Search Results for author: Li Cheng

Found 54 papers, 23 papers with code

Automated Generation of Accurate & Fluent Medical X-ray Reports

1 code implementation EMNLP 2021 Hoang Nguyen, Dong Nie, Taivanbat Badamdorj, Yujie Liu, Yingying Zhu, Jason Truong, Li Cheng

Our paper aims to automate the generation of medical reports from chest X-ray image inputs, a critical yet time-consuming task for radiologists.

Medical Report Generation

Generative Human Motion Stylization in Latent Space

no code implementations24 Jan 2024 Chuan Guo, Yuxuan Mu, Xinxin Zuo, Peng Dai, Youliang Yan, Juwei Lu, Li Cheng

Building upon this, we present a novel generative model that produces diverse stylization results of a single motion (latent) code.

MotionScript: Natural Language Descriptions for Expressive 3D Human Motions

no code implementations19 Dec 2023 Payam Jome Yazdian, Eric Liu, Li Cheng, Angelica Lim

This paper proposes MotionScript, a motion-to-text conversion algorithm and natural language representation for human body motions.

MoMask: Generative Masked Modeling of 3D Human Motions

1 code implementation29 Nov 2023 Chuan Guo, Yuxuan Mu, Muhammad Gohar Javed, Sen Wang, Li Cheng

For the base-layer motion tokens, a Masked Transformer is designated to predict randomly masked motion tokens conditioned on text input at training stage.

Human motion prediction Motion Forecasting +2

Two-stage Synthetic Supervising and Multi-view Consistency Self-supervising based Animal 3D Reconstruction by Single Image

1 code implementation22 Nov 2023 Zijian Kuang, Lihang Ying, Shi Jin, Li Cheng

To address this challenge, we propose the combination of two-stage supervised and self-supervised training to address the challenge of obtaining animal cooperation for 3D scanning.

3D Reconstruction Single-View 3D Reconstruction

Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications

1 code implementation12 Apr 2023 Wei Ji, Jingjing Li, Qi Bi, TingWei Liu, Wenbo Li, Li Cheng

Recently, Meta AI Research approaches a general, promptable Segment Anything Model (SAM) pre-trained on an unprecedentedly large segmentation dataset (SA-1B).

Image Segmentation Segmentation +1

Event-based Human Pose Tracking by Spiking Spatiotemporal Transformer

1 code implementation16 Mar 2023 Shihao Zou, Yuxuan Mu, Xinxin Zuo, Sen Wang, Li Cheng

Motivated by the above mentioned issues, we present in this paper a dedicated end-to-end sparse deep learning approach for event-based pose tracking: 1) to our knowledge this is the first time that 3D human pose tracking is obtained from events only, thus eliminating the need of accessing to any frame-based images as part of input; 2) our approach is based entirely upon the framework of Spiking Neural Networks (SNNs), which consists of Spike-Element-Wise (SEW) ResNet and a novel Spiking Spatiotemporal Transformer; 3) a large-scale synthetic dataset is constructed that features a broad and diverse set of annotated 3D human motions, as well as longer hours of event stream data, named SynEventHPD.

3D Human Pose Estimation 3D Human Pose Tracking

Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippet

1 code implementation9 Jul 2022 Shihao Zou, Yuanlu Xu, Chao Li, Lingni Ma, Li Cheng, Minh Vo

In this paper, we propose Snipper, a unified framework to perform multi-person 3D pose estimation, tracking, and motion forecasting simultaneously in a single stage.

3D Pose Estimation Motion Forecasting +1

Dual Learning Music Composition and Dance Choreography

no code implementations28 Jan 2022 Shuang Wu, Zhenguang Li, Shijian Lu, Li Cheng

Music and dance have always co-existed as pillars of human activities, contributing immensely to the cultural, social, and entertainment functions in virtually all societies.

Exploring Denoised Cross-Video Contrast for Weakly-Supervised Temporal Action Localization

no code implementations CVPR 2022 Jingjing Li, Tianyu Yang, Wei Ji, Jue Wang, Li Cheng

Inspired by recent success in unsupervised contrastive representation learning, we propose a novel denoised cross-video contrastive algorithm, aiming to enhance the feature discrimination ability of video snippets for accurate temporal action localization in the weakly-supervised setting.

Contrastive Learning Denoising +4

Contrastive Learning for Unsupervised Video Highlight Detection

no code implementations CVPR 2022 Taivanbat Badamdorj, Mrigank Rochan, Yang Wang, Li Cheng

Our framework encodes a video into a vector representation by learning to pick video clips that help to distinguish it from other videos via a contrastive objective using dropout noise.

Contrastive Learning Highlight Detection

Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction

1 code implementation30 Dec 2021 Zhenguang Liu, Shuang Wu, Shuyuan Jin, Shouling Ji, Qi Liu, Shijian Lu, Li Cheng

One aspect that has been obviated so far, is the fact that how we represent the skeletal pose has a critical impact on the prediction results.

motion prediction

Music-to-Dance Generation with Optimal Transport

no code implementations3 Dec 2021 Shuang Wu, Shijian Lu, Li Cheng

We introduce an optimal transport distance for evaluating the authenticity of the generated dance distribution and a Gromov-Wasserstein distance to measure the correspondence between the dance distribution and the input music.

Retrieval Unity

3D Pose Estimation and Future Motion Prediction from 2D Images

no code implementations26 Nov 2021 Ji Yang, Youdong Ma, Xinxin Zuo, Sen Wang, Minglun Gong, Li Cheng

This paper considers to jointly tackle the highly correlated tasks of estimating 3D human body poses and predicting future 3D motions from RGB image sequences.

3D Pose Estimation motion prediction

The RETA Benchmark for Retinal Vascular Tree Analysis

no code implementations23 Nov 2021 Xingzheng Lyu, Li Cheng, Sanyuan Zhang

Topological and geometrical analysis of retinal blood vessel is a cost-effective way for early detection of many common diseases.


Action2video: Generating Videos of Human 3D Actions

no code implementations12 Nov 2021 Chuan Guo, Xinxin Zuo, Sen Wang, Xinshuang Liu, Shihao Zou, Minglun Gong, Li Cheng

Action2motion stochastically generates plausible 3D pose sequences of a prescribed action category, which are processed and rendered by motion2video to form 2D videos.

Automated Generation of Accurate \& Fluent Medical X-ray Reports

1 code implementation27 Aug 2021 Hoang T. N. Nguyen, Dong Nie, Taivanbat Badamdorj, Yujie Liu, Yingying Zhu, Jason Truong, Li Cheng

Our paper focuses on automating the generation of medical reports from chest X-ray image inputs, a critical yet time-consuming task for radiologists.

Human Pose and Shape Estimation from Single Polarization Images

1 code implementation15 Aug 2021 Shihao Zou, Xinxin Zuo, Sen Wang, Yiming Qian, Chuan Guo, Li Cheng

This paper focuses on a new problem of estimating human pose and shape from single polarization images.

Surface Normal Estimation

EventHPE: Event-based 3D Human Pose and Shape Estimation

1 code implementation ICCV 2021 Shihao Zou, Chuan Guo, Xinxin Zuo, Sen Wang, Pengyu Wang, Xiaoqin Hu, Shoushun Chen, Minglun Gong, Li Cheng

Event camera is an emerging imaging sensor for capturing dynamics of moving objects as events, which motivates our work in estimating 3D human pose and shape from the event signals.

3D human pose and shape estimation Optical Flow Estimation

Self-supervised 3D Human Mesh Recovery from Noisy Point Clouds

1 code implementation15 Jul 2021 Xinxin Zuo, Sen Wang, Qiang Sun, Minglun Gong, Li Cheng

However, Chamfer distance is quite sensitive to noise and outliers, thus could be unreliable to assign correspondences.

Human Mesh Recovery

CHASE: Robust Visual Tracking via Cell-Level Differentiable Neural Architecture Search

1 code implementation2 Jul 2021 Seyed Mojtaba Marvasti-Zadeh, Javad Khaghani, Li Cheng, Hossein Ghanei-Yakhdan, Shohreh Kasaei

A strong visual object tracker nowadays relies on its well-crafted modules, which typically consist of manually-designed network architectures to deliver high-quality tracking results.

Neural Architecture Search Semantic Segmentation +1

Calibrated RGB-D Salient Object Detection

1 code implementation CVPR 2021 Wei Ji, Jingjing Li, Shuang Yu, Miao Zhang, Yongri Piao, Shunyu Yao, Qi Bi, Kai Ma, Yefeng Zheng, Huchuan Lu, Li Cheng

Complex backgrounds and similar appearances between objects and their surroundings are generally recognized as challenging scenarios in Salient Object Detection (SOD).

Object object-detection +3

Reconstruct high-resolution multi-focal plane images from a single 2D wide field image

no code implementations21 Sep 2020 Jiabo Ma, Sibo Liu, Shenghua Cheng, Xiuli Liu, Li Cheng, Shaoqun Zeng

High-resolution 3D medical images are important for analysis and diagnosis, but axial scanning to acquire them is very time-consuming.

Generative Adversarial Network Super-Resolution

Action2Motion: Conditioned Generation of 3D Human Motions

1 code implementation30 Jul 2020 Chuan Guo, Xinxin Zuo, Sen Wang, Shihao Zou, Qingyao Sun, Annan Deng, Minglun Gong, Li Cheng

Action recognition is a relatively established task, where givenan input sequence of human motion, the goal is to predict its ac-tion category.

Action Generation

3D Human Shape Reconstruction from a Polarization Image

no code implementations ECCV 2020 Shihao Zou, Xinxin Zuo, Yiming Qian, Sen Wang, Chi Xu, Minglun Gong, Li Cheng

Inspired by the recent advances in human shape estimation from single color images, in this paper, we attempt at estimating human body shapes by leveraging the geometric cues from single polarization images.

SparseFusion: Dynamic Human Avatar Modeling from Sparse RGBD Images

no code implementations5 Jun 2020 Xinxin Zuo, Sen Wang, Jiangbin Zheng, Weiwei Yu, Minglun Gong, Ruigang Yang, Li Cheng

First, based on a generative human template, for every two frames having sufficient overlap, an initial pairwise alignment is performed; It is followed by a global non-rigid registration procedure, in which partial results from RGBD frames are collected into a unified 3D shape, under the guidance of correspondences from the pairwise alignment; Finally, the texture map of the reconstructed human model is optimized to deliver a clear and spatially consistent texture.

COMET: Context-Aware IoU-Guided Network for Small Object Tracking

no code implementations4 Jun 2020 Seyed Mojtaba Marvasti-Zadeh, Javad Khaghani, Hossein Ghanei-Yakhdan, Shohreh Kasaei, Li Cheng

To address this problem, we introduce a context-aware IoU-guided tracker (COMET) that exploits a multitask two-stream network and an offline reference proposal generation strategy.

Object Tracking

Polarization Human Shape and Pose Dataset

no code implementations30 Apr 2020 Shihao Zou, Xinxin Zuo, Yiming Qian, Sen Wang, Chuan Guo, Chi Xu, Minglun Gong, Li Cheng

Polarization images are known to be able to capture polarized reflected lights that preserve rich geometric cues of an object, which has motivated its recent applications in reconstructing detailed surface normal of the objects of interest.

Stabilizing Training of Generative Adversarial Nets via Langevin Stein Variational Gradient Descent

no code implementations22 Apr 2020 Dong Wang, Xiaoqian Qin, Fengyi Song, Li Cheng

Generative adversarial networks (GANs), famous for the capability of learning complex underlying data distribution, are however known to be tricky in the training process, which would probably result in mode collapse or performance deterioration.

Variational Inference

Outlier Detection Ensemble with Embedded Feature Selection

no code implementations15 Jan 2020 Li Cheng, Yijie Wang, Xinwang Liu, Bin Li

Existing methods usually perform feature selection and outlier scoring separately, which would select feature subsets that may not optimally serve for outlier detection, leading to unsatisfying performance.

feature selection Outlier Detection

Deep Learning for Visual Tracking: A Comprehensive Survey

1 code implementation2 Dec 2019 Seyed Mojtaba Marvasti-Zadeh, Li Cheng, Hossein Ghanei-Yakhdan, Shohreh Kasaei

Second, popular visual tracking benchmarks and their respective properties are compared, and their evaluation metrics are summarized.

Visual Tracking

WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis

1 code implementation12 Nov 2019 Tianfu Li, Zhibin Zhao, Chuang Sun, Li Cheng, Xuefeng Chen, Ruqiang Yan, Robert X. Gao

In this paper, a novel wavelet driven deep neural network termed as WaveletKernelNet (WKN) is presented, where a continuous wavelet convolutional (CWConv) layer is designed to replace the first convolutional layer of the standard CNN.

Management Translation

Estimating Position Bias without Intrusive Interventions

no code implementations12 Dec 2018 Agarwal Aman, Zaitsev Ivan, Wang Xuanhui, Li Cheng, Najork Marc, Joachims Thorsten

Presentation bias is one of the key challenges when learning from implicit feedback in search engines, as it confounds the relevance signal.

counterfactual Learning-To-Rank +1

Offline Comparison of Ranking Functions using Randomized Data

no code implementations11 Oct 2018 Agarwal Aman, Wang Xuanhui, Li Cheng, Bendersky Michael, Najork Marc

In this paper, we study how to improve the data efficiency of IPS approaches in the offline comparison setting.

Off-policy evaluation

Too Far to See? Not Really! --- Pedestrian Detection with Scale-aware Localization Policy

no code implementations1 Sep 2017 Xiaowei Zhang, Li Cheng, Bo Li, Hai-Miao Hu

A major bottleneck of pedestrian detection lies on the sharp performance deterioration in the presence of small-size pedestrians that are relatively far from the camera.

Pedestrian Detection Region Proposal

Synthesizing Filamentary Structured Images with GANs

1 code implementation7 Jun 2017 He Zhao, Huiqi Li, Li Cheng

This paper aims at synthesizing filamentary structured images such as retinal fundus images and neuronal images, as follows: Given a ground-truth, to generate multiple realistic looking phantoms.

Style Transfer

Multivariate Regression with Gross Errors on Manifold-valued Data

no code implementations26 Mar 2017 Xiaowei Zhang, Xudong Shi, Yu Sun, Li Cheng

Our model first takes a correction step on the grossly corrupted responses via geodesic curves on the manifold, and then performs multivariate linear regression on the corrected data.


Multivariate Regression with Grossly Corrupted Observations: A Robust Approach and its Applications

no code implementations11 Jan 2017 Xiaowei Zhang, Chi Xu, Yu Zhang, Tingshao Zhu, Li Cheng

The implementation of our approach and comparison methods as well as the involved datasets are made publicly available in support of the open-source and reproducible research initiatives.

Hand Pose Estimation regression

An Interval-Based Bayesian Generative Model for Human Complex Activity Recognition

no code implementations4 Jan 2017 Li Liu, Yongzhong Yang, Lakshmi Narasimhan Govindarajan, Shu Wang, Bin Hu, Li Cheng, David S. Rosenblum

We propose in this paper an atomic action-based Bayesian model that constructs Allen's interval relation networks to characterize complex activities with structural varieties in a probabilistic generative way: By introducing latent variables from the Chinese restaurant process, our approach is able to capture all possible styles of a particular complex activity as a unique set of distributions over atomic actions and relations.

Activity Recognition

Learning to Search on Manifolds for 3D Pose Estimation of Articulated Objects

no code implementations2 Dec 2016 Yu Zhang, Chi Xu, Li Cheng

This paper focuses on the challenging problem of 3D pose estimation of a diverse spectrum of articulated objects from single depth images.

3D Pose Estimation Structured Prediction

Lie-X: Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups

no code implementations13 Sep 2016 Chi Xu, Lakshmi Narasimhan Govindarajan, Yu Zhang, Li Cheng

Pose estimation, tracking, and action recognition of articulated objects from depth images are important and challenging problems, which are normally considered separately.

Action Recognition Pose Estimation +2

Hand Action Detection from Ego-centric Depth Sequences with Error-correcting Hough Transform

no code implementations7 Jun 2016 Chi Xu, Lakshmi Narasimhan Govindarajan, Li Cheng

Detecting hand actions from ego-centric depth sequences is a practically challenging problem, owing mostly to the complex and dexterous nature of hand articulations as well as non-stationary camera motion.

Action Detection Action Recognition +1

Learning to Boost Filamentary Structure Segmentation

no code implementations ICCV 2015 Lin Gu, Li Cheng

Step one of our approach centers on a data-driven latent classification tree model to detect the filamentary fragments.

Image Matting Segmentation

Mouse Pose Estimation From Depth Images

no code implementations24 Nov 2015 Ashwin Nanjappa, Li Cheng, Wei Gao, Chi Xu, Adam Claridge-Chang, Zoe Bichler

We focus on the challenging problem of efficient mouse 3D pose estimation based on static images, and especially single depth images.

3D Pose Estimation

Transduction on Directed Graphs via Absorbing Random Walks

no code implementations19 Feb 2014 Jaydeep De, Xiaowei Zhang, Li Cheng

In this paper we consider the problem of graph-based transductive classification, and we are particularly interested in the directed graph scenario which is a natural form for many real world applications.

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