Meng Zheng, Benjamin Planche, Zhongpai Gao, Terrence Chen, Marc Niethammer, Ziyan Wu

Given a medical volume, a user first segments a slice (or several slices) via the interaction module and then propagates the segmentation(s) to the remaining slices.


Progressive Multi-view Human Mesh Recovery with Self-Supervision

no code implementations10 Dec 2022 Xuan Gong, Liangchen Song, Meng Zheng, Benjamin Planche, Terrence Chen, Junsong Yuan, David Doermann, Ziyan Wu

To date, little attention has been given to multi-view 3D human mesh estimation, despite real-life applicability (e. g., motion capture, sport analysis) and robustness to single-view ambiguities.

Benchmarking Diversity +1

Forecasting Human Trajectory from Scene History

1 code implementation17 Oct 2022 Mancheng Meng, Ziyan Wu, Terrence Chen, Xiran Cai, Xiang Sean Zhou, Fan Yang, Dinggang Shen

We categorize scene history information into two types: historical group trajectory and individual-surroundings interaction.

Trajectory Prediction

Self-supervised Human Mesh Recovery with Cross-Representation Alignment

no code implementations10 Sep 2022 Xuan Gong, Meng Zheng, Benjamin Planche, Srikrishna Karanam, Terrence Chen, David Doermann, Ziyan Wu

However, on synthetic dense correspondence maps (i. e., IUV) few have been explored since the domain gap between synthetic training data and real testing data is hard to address for 2D dense representation.

Diversity Human Mesh Recovery

Preserving Privacy in Federated Learning with Ensemble Cross-Domain Knowledge Distillation

no code implementations10 Sep 2022 Xuan Gong, Abhishek Sharma, Srikrishna Karanam, Ziyan Wu, Terrence Chen, David Doermann, Arun Innanje

Federated Learning (FL) is a machine learning paradigm where local nodes collaboratively train a central model while the training data remains decentralized.

Federated Learning Image Classification +4

PseudoClick: Interactive Image Segmentation with Click Imitation

no code implementations12 Jul 2022 Qin Liu, Meng Zheng, Benjamin Planche, Srikrishna Karanam, Terrence Chen, Marc Niethammer, Ziyan Wu

The goal of click-based interactive image segmentation is to obtain precise object segmentation masks with limited user interaction, i. e., by a minimal number of user clicks.

Image Segmentation Segmentation +1

SMPL-A: Modeling Person-Specific Deformable Anatomy

no code implementations CVPR 2022 Hengtao Guo, Benjamin Planche, Meng Zheng, Srikrishna Karanam, Terrence Chen, Ziyan Wu

In order to obtain accurate target location information, clinicians have to either conduct frequent intraoperative scans, resulting in higher exposition of patients to radiations, or adopt proxy procedures (e. g., creating and using custom molds to keep patients in the exact same pose during both preoperative organ scanning and subsequent treatment.

Anatomy Human Mesh Recovery

Learning Hierarchical Attention for Weakly-supervised Chest X-Ray Abnormality Localization and Diagnosis

1 code implementation23 Dec 2021 Xi Ouyang, Srikrishna Karanam, Ziyan Wu, Terrence Chen, Jiayu Huo, Xiang Sean Zhou, Qian Wang, Jie-Zhi Cheng

However, doing this accurately will require a large amount of disease localization annotations by clinical experts, a task that is prohibitively expensive to accomplish for most applications.

Decision Making

Towards Generic Interface for Human-Neural Network Knowledge Exchange

no code implementations29 Sep 2021 Yunhao Ge, Yao Xiao, Zhi Xu, Linwei Li, Ziyan Wu, Laurent Itti

Take image classification as an example, HNI visualizes the reasoning logic of a NN with class-specific Structural Concept Graphs (c-SCG), which are human-interpretable.

Image Classification Zero-Shot Learning

Learning Local Recurrent Models for Human Mesh Recovery

no code implementations27 Jul 2021 Runze Li, Srikrishna Karanam, Ren Li, Terrence Chen, Bir Bhanu, Ziyan Wu

We conduct a variety of experiments on standard video mesh recovery benchmark datasets such as Human3. 6M, MPI-INF-3DHP, and 3DPW, demonstrating the efficacy of our design of modeling local dynamics as well as establishing state-of-the-art results based on standard evaluation metrics.

3D Human Pose Estimation 3D Human Shape Estimation +1

Spatio-Temporal Representation Factorization for Video-based Person Re-Identification

no code implementations ICCV 2021 Abhishek Aich, Meng Zheng, Srikrishna Karanam, Terrence Chen, Amit K. Roy-Chowdhury, Ziyan Wu

To alleviate these problems, we propose Spatio-Temporal Representation Factorization (STRF), a flexible new computational unit that can be used in conjunction with most existing 3D convolutional neural network architectures for re-ID.

Video-Based Person Re-Identification

Everybody Is Unique: Towards Unbiased Human Mesh Recovery

no code implementations13 Jul 2021 Ren Li, Meng Zheng, Srikrishna Karanam, Terrence Chen, Ziyan Wu

Next, we present a simple baseline to address this problem that is scalable and can be easily used in conjunction with existing algorithms to improve their performance.

 Ranked #1 on 3D Human Shape Estimation on SSP-3D (PVE-T metric)

3D Human Pose Estimation 3D Human Shape Estimation +1

Ensemble Attention Distillation for Privacy-Preserving Federated Learning

no code implementations ICCV 2021 Xuan Gong, Abhishek Sharma, Srikrishna Karanam, Ziyan Wu, Terrence Chen, David Doermann, Arun Innanje

Such decentralized training naturally leads to issues of imbalanced or differing data distributions among the local models and challenges in fusing them into a central model.

Federated Learning Privacy Preserving

Towards Visually Explaining Similarity Models

no code implementations13 Aug 2020 Meng Zheng, Srikrishna Karanam, Terrence Chen, Richard J. Radke, Ziyan Wu

We show that the resulting similarity models perform, and can be visually explained, better than the corresponding baseline models trained without these constraints.

Image Retrieval Metric Learning +3

Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19

1 code implementation6 Apr 2020 Feng Shi, Jun Wang, Jun Shi, Ziyan Wu, Qian Wang, Zhenyu Tang, Kelei He, Yinghuan Shi, Dinggang Shen

In this review paper, we thus cover the entire pipeline of medical imaging and analysis techniques involved with COVID-19, including image acquisition, segmentation, diagnosis, and follow-up.

Computed Tomography (CT)

Hierarchical Kinematic Human Mesh Recovery

no code implementations ECCV 2020 Georgios Georgakis, Ren Li, Srikrishna Karanam, Terrence Chen, Jana Kosecka, Ziyan Wu

In this work, we address this gap by proposing a new technique for regression of human parametric model that is explicitly informed by the known hierarchical structure, including joint interdependencies of the model.

Human Mesh Recovery regression

Towards Visually Explaining Variational Autoencoders

2 code implementations CVPR 2020 Wenqian Liu, Runze Li, Meng Zheng, Srikrishna Karanam, Ziyan Wu, Bir Bhanu, Richard J. Radke, Octavia Camps

We present methods to generate visual attention from the learned latent space, and also demonstrate such attention explanations serve more than just explaining VAE predictions.


Visual Similarity Attention

no code implementations18 Nov 2019 Meng Zheng, Srikrishna Karanam, Terrence Chen, Richard J. Radke, Ziyan Wu

While there has been substantial progress in learning suitable distance metrics, these techniques in general lack transparency and decision reasoning, i. e., explaining why the input set of images is similar or dissimilar.

Image Retrieval Person Re-Identification +2

Counterfactual Visual Explanations

1 code implementation16 Apr 2019 Yash Goyal, Ziyan Wu, Jan Ernst, Dhruv Batra, Devi Parikh, Stefan Lee

In this work, we develop a technique to produce counterfactual visual explanations.

counterfactual General Classification +1

Incremental Scene Synthesis

no code implementations NeurIPS 2019 Benjamin Planche, Xuejian Rong, Ziyan Wu, Srikrishna Karanam, Harald Kosch, YingLi Tian, Jan Ernst, Andreas Hutter

We present a method to incrementally generate complete 2D or 3D scenes with the following properties: (a) it is globally consistent at each step according to a learned scene prior, (b) real observations of a scene can be incorporated while observing global consistency, (c) unobserved regions can be hallucinated locally in consistence with previous observations, hallucinations and global priors, and (d) hallucinations are statistical in nature, i. e., different scenes can be generated from the same observations.

Autonomous Navigation Hallucination

Learning without Memorizing

1 code implementation CVPR 2019 Prithviraj Dhar, Rajat Vikram Singh, Kuan-Chuan Peng, Ziyan Wu, Rama Chellappa

Incremental learning (IL) is an important task aimed at increasing the capability of a trained model, in terms of the number of classes recognizable by the model.

Incremental Learning

Sharpen Focus: Learning with Attention Separability and Consistency

1 code implementation ICCV 2019 Lezi Wang, Ziyan Wu, Srikrishna Karanam, Kuan-Chuan Peng, Rajat Vikram Singh, Bo Liu, Dimitris N. Metaxas

Recent developments in gradient-based attention modeling have seen attention maps emerge as a powerful tool for interpreting convolutional neural networks.

General Classification Image Classification

Learning Local RGB-to-CAD Correspondences for Object Pose Estimation

1 code implementation ICCV 2019 Georgios Georgakis, Srikrishna Karanam, Ziyan Wu, Jana Kosecka

In this paper, we solve this key problem of existing methods requiring expensive 3D pose annotations by proposing a new method that matches RGB images to CAD models for object pose estimation.

Object Pose Estimation

Seeing Beyond Appearance - Mapping Real Images into Geometrical Domains for Unsupervised CAD-based Recognition

no code implementations9 Oct 2018 Benjamin Planche, Sergey Zakharov, Ziyan Wu, Andreas Hutter, Harald Kosch, Slobodan Ilic

Applying our approach to object recognition from texture-less CAD data, we present a custom generative network which fully utilizes the purely geometrical information to learn robust features and achieve a more refined mapping for unseen color images.

Denoising Domain Adaptation +1

Keep it Unreal: Bridging the Realism Gap for 2.5D Recognition with Geometry Priors Only

no code implementations24 Apr 2018 Sergey Zakharov, Benjamin Planche, Ziyan Wu, Andreas Hutter, Harald Kosch, Slobodan Ilic

With the increasing availability of large databases of 3D CAD models, depth-based recognition methods can be trained on an uncountable number of synthetically rendered images.

Generative Adversarial Network

Tell Me Where to Look: Guided Attention Inference Network

2 code implementations CVPR 2018 Kunpeng Li, Ziyan Wu, Kuan-Chuan Peng, Jan Ernst, Yun Fu

Weakly supervised learning with only coarse labels can obtain visual explanations of deep neural network such as attention maps by back-propagating gradients.

Object Localization Semantic Segmentation +1

End-to-end learning of keypoint detector and descriptor for pose invariant 3D matching

no code implementations CVPR 2018 Georgios Georgakis, Srikrishna Karanam, Ziyan Wu, Jan Ernst, Jana Kosecka

Finding correspondences between images or 3D scans is at the heart of many computer vision and image retrieval applications and is often enabled by matching local keypoint descriptors.

Image Retrieval Keypoint Detection +2

Learning Compositional Visual Concepts with Mutual Consistency

no code implementations CVPR 2018 Yunye Gong, Srikrishna Karanam, Ziyan Wu, Kuan-Chuan Peng, Jan Ernst, Peter C. Doerschuk

Compositionality of semantic concepts in image synthesis and analysis is appealing as it can help in decomposing known and generatively recomposing unknown data.

Data Augmentation Face Verification +1

Weakly Supervised Summarization of Web Videos

no code implementations ICCV 2017 Rameswar Panda, Abir Das, Ziyan Wu, Jan Ernst, Amit K. Roy-Chowdhury

Casting the problem as a weakly supervised learning problem, we propose a flexible deep 3D CNN architecture to learn the notion of importance using only video-level annotation, and without any human-crafted training data.

Weakly-supervised Learning

Zero-Shot Deep Domain Adaptation

no code implementations ECCV 2018 Kuan-Chuan Peng, Ziyan Wu, Jan Ernst

Therefore, the source-domain task of interest solution (e. g. a classifier for classification tasks) which is jointly trained with the source-domain representation can be applicable to both the source and target representations.

Classification Domain Adaptation +3

A Systematic Evaluation and Benchmark for Person Re-Identification: Features, Metrics, and Datasets

3 code implementations31 May 2016 Srikrishna Karanam, Mengran Gou, Ziyan Wu, Angels Rates-Borras, Octavia Camps, Richard J. Radke

To ensure a fair comparison, all of the approaches were implemented using a unified code library that includes 11 feature extraction algorithms and 22 metric learning and ranking techniques.

Metric Learning Person Re-Identification

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