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.
3 code implementations • 31 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.
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.
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.
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.
1 code implementation • 16 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.
1 code implementation • 23 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.
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.
1 code implementation • 11 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.
1 code implementation • 17 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.
1 code implementation • 6 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.
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.
1 code implementation • 22 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.
no code implementations • 24 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.
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.
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.
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.
no code implementations • 27 Feb 2017 • Benjamin Planche, Ziyan Wu, Kai Ma, Shanhui Sun, Stefan Kluckner, Terrence Chen, Andreas Hutter, Sergey Zakharov, Harald Kosch, Jan Ernst
Recent progress in computer vision has been dominated by deep neural networks trained over large amounts of labeled data.
no code implementations • 9 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.
no code implementations • CVPR 2019 • Meng Zheng, Srikrishna Karanam, Ziyan Wu, Richard J. Radke
We propose a new deep architecture for person re-identification (re-id).
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.
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.
no code implementations • 18 Nov 2019 • Ren Li, Changjiang Cai, Georgios Georgakis, Srikrishna Karanam, Terrence Chen, Ziyan Wu
We consider the problem of human pose estimation.
no code implementations • 18 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.
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.
no code implementations • 13 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.
no code implementations • CVPR 2021 • Yunhao Ge, Yao Xiao, Zhi Xu, Meng Zheng, Srikrishna Karanam, Terrence Chen, Laurent Itti, Ziyan Wu
Despite substantial progress in applying neural networks (NN) to a wide variety of areas, they still largely suffer from a lack of transparency and interpretability.
no code implementations • 13 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)
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.
Ranked #2 on Person Re-Identification on DukeMTMC-VideoReID
no code implementations • 27 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.
Ranked #44 on 3D Human Pose Estimation on 3DPW
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.
no code implementations • 29 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.
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.
no code implementations • 12 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.
no code implementations • 10 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.
no code implementations • 10 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.
no code implementations • 21 Sep 2022 • Liangchen Song, Xuan Gong, Benjamin Planche, Meng Zheng, David Doermann, Junsong Yuan, Terrence Chen, Ziyan Wu
We propose to regularize the estimated motion to be predictable.
no code implementations • 16 Oct 2022 • Xuan Gong, Liangchen Song, Rishi Vedula, Abhishek Sharma, Meng Zheng, Benjamin Planche, Arun Innanje, Terrence Chen, Junsong Yuan, David Doermann, Ziyan Wu
We propose a privacy-preserving FL framework leveraging unlabeled public data for one-way offline knowledge distillation in this work.
no code implementations • 10 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.
no code implementations • 23 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.
no code implementations • 12 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.
no code implementations • 15 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.
no code implementations • 12 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.
no code implementations • 5 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.
no code implementations • 4 Mar 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.
no code implementations • 9 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.
no code implementations • 19 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.
no code implementations • 19 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.