no code implementations • 8 Sep 2023 • Chengwu Liu, Jianhao Shen, Huajian Xin, Zhengying Liu, Ye Yuan, Haiming Wang, Wei Ju, Chuanyang Zheng, Yichun Yin, Lin Li, Ming Zhang, Qun Liu
We present FIMO, an innovative dataset comprising formal mathematical problem statements sourced from the International Mathematical Olympiad (IMO) Shortlisted Problems.
no code implementations • 21 Aug 2023 • Zhuang Liu, Ye Yuan, Zhilong Ji, Jingfeng Bai, Xiang Bai
Then we design a semantic aware module (SAM), which projects the visual and classification feature into semantic space.
1 code implementation • 20 Jul 2023 • Wendi Li, Wei Wei, Xiaoye Qu, Xian-Ling Mao, Ye Yuan, Wenfeng Xie, Dangyang Chen
TREA constructs a multi-hierarchical scalable tree as the reasoning structure to clarify the causal relationships between mentioned entities, and fully utilizes historical conversations to generate more reasonable and suitable responses for recommended results.
no code implementations • 20 Jul 2023 • Rongqing Li, Jiaqi Yu, Changsheng Li, Wenhan Luo, Ye Yuan, Guoren Wang
There is a crucial limitation: these works assume the dataset used for training the target model to be known beforehand and leverage this dataset for model attribute attack.
no code implementations • 2 Jul 2023 • Kaituo Feng, Yikun Miao, Changsheng Li, Ye Yuan, Guoren Wang
Knowledge distillation (KD) has shown to be effective to boost the performance of graph neural networks (GNNs), where the typical objective is to distill knowledge from a deeper teacher GNN into a shallower student GNN.
1 code implementation • 10 Jun 2023 • Yonggan Fu, Ye Yuan, Souvik Kundu, Shang Wu, Shunyao Zhang, Yingyan Lin
Generalizable Neural Radiance Fields (GNeRF) are one of the most promising real-world solutions for novel view synthesis, thanks to their cross-scene generalization capability and thus the possibility of instant rendering on new scenes.
no code implementations • 25 May 2023 • Xiaomeng Yang, Zhi Qiao, Jin Wei, Yu Zhou, Ye Yuan, Zhilong Ji, Dongbao Yang, Weiping Wang
Scene Text Recognition (STR) is a challenging task due to variations in text style, shape, and background.
no code implementations • 24 Apr 2023 • Yonggan Fu, Ye Yuan, Shang Wu, Jiayi Yuan, Yingyan Lin
Transfer learning leverages feature representations of deep neural networks (DNNs) pretrained on source tasks with rich data to empower effective finetuning on downstream tasks.
no code implementations • CVPR 2023 • Davis Rempe, Zhengyi Luo, Xue Bin Peng, Ye Yuan, Kris Kitani, Karsten Kreis, Sanja Fidler, Or Litany
We introduce a method for generating realistic pedestrian trajectories and full-body animations that can be controlled to meet user-defined goals.
no code implementations • 23 Feb 2023 • Yang Zhang, Wenbing Huang, Zhewei Wei, Ye Yuan, Zhaohan Ding
Predicting the binding sites of the target proteins plays a fundamental role in drug discovery.
no code implementations • 15 Feb 2023 • Jun Liu, Ye Yuan
We prove that various stochastic gradient descent methods, including the stochastic gradient descent (SGD), stochastic heavy-ball (SHB), and stochastic Nesterov's accelerated gradient (SNAG) methods, almost surely avoid any strict saddle manifold.
no code implementations • ICCV 2023 • Jingbo Wang, Ye Yuan, Zhengyi Luo, Kevin Xie, Dahua Lin, Umar Iqbal, Sanja Fidler, Sameh Khamis
In this work, we propose a holistic framework for learning physically plausible human dynamics from real driving scenarios, narrowing the gap between real and simulated human behavior in safety-critical applications.
no code implementations • ICCV 2023 • Ye Yuan, Jiaming Song, Umar Iqbal, Arash Vahdat, Jan Kautz
Specifically, we propose a physics-based motion projection module that uses motion imitation in a physics simulator to project the denoised motion of a diffusion step to a physically-plausible motion.
no code implementations • 30 Nov 2022 • Ying Wang, Ye Yuan, Xin Luo
Based on this idea, a Node-collaboration-informed Graph Convolutional Network (NGCN) is proposed with three-fold ideas: a) Learning latent collaborative information from the interaction of node pairs via a node-collaboration module; b) Building the residual connection and weighted representation propagation to obtain high representation capacity; and c) Implementing the model optimization in an end-to-end fashion to achieve precise representation to the target UWG.
1 code implementation • 27 Nov 2022 • Leilei Cao, Yibo Guo, Ye Yuan, Qiangguo Jin
In this way, the spatial details can be better captured and the semantic features of target class in the query image can be focused.
Ranked #11 on
Few-Shot Semantic Segmentation
on COCO-20i (1-shot)
no code implementations • 30 Oct 2022 • Zhuang Liu, Zhichao Zhao, Ye Yuan, Zhi Qiao, Jinfeng Bai, Zhilong Ji
In this technical report, we briefly introduce the solution of our team ''summer'' for Atomospheric Turbulence Mitigation in UG$^2$+ Challenge in CVPR 2022.
1 code implementation • 25 Oct 2022 • Jianhao Shen, Chenguang Wang, Ye Yuan, Jiawei Han, Heng Ji, Koushik Sen, Ming Zhang, Dawn Song
For instance, we outperform the fully finetuning approaches on a KG completion benchmark by tuning only 1% of the parameters.
Ranked #5 on
Link Prediction
on UMLS
no code implementations • NeurIPS 2020 • Zixuan Xu, Banghuai Li, Ye Yuan, Anhong Dang
What's more, to fully exploit Beta Representation, a novel pipeline Beta R-CNN equipped with BetaHead and BetaMask is proposed, leading to high detection performance in occluded and crowded scenes.
Ranked #9 on
Object Detection
on CrowdHuman (full body)
no code implementations • 21 Oct 2022 • Zhenggang Tang, Balakumar Sundaralingam, Jonathan Tremblay, Bowen Wen, Ye Yuan, Stephen Tyree, Charles Loop, Alexander Schwing, Stan Birchfield
We present a system for collision-free control of a robot manipulator that uses only RGB views of the world.
no code implementations • 12 Sep 2022 • Sen Pei, Shixiong Xu, Ye Yuan, Jiashi Feng, Xiaohui Shen, Xiaojie Jin
To the best of our knowledge, this is the first time the incremental learning settings are introduced to video highlights detection, which in turn relieves the burden of training video inputs and promotes the scalability of conventional neural networks in proportion to both the size of the dataset and the quantity of domains.
no code implementations • 4 Aug 2022 • Jinli Li, Ye Yuan
High-dimensional and incomplete (HDI) data holds tremendous interactive information in various industrial applications.
no code implementations • 4 Aug 2022 • Jiufang Chen, Ye Yuan
Stochastic gradient descent (SGD) algorithm is an effective learning strategy to build a latent factor analysis (LFA) model on a high-dimensional and incomplete (HDI) matrix.
1 code implementation • 23 Jul 2022 • Bohan Li, Ye Yuan, Dingkang Liang, Xiao Liu, Zhilong Ji, Jinfeng Bai, Wenyu Liu, Xiang Bai
Recently, most handwritten mathematical expression recognition (HMER) methods adopt the encoder-decoder networks, which directly predict the markup sequences from formula images with the attention mechanism.
no code implementations • 22 Jul 2022 • Hanjie Li, Changsheng Li, Kaituo Feng, Ye Yuan, Guoren Wang, Hongyuan Zha
Recent years have witnessed the increasing attentions paid to dynamic graph neural networks for modelling such graph data, where almost all the existing approaches assume that when a new link is built, the embeddings of the neighbor nodes should be updated by learning the temporal dynamics to propagate new information.
1 code implementation • 28 Jun 2022 • Yanjiang Yu, Puyang Zhang, Kaihao Zhang, Wenhan Luo, Changsheng Li, Ye Yuan, Guoren Wang
To this end, we propose a Face Restoration Searching Network (FRSNet) to adaptively search the suitable feature extraction architecture within our specified search space, which can directly contribute to the restoration quality.
no code implementations • 27 Jun 2022 • Xiao Fan, Shuxin Zhuang, Zhemin Zhuang, Ye Yuan, Shunmin Qiu, Alex Noel Joseph Raj, Yibiao Rong
Deformable image registration can obtain dynamic information about images, which is of great significance in medical image analysis.
no code implementations • 18 Jun 2022 • Zhengyi Luo, Ye Yuan, Kris M. Kitani
Second, we use a design-and-control framework to optimize a humanoid's physical attributes to find body designs that can better imitate the pre-specified human motion sequence(s).
no code implementations • 18 Jun 2022 • Zhengyi Luo, Shun Iwase, Ye Yuan, Kris Kitani
Since 2D third-person observations are coupled with the camera pose, we propose to disentangle the camera pose and use a multi-step projection gradient defined in the global coordinate frame as the movement cue for our embodied agent.
Ranked #300 on
3D Human Pose Estimation
on Human3.6M
no code implementations • 14 Jun 2022 • Kaituo Feng, Changsheng Li, Ye Yuan, Guoren Wang
Knowledge distillation (KD) has demonstrated its effectiveness to boost the performance of graph neural networks (GNNs), where its goal is to distill knowledge from a deeper teacher GNN into a shallower student GNN.
1 code implementation • 3 Jun 2022 • Yanglan Ou, Ye Yuan, Xiaolei Huang, Stephen T. C. Wong, John Volpi, James Z. Wang, Kelvin Wong
We also propose a new mixture-of-experts (MoE) based decoder, which treats the feature maps from the encoder as experts and selects a suitable set of expert features to predict the label for each pixel.
no code implementations • 24 May 2022 • Jiachen Li, Ye Yuan, Hong-Bin Shen
Symbolic Regression (SR) is a type of regression analysis to automatically find the mathematical expression that best fits the data.
no code implementations • 5 May 2022 • Ye Yuan, Xin Luo
A high-dimensional and incomplete (HDI) matrix frequently appears in various big-data-related applications, which demonstrates the inherently non-negative interactions among numerous nodes.
no code implementations • 29 Apr 2022 • Zhexuan Zeng, Zuogong Yue, Alexandre Mauroy, Jorge Goncalves, Ye Yuan
The necessary and sufficient condition is proposed -- which is built from Koopman operator -- to the exact identification of the CT system from sampled data.
no code implementations • 28 Apr 2022 • Ye Yuan
Understanding and modeling human behavior is fundamental to almost any computer vision and robotics applications that involve humans.
no code implementations • 26 Apr 2022 • Shiye Wang, Changsheng Li, Yanming Li, Ye Yuan, Guoren Wang
Inheriting the advantages from information bottleneck, SIB-MSC can learn a latent space for each view to capture common information among the latent representations of different views by removing superfluous information from the view itself while retaining sufficient information for the latent representations of other views.
no code implementations • 5 Apr 2022 • Yuda Song, Ye Yuan, Wen Sun, Kris Kitani
Our theoretical analysis shows that our method is a no-regret algorithm and we provide the convergence rate in the agnostic setting.
no code implementations • 30 Mar 2022 • Ye Yuan, Guangxiao Yuan, Renfang Wang, Xin Luo
High-Dimensional and Incomplete (HDI) data are frequently found in various industrial applications with complex interactions among numerous nodes, which are commonly non-negative for representing the inherent non-negativity of node interactions.
2 code implementations • CVPR 2022 • Ye Yuan, Xiao Liu, Wondimu Dikubab, Hui Liu, Zhilong Ji, Zhongqin Wu, Xiang Bai
In this paper, we propose a simple and efficient method for HMER, which is the first to incorporate syntax information into an encoder-decoder network.
no code implementations • 18 Feb 2022 • Nianzu Yang, Huaijin Wu, Junchi Yan, Xiaoyong Pan, Ye Yuan, Le Song
From the application perspective, one of the emerging and attractive areas is aiding the design and discovery of molecules, especially in drug industry.
no code implementations • 9 Feb 2022 • Jun Liu, Ye Yuan
We further provide last-iterate almost sure convergence rates analysis for stochastic gradient methods on weakly convex smooth functions, in contrast with most existing results in the literature that only provide convergence in expectation for a weighted average of the iterates.
no code implementations • 8 Dec 2021 • Kai Zheng, Yuanjiang Wang, Ye Yuan
We delve into this problem and find that the lightweight model is prone to collapse in semantic space when simply performing instance-wise contrast.
1 code implementation • CVPR 2022 • Ye Yuan, Umar Iqbal, Pavlo Molchanov, Kris Kitani, Jan Kautz
Since the joint reconstruction of human motions and camera poses is underconstrained, we propose a global trajectory predictor that generates global human trajectories based on local body movements.
Ranked #1 on
Global 3D Human Pose Estimation
on EMDB
no code implementations • 8 Nov 2021 • Handong Ma, Changsheng Li, Xinchu Shi, Ye Yuan, Guoren Wang
To make the learnt graph structure more stable and effective, we take into account $k$-nearest neighbor graph as a priori, and learn a relation propagation graph structure.
no code implementations • 5 Nov 2021 • Lei Gan, Huabin Huang, Banghuai Li, Ye Yuan
In this paper, we present a novel add-on module, named Feature Balance Network (FBNet), to eliminate the feature camouflage in urban-scene segmentation.
no code implementations • 28 Oct 2021 • Yanming Li, Changsheng Li, Shiye Wang, Ye Yuan, Guoren Wang
In this paper, we propose a new deep subspace clustering framework, motivated by the energy-based models.
1 code implementation • 26 Oct 2021 • Zhenyu Lu, Yurong Cheng, Mingjun Zhong, George Stoian, Ye Yuan, Guoren Wang
A typical approach is to formulate causal inference as a supervised learning problem and so counterfactual could be predicted.
1 code implementation • ICLR 2022 • Ye Yuan, Yuda Song, Zhengyi Luo, Wen Sun, Kris Kitani
Specifically, we learn a conditional policy that, in an episode, first applies a sequence of transform actions to modify an agent's skeletal structure and joint attributes, and then applies control actions under the new design.
1 code implementation • 22 Sep 2021 • Zeyuan Yin, Ye Yuan, Panfeng Guo, Pan Zhou
Edge devices in federated learning usually have much more limited computation and communication resources compared to servers in a data center.
no code implementations • 20 Sep 2021 • Tianfu He, Guochun Chen, Chuishi Meng, Huajun He, Zheyi Pan, Yexin Li, Sijie Ruan, Huimin Ren, Ye Yuan, Ruiyuan Li, Junbo Zhang, Jie Bao, Hui He, Yu Zheng
People often refer to a place of interest (POI) by an alias.
1 code implementation • 30 Aug 2021 • Ye Yuan, Wuyang Chen, Zhaowen Wang, Matthew Fisher, Zhifei Zhang, Zhangyang Wang, Hailin Jin
The novel graph constructor maps a glyph's latent code to its graph representation that matches expert knowledge, which is trained to help the translation task.
1 code implementation • ICCV 2021 • Weixin Feng, Yuanjiang Wang, Lihua Ma, Ye Yuan, Chi Zhang
The instance discrimination paradigm has become dominant in unsupervised learning.
1 code implementation • 23 Jul 2021 • Zhenyu Wu, Zhaowen Wang, Ye Yuan, Jianming Zhang, Zhangyang Wang, Hailin Jin
Existing diversity tests of samples from GANs are usually conducted qualitatively on a small scale, and/or depends on the access to original training data as well as the trained model parameters.
1 code implementation • 15 Jul 2021 • Ye Yuan, Jun Liu, Dou Jin, Zuogong Yue, Ruijuan Chen, Maolin Wang, Chuan Sun, Lei Xu, Feng Hua, Xin He, Xinlei Yi, Tao Yang, Hai-Tao Zhang, Shaochun Sui, Han Ding
Although there has been a joint effort in tackling such a critical issue by proposing privacy-preserving machine learning frameworks, such as federated learning, most state-of-the-art frameworks are built still in a centralized way, in which a central client is needed for collecting and distributing model information (instead of data itself) from every other client, leading to high communication pressure and high vulnerability when there exists a failure at or attack on the central client.
1 code implementation • NeurIPS 2021 • Zhengyi Luo, Ryo Hachiuma, Ye Yuan, Kris Kitani
By comparing the pose instructed by the kinematic model against the pose generated by the dynamics model, we can use their misalignment to further improve the kinematic model.
Egocentric Pose Estimation
Human-Object Interaction Detection
+1
1 code implementation • 28 Apr 2021 • Yanglan Ou, Ye Yuan, Xiaolei Huang, Kelvin Wong, John Volpi, James Z. Wang, Stephen T. C. Wong
Thus, it is not ideal to apply most existing segmentation methods as they are designed for either 2D or 3D images.
no code implementations • CVPR 2021 • Ye Yuan, Shih-En Wei, Tomas Simon, Kris Kitani, Jason Saragih
Based on this refined kinematic pose, the policy learns to compute dynamics-based control (e. g., joint torques) of the character to advance the current-frame pose estimate to the pose estimate of the next frame.
Ranked #225 on
3D Human Pose Estimation
on Human3.6M
2 code implementations • ICCV 2021 • Ye Yuan, Xinshuo Weng, Yanglan Ou, Kris Kitani
Instead, we would prefer a method that allows an agent's state at one time to directly affect another agent's state at a future time.
Ranked #9 on
Trajectory Prediction
on ETH/UCY
3 code implementations • CVPR 2021 • Bo Sun, Banghuai Li, Shengcai Cai, Ye Yuan, Chi Zhang
We present Few-Shot object detection via Contrastive proposals Encoding (FSCE), a simple yet effective approach to learning contrastive-aware object proposal encodings that facilitate the classification of detected objects.
Ranked #11 on
Few-Shot Object Detection
on MS-COCO (30-shot)
no code implementations • 25 Nov 2020 • Ye Yuan, Xueying Ding, Ziv Bar-Joseph
Causal inference from observation data is a core problem in many scientific fields.
no code implementations • 10 Nov 2020 • Zhengyi Luo, Ryo Hachiuma, Ye Yuan, Shun Iwase, Kris M. Kitani
We propose a method for incorporating object interaction and human body dynamics into the task of 3D ego-pose estimation using a head-mounted camera.
no code implementations • 9 Nov 2020 • Alex Carderas, Ye Yuan, Itamar Livnat, Ryan Yanagihara, Rosita Saul, Gabrielle Montes De Oca, Kai Zheng, Andrew W. Browne
Objective: To develop software utilizing optical character recognition toward the automatic extraction of data from bar charts for meta-analysis.
Optical Character Recognition
Optical Character Recognition (OCR)
+1
1 code implementation • NeurIPS 2020 • Ming Chen, Zhewei Wei, Bolin Ding, Yaliang Li, Ye Yuan, Xiaoyong Du, Ji-Rong Wen
Most notably, GBP can deliver superior performance on a graph with over 60 million nodes and 1. 8 billion edges in less than half an hour on a single machine.
no code implementations • 6 Oct 2020 • Yuli Zheng, Zhenyu Wu, Ye Yuan, Tianlong Chen, Zhangyang Wang
While machine learning is increasingly used in this field, the resulting large-scale collection of user private information has reinvigorated the privacy debate, considering dozens of data breach incidents every year caused by unauthorized hackers, and (potentially even more) information misuse/abuse by authorized parties.
no code implementations • 25 Aug 2020 • Xinshuo Weng, Ye Yuan, Kris Kitani
To evaluate this hypothesis, we propose a unified solution for 3D MOT and trajectory forecasting which also incorporates two additional novel computational units.
no code implementations • 16 Aug 2020 • Xinyu Gong, Wuyang Chen, Yifan Jiang, Ye Yuan, Xian-Ming Liu, Qian Zhang, Yuan Li, Zhangyang Wang
Such simplification limits the fusion of information at different scales and fails to maintain high-resolution representations.
no code implementations • ECCV 2020 • Mariko Isogawa, Dorian Chan, Ye Yuan, Kris Kitani, Matthew O'Toole
Non-line-of-sight (NLOS) imaging techniques use light that diffusely reflects off of visible surfaces (e. g., walls) to see around corners.
no code implementations • 28 Jul 2020 • Changsheng Li, Handong Ma, Zhao Kang, Ye Yuan, Xiao-Yu Zhang, Guoren Wang
Unsupervised active learning has attracted increasing attention in recent years, where its goal is to select representative samples in an unsupervised setting for human annotating.
1 code implementation • 7 Jul 2020 • Zixuan Xu, Banghuai Li, Miao Geng, Ye Yuan
Based on the prediction of each anchor template, we propose to aggregate the results, which can reduce the landmark uncertainty due to the large poses.
Ranked #1 on
Facial Landmark Detection
on AFLW-Front
1 code implementation • ICML 2020 • Xuxi Chen, Wuyang Chen, Tianlong Chen, Ye Yuan, Chen Gong, Kewei Chen, Zhangyang Wang
Many real-world applications have to tackle the Positive-Unlabeled (PU) learning problem, i. e., learning binary classifiers from a large amount of unlabeled data and a few labeled positive examples.
1 code implementation • NeurIPS 2020 • Ye Yuan, Kris Kitani
Our approach is the first humanoid control method that successfully learns from a large-scale human motion dataset (Human3. 6M) and generates diverse long-term motions.
1 code implementation • ICDE 2020 • Chi Harold Liu, Yinuo Zhao, Zipeng Dai, Ye Yuan, Guoren Wang, Dapeng Wu, Kin K. Leung
Spatial crowdsourcing (SC) utilizes the potential of a crowd to accomplish certain location based tasks.
no code implementations • 1 Apr 2020 • Yanglan Ou, Yuan Xue, Ye Yuan, Tao Xu, Vincent Pisztora, Jia Li, Xiaolei Huang
In this paper, we propose a novel and more flexible GCN model with a feature encoder that adaptively updates the adjacency matrix during learning and demonstrate that this model design leads to improved performance.
1 code implementation • CVPR 2020 • Mariko Isogawa, Ye Yuan, Matthew O'Toole, Kris Kitani
We bring together a diverse set of technologies from NLOS imaging, human pose estimation and deep reinforcement learning to construct an end-to-end data processing pipeline that converts a raw stream of photon measurements into a full 3D human pose sequence estimate.
1 code implementation • 21 Mar 2020 • Changming Zhao, Dongrui Wu, Jian Huang, Ye Yuan, Hai-Tao Zhang, Ruimin Peng, Zhenhua Shi
Bootstrap aggregating (Bagging) and boosting are two popular ensemble learning approaches, which combine multiple base learners to generate a composite model for more accurate and more reliable performance.
1 code implementation • ECCV 2020 • Ye Yuan, Kris Kitani
To obtain samples from a pretrained generative model, most existing generative human motion prediction methods draw a set of independent Gaussian latent codes and convert them to motion samples.
Ranked #1 on
Human Pose Forecasting
on AMASS
(APD metric)
no code implementations • 17 Mar 2020 • Xinshuo Weng, Ye Yuan, Kris Kitani
We evaluate on KITTI and nuScenes datasets showing that our method with socially-aware feature learning and diversity sampling achieves new state-of-the-art performance on 3D MOT and trajectory prediction.
no code implementations • 3 Mar 2020 • Zepeng Huo, Arash Pakbin, Xiaohan Chen, Nathan Hurley, Ye Yuan, Xiaoning Qian, Zhangyang Wang, Shuai Huang, Bobak Mortazavi
Activity recognition in wearable computing faces two key challenges: i) activity characteristics may be context-dependent and change under different contexts or situations; ii) unknown contexts and activities may occur from time to time, requiring flexibility and adaptability of the algorithm.
1 code implementation • CVPR 2020 • Xi Chen, Zuoxin Li, Ye Yuan, Gang Yu, Jianxin Shen, Donglian Qi
For higher efficiency, SAT takes advantage of the inter-frame consistency and deals with each target object as a tracklet.
Semantic Segmentation
Semi-Supervised Video Object Segmentation
+1
1 code implementation • 17 Dec 2019 • Ye Yuan, Wuyang Chen, Yang Yang, Zhangyang Wang
This work addresses the above two shortcomings of triplet loss, extending its effectiveness to large-scale ReID datasets with potentially noisy labels.
no code implementations • 13 Dec 2019 • Ye Yuan, Jian Guan, Pengming Feng, Yanxia Wu
In this letter, we aim to address a synthetic aperture radar (SAR) despeckling problem with the necessity of neither clean (speckle-free) SAR images nor independent speckled image pairs from the same scene, and a practical solution for SAR despeckling (PSD) is proposed.
1 code implementation • 26 Nov 2019 • Ye Yuan, Wuyang Chen, Tianlong Chen, Yang Yang, Zhou Ren, Zhangyang Wang, Gang Hua
Many real-world applications, such as city-scale traffic monitoring and control, requires large-scale re-identification.
4 code implementations • 14 Nov 2019 • Yinda Xu, Zeyu Wang, Zuoxin Li, Ye Yuan, Gang Yu
Following these guidelines, we design our Fully Convolutional Siamese tracker++ (SiamFC++) by introducing both classification and target state estimation branch(G1), classification score without ambiguity(G2), tracking without prior knowledge(G3), and estimation quality score(G4).
Ranked #2 on
Visual Object Tracking
on VOT2017/18
(using extra training data)
no code implementations • 25 Sep 2019 • Jun Liu, Beitong Zhou, Weigao Sun, Ruijuan Chen, Claire J. Tomlin, Ye Yuan
In this paper, we propose a novel technique for improving the stochastic gradient descent (SGD) method to train deep networks, which we term \emph{PowerSGD}.
no code implementations • 25 Sep 2019 • Zhenyu Wu, Ye Yuan, Zhaowen Wang, Jianming Zhang, Zhangyang Wang, Hailin Jin
Generative adversarial networks (GANs) nowadays are capable of producing im-ages of incredible realism.
1 code implementation • 15 Sep 2019 • Ye Yuan, Junlin Li, Liang Li, Frank Jiang, Xiuchuan Tang, Fumin Zhang, Sheng Liu, Jorge Goncalves, Henning U. Voss, Xiuting Li, Jürgen Kurths, Han Ding
The study presents a general framework for discovering underlying Partial Differential Equations (PDEs) using measured spatiotemporal data.
5 code implementations • ICCV 2019 • Tianlong Chen, Shaojin Ding, Jingyi Xie, Ye Yuan, Wuyang Chen, Yang Yang, Zhou Ren, Zhangyang Wang
Attention mechanism has been shown to be effective for person re-identification (Re-ID).
Ranked #16 on
Person Re-Identification
on Market-1501-C
no code implementations • ICLR 2020 • Ye Yuan, Kris Kitani
To learn the parameters of the DSF, the diversity of the trajectory samples is evaluated by a diversity loss based on a determinantal point process (DPP).
Ranked #5 on
Human Pose Forecasting
on HumanEva-I
1 code implementation • ICCV 2019 • Ye Yuan, Kris Kitani
We propose the use of a proportional-derivative (PD) control based policy learned via reinforcement learning (RL) to estimate and forecast 3D human pose from egocentric videos.
no code implementations • CVPR 2020 • Jiaqi Guan, Ye Yuan, Kris M. Kitani, Nicholas Rhinehart
Automatically reasoning about future human behaviors is a difficult problem but has significant practical applications to assistive systems.
no code implementations • 9 Apr 2019 • Ye Yuan, Wenhan Yang, Wenqi Ren, Jiaying Liu, Walter J. Scheirer, Zhangyang Wang
The UG$^{2+}$ challenge in IEEE CVPR 2019 aims to evoke a comprehensive discussion and exploration about how low-level vision techniques can benefit the high-level automatic visual recognition in various scenarios.
no code implementations • 1 Apr 2019 • Wenqian Jiang, Cheng Cheng, Beitong Zhou, Guijun Ma, Ye Yuan
This paper proposes a novel fault diagnosis approach based on generative adversarial networks (GAN) for imbalanced industrial time series where normal samples are much larger than failure cases.
1 code implementation • 26 Mar 2019 • Dongrui Wu, Ye Yuan, Yihua Tan
Our final algorithm, mini-batch gradient descent with regularization, DropRule and AdaBound (MBGD-RDA), can achieve fast convergence in training TSK fuzzy systems, and also superior generalization performance in testing.
no code implementations • 2 Mar 2019 • Cheng Cheng, Beitong Zhou, Guijun Ma, Dongrui Wu, Ye Yuan
However, for diverse working conditions in the industry, deep learning suffers two difficulties: one is that the well-defined (source domain) and new (target domain) datasets are with different feature distributions; another one is the fact that insufficient or no labelled data in target domain significantly reduce the accuracy of fault diagnosis.
no code implementations • 19 Feb 2019 • Chen Change Loy, Dahua Lin, Wanli Ouyang, Yuanjun Xiong, Shuo Yang, Qingqiu Huang, Dongzhan Zhou, Wei Xia, Quanquan Li, Ping Luo, Junjie Yan, Jian-Feng Wang, Zuoxin Li, Ye Yuan, Boxun Li, Shuai Shao, Gang Yu, Fangyun Wei, Xiang Ming, Dong Chen, Shifeng Zhang, Cheng Chi, Zhen Lei, Stan Z. Li, Hongkai Zhang, Bingpeng Ma, Hong Chang, Shiguang Shan, Xilin Chen, Wu Liu, Boyan Zhou, Huaxiong Li, Peng Cheng, Tao Mei, Artem Kukharenko, Artem Vasenin, Nikolay Sergievskiy, Hua Yang, Liangqi Li, Qiling Xu, Yuan Hong, Lin Chen, Mingjun Sun, Yirong Mao, Shiying Luo, Yongjun Li, Ruiping Wang, Qiaokang Xie, Ziyang Wu, Lei Lu, Yiheng Liu, Wengang Zhou
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
no code implementations • 28 Jan 2019 • Rosaura G. VidalMata, Sreya Banerjee, Brandon RichardWebster, Michael Albright, Pedro Davalos, Scott McCloskey, Ben Miller, Asong Tambo, Sushobhan Ghosh, Sudarshan Nagesh, Ye Yuan, Yueyu Hu, Junru Wu, Wenhan Yang, Xiaoshuai Zhang, Jiaying Liu, Zhangyang Wang, Hwann-Tzong Chen, Tzu-Wei Huang, Wen-Chi Chin, Yi-Chun Li, Mahmoud Lababidi, Charles Otto, Walter J. Scheirer
From the observed results, it is evident that we are in the early days of building a bridge between computational photography and visual recognition, leaving many opportunities for innovation in this area.
no code implementations • 17 Dec 2018 • Ye Yuan, Guijun Ma, Cheng Cheng, Beitong Zhou, Huan Zhao, Hai-Tao Zhang, Han Ding
A central challenge in manufacturing sector lies in the requirement of a general framework to ensure satisfied diagnosis and monitoring performances in different manufacturing applications.
1 code implementation • 8 Dec 2018 • Cheng Cheng, Guijun Ma, Yong Zhang, Mingyang Sun, Fei Teng, Han Ding, Ye Yuan
In industrial applications, nearly half the failures of motors are caused by the degradation of rolling element bearings (REBs).
1 code implementation • 1 Oct 2018 • Ye Yuan, Xiuchuan Tang, Wei Pan, Xiuting Li, Wei Zhou, Hai-Tao Zhang, Han Ding, Jorge Goncalves
Cyber-physical systems (CPSs) embed software into the physical world.
no code implementations • ECCV 2018 • Ye Yuan, Kris Kitani
Motivated by this, we propose a novel control-based approach to model human motion with physics simulation and use imitation learning to learn a video-conditioned control policy for ego-pose estimation.
1 code implementation • Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2018 • Yaqing Wang, Fenglong Ma, Zhiwei Jin, Ye Yuan, Guangxu Xun, Kishlay Jha, Lu Su, Jing Gao
One of the unique challenges for fake news detection on social media is how to identify fake news on newly emerged events.
no code implementations • 18 Apr 2018 • Jianfeng Wang, Ye Yuan, Boxun Li, Gang Yu, Sun Jian
A new dataset called 4K-Face is also introduced to evaluate the performance of face detection with extreme large scale variations.
1 code implementation • 20 Nov 2017 • Jianfeng Wang, Ye Yuan, Gang Yu
The performance of face detection has been largely improved with the development of convolutional neural network.
Ranked #1 on
Occluded Face Detection
on MAFA
1 code implementation • 5 Nov 2017 • Omid Ardakanian, Vincent W. S. Wong, Roel Dobbe, Steven H. Low, Alexandra von Meier, Claire Tomlin, Ye Yuan
Large-scale integration of distributed energy resources into residential distribution feeders necessitates careful control of their operation through power flow analysis.
no code implementations • 5 Jul 2017 • Po-Yao Huang, Ye Yuan, Zhenzhong Lan, Lu Jiang, Alexander G. Hauptmann
We report on CMU Informedia Lab's system used in Google's YouTube 8 Million Video Understanding Challenge.
5 code implementations • 27 Feb 2017 • Panqu Wang, Pengfei Chen, Ye Yuan, Ding Liu, Zehua Huang, Xiaodi Hou, Garrison Cottrell
This framework 1) effectively enlarges the receptive fields (RF) of the network to aggregate global information; 2) alleviates what we call the "gridding issue" caused by the standard dilated convolution operation.
Ranked #20 on
Semantic Segmentation
on PASCAL VOC 2012 test
no code implementations • 8 Dec 2016 • Xiaoming Deng, Ye Yuan, Yinda Zhang, Ping Tan, Liang Chang, Shuo Yang, Hongan Wang
Hand detection is essential for many hand related tasks, e. g. parsing hand pose, understanding gesture, which are extremely useful for robotics and human-computer interaction.
1 code implementation • 6 Nov 2016 • Zhilin Yang, Bhuwan Dhingra, Ye Yuan, Junjie Hu, William W. Cohen, Ruslan Salakhutdinov
Previous work combines word-level and character-level representations using concatenation or scalar weighting, which is suboptimal for high-level tasks like reading comprehension.
Ranked #50 on
Question Answering
on SQuAD1.1 dev
no code implementations • 21 Oct 2016 • Ye Yuan, Steven Low, Omid Ardakanian, Claire Tomlin
We show that the admittance matrix can be uniquely identified from a sequence of measurements corresponding to different steady states when every node in the system is equipped with a measurement device, and a Kron-reduced admittance matrix can be determined even if some nodes in the system are not monitored (hidden nodes).
no code implementations • NeurIPS 2016 • Zhilin Yang, Ye Yuan, Yuexin Wu, Ruslan Salakhutdinov, William W. Cohen
We propose a novel extension of the encoder-decoder framework, called a review network.
no code implementations • 24 Mar 2016 • Ye Yuan, Mu Li, Jun Liu, Claire J. Tomlin
We propose a new method to accelerate the convergence of optimization algorithms.