Search Results for author: Tong Li

Found 40 papers, 18 papers with code

CustomListener: Text-guided Responsive Interaction for User-friendly Listening Head Generation

no code implementations1 Mar 2024 Xi Liu, Ying Guo, Cheng Zhen, Tong Li, Yingying Ao, Pengfei Yan

To achieve coherence between segments, we design a Past Guided Generation Module (PGG) to maintain the consistency of customized listener attributes through the motion prior, and utilize a diffusion-based structure conditioned on the portrait token and the motion prior to realize the controllable generation.

Towards Fine-Grained Explainability for Heterogeneous Graph Neural Network

1 code implementation23 Dec 2023 Tong Li, Jiale Deng, Yanyan Shen, Luyu Qiu, Yongxiang Huang, Caleb Chen Cao

Heterogeneous graph neural networks (HGNs) are prominent approaches to node classification tasks on heterogeneous graphs.

Node Classification

Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation

1 code implementation11 Dec 2023 Qi Yang, Xing Nie, Tong Li, Pengfei Gao, Ying Guo, Cheng Zhen, Pengfei Yan, Shiming Xiang

For the first time, our framework explores three types of bilateral entanglements within AVS: pixel entanglement, modality entanglement, and temporal entanglement.

Keyword spotting -- Detecting commands in speech using deep learning

no code implementations9 Dec 2023 Sumedha Rai, Tong Li, Bella Lyu

Speech recognition has become an important task in the development of machine learning and artificial intelligence.

Feature Engineering Keyword Spotting +2

You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception

no code implementations9 Dec 2023 Sheng Jin, Shuhuai Li, Tong Li, Wentao Liu, Chen Qian, Ping Luo

Human-centric perception (e. g. pedetrian detection, segmentation, pose estimation, and attribute analysis) is a long-standing problem for computer vision.

Attribute Multi-Task Learning +1

Joint adjustment image steganography networks

1 code implementation Signal Processing: Image Communication 2023 Le Zhang, Yao Lu, Tong Li, Guangming Lu

Thus, the security and quality of stego and revealed secret images still have much room for promotion, especially for large-capacity image steganography.

Image Steganography Steganographics

Stimulating the Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling

1 code implementation8 Jul 2023 Tong Li, Hansen Feng, Lizhi Wang, Zhiwei Xiong, Hua Huang

Image denoising is a fundamental problem in computational photography, where achieving high perception with low distortion is highly demanding.

Image Denoising

Carbon emissions and sustainability of launching 5G mobile networks in China

no code implementations14 Jun 2023 Tong Li, Li Yu, Yibo Ma, Tong Duan, Wenzhen Huang, Yan Zhou, Depeng Jin, Yong Li, Tao Jiang

We show that the decline in carbon efficiency leads to a carbon efficiency trap, estimated to cause additional carbon emissions of 23. 82 +- 1. 07 megatons in China.

A Sequence-to-Sequence&Set Model for Text-to-Table Generation

1 code implementation31 May 2023 Tong Li, Zhihao Wang, Liangying Shao, Xuling Zheng, Xiaoli Wang, Jinsong Su

Specifically, in addition to a text encoder encoding the input text, our model is equipped with a table header generator to first output a table header, i. e., the first row of the table, in the manner of sequence generation.

Improving Knowledge Distillation via Transferring Learning Ability

1 code implementation24 Apr 2023 Long Liu, Tong Li, Hui Cheng

Existing knowledge distillation methods generally use a teacher-student approach, where the student network solely learns from a well-trained teacher.

Knowledge Distillation

Connectivity based Real-Time fMRI Neurofeedback Training in Youth with a History of Major Depressive Disorder

no code implementations25 Jan 2023 Xiaofu He, Diana Rodriguez Moreno, Zhenghua Hou, Keely Cheslack-Postava, Yanni Jiang, Tong Li, Ronit Kishon, Larry Amsel, George Musa, Zhishun Wang, Christina W. Hovena

Therefore, the aim of present study is to investigate the use of connectivity between amygdala and prefrontal regions as the target of neurofeedback training in healthy individuals and subjects with a life-time history of major depressive disorder (MDD) performing an emotion regulation task.

Single Depth-image 3D Reflection Symmetry and Shape Prediction

no code implementations ICCV 2023 Zhaoxuan Zhang, Bo Dong, Tong Li, Felix Heide, Pieter Peers, BaoCai Yin, Xin Yang

In this paper, we present Iterative Symmetry Completion Network (ISCNet), a single depth-image shape completion method that exploits reflective symmetry cues to obtain more detailed shapes.

UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression

1 code implementation6 Dec 2022 Jiaqi Chen, Tong Li, Jinghui Qin, Pan Lu, Liang Lin, Chongyu Chen, Xiaodan Liang

Naturally, we also present a unified multi-task Geometric Transformer framework, Geoformer, to tackle calculation and proving problems simultaneously in the form of sequence generation, which finally shows the reasoning ability can be improved on both two tasks by unifying formulation.

Geometry Problem Solving Logical Reasoning +1

Point Cloud Scene Completion with Joint Color and Semantic Estimation from Single RGB-D Image

no code implementations12 Oct 2022 Zhaoxuan Zhang, Xiaoguang Han, Bo Dong, Tong Li, BaoCai Yin, Xin Yang

Given a single RGB-D image, our method first predicts its semantic segmentation map and goes through the 3D volume branch to obtain a volumetric scene reconstruction as a guide to the next view inpainting step, which attempts to make up the missing information; the third step involves projecting the volume under the same view of the input, concatenating them to complete the current view RGB-D and segmentation map, and integrating all RGB-D and segmentation maps into the point cloud.

Image Inpainting Segmentation +1

DisenHCN: Disentangled Hypergraph Convolutional Networks for Spatiotemporal Activity Prediction

1 code implementation14 Aug 2022 Yinfeng Li, Chen Gao, Quanming Yao, Tong Li, Depeng Jin, Yong Li

In particular, we first unify the fine-grained user similarity and the complex matching between user preferences and spatiotemporal activity into a heterogeneous hypergraph.

Activity Prediction Graph Embedding +1

Enhancing Collaborative Filtering Recommender with Prompt-Based Sentiment Analysis

1 code implementation19 Jul 2022 Elliot Dang, Zheyuan Hu, Tong Li

We build the recommenders on the Amazon US Reviews dataset, and tune the pretrained BERT and RoBERTa with the traditional fine-tuned paradigm as well as the new prompt-based learning paradigm.

Collaborative Filtering Sentiment Analysis

Medical Scientific Table-to-Text Generation with Human-in-the-Loop under the Data Sparsity Constraint

no code implementations24 May 2022 Heng-Yi Wu, Jingqing Zhang, Julia Ive, Tong Li, Vibhor Gupta, Bingyuan Chen, Yike Guo

Structured (tabular) data in the preclinical and clinical domains contains valuable information about individuals and an efficient table-to-text summarization system can drastically reduce manual efforts to condense this data into reports.

Data Augmentation Table-to-Text Generation +1

A Scalable Workflow to Build Machine Learning Classifiers with Clinician-in-the-Loop to Identify Patients in Specific Diseases

no code implementations18 May 2022 Jingqing Zhang, Atri Sharma, Luis Bolanos, Tong Li, Ashwani Tanwar, Vibhor Gupta, Yike Guo

This paper proposes a scalable workflow which leverages both structured data and unstructured textual notes from EHRs with techniques including NLP, AutoML and Clinician-in-the-Loop mechanism to build machine learning classifiers to identify patients at scale with given diseases, especially those who might currently be miscoded or missed by ICD codes.

AutoML Specificity

Algorithms for Adaptive Experiments that Trade-off Statistical Analysis with Reward: Combining Uniform Random Assignment and Reward Maximization

no code implementations15 Dec 2021 Tong Li, Jacob Nogas, Haochen Song, Harsh Kumar, Audrey Durand, Anna Rafferty, Nina Deliu, Sofia S. Villar, Joseph J. Williams

TS-PostDiff takes a Bayesian approach to mixing TS and Uniform Random (UR): the probability a participant is assigned using UR allocation is the posterior probability that the difference between two arms is 'small' (below a certain threshold), allowing for more UR exploration when there is little or no reward to be gained.

Thompson Sampling

Nonlinear Approaches to Intergenerational Income Mobility allowing for Measurement Error

no code implementations20 Jul 2021 Brantly Callaway, Tong Li, Irina Murtazashvili

This paper considers nonlinear measures of intergenerational income mobility such as (i) the effect of parents' permanent income on the entire distribution of child's permanent income, (ii) transition matrices, and (iii) rank-rank correlations when observed annual incomes are treated as measured-with-error versions of permanent incomes.

Two Sample Unconditional Quantile Effect

no code implementations20 May 2021 Atsushi Inoue, Tong Li, Qi Xu

This paper proposes a new framework to evaluate unconditional quantile effects (UQE) in a data combination model.

counterfactual Vocal Bursts Valence Prediction

Policy Evaluation during a Pandemic

1 code implementation14 May 2021 Brantly Callaway, Tong Li

National and local governments have implemented a large number of policies in response to the Covid-19 pandemic.

Epidemiology

Self-Adaptive Transfer Learning for Multicenter Glaucoma Classification in Fundus Retina Images

no code implementations7 May 2021 Yiming Bao, Jun Wang, Tong Li, Linyan Wang, Jianwei Xu, Juan Ye, Dahong Qian

Specifically, the encoder of a DL model that is pre-trained on the source domain is used to initialize the encoder of a reconstruction model.

Domain Adaptation Transfer Learning

Document-aligned Japanese-English Conversation Parallel Corpus

1 code implementation WMT (EMNLP) 2020 Matīss Rikters, Ryokan Ri, Tong Li, Toshiaki Nakazawa

Sentence-level (SL) machine translation (MT) has reached acceptable quality for many high-resourced languages, but not document-level (DL) MT, which is difficult to 1) train with little amount of DL data; and 2) evaluate, as the main methods and data sets focus on SL evaluation.

Machine Translation Sentence +1

Microscopic origin of reflection-asymmetric nuclear shapes

no code implementations11 Dec 2020 Mengzhi Chen, Tong Li, Jacek Dobaczewski, Witold Nazarewicz

Background: The presence of nuclear ground states with stable reflection-asymmetric shapes is supported by rich experimental evidence.

Nuclear Theory

C-Learning: Horizon-Aware Cumulative Accessibility Estimation

1 code implementation ICLR 2021 Panteha Naderian, Gabriel Loaiza-Ganem, Harry J. Braviner, Anthony L. Caterini, Jesse C. Cresswell, Tong Li, Animesh Garg

In order to address these limitations, we introduce the concept of cumulative accessibility functions, which measure the reachability of a goal from a given state within a specified horizon.

Continuous Control Motion Planning

Designing the Business Conversation Corpus

1 code implementation WS 2019 Matīss Rikters, Ryokan Ri, Tong Li, Toshiaki Nakazawa

While the progress of machine translation of written text has come far in the past several years thanks to the increasing availability of parallel corpora and corpora-based training technologies, automatic translation of spoken text and dialogues remains challenging even for modern systems.

 Ranked #1 on Machine Translation on Business Scene Dialogue JA-EN (using extra training data)

Machine Translation Translation

Relation-aware Meta-learning for Market Segment Demand Prediction with Limited Records

no code implementations1 Aug 2020 Jiatu Shi, Huaxiu Yao, Xian Wu, Tong Li, Zedong Lin, Tengfei Wang, Binqiang Zhao

The goal is to facilitate the learning process in the target segments by leveraging the learned knowledge from data-sufficient source segments.

Meta-Learning Relation

Evaluating Policies Early in a Pandemic: Bounding Policy Effects with Nonrandomly Missing Data

no code implementations19 May 2020 Brantly Callaway, Tong Li

During the early part of the Covid-19 pandemic, national and local governments introduced a number of policies to combat the spread of Covid-19.

Urban Anomaly Analytics: Description, Detection, and Prediction

no code implementations25 Apr 2020 Mingyang Zhang, Tong Li, Yue Yu, Yong Li, Pan Hui, Yu Zheng

Urban anomalies may result in loss of life or property if not handled properly.

Edge Intelligence: Architectures, Challenges, and Applications

no code implementations26 Mar 2020 Dianlei Xu, Tong Li, Yong Li, Xiang Su, Sasu Tarkoma, Tao Jiang, Jon Crowcroft, Pan Hui

Edge intelligence refers to a set of connected systems and devices for data collection, caching, processing, and analysis in locations close to where data is captured based on artificial intelligence.

On the Optimality of Gaussian Kernel Based Nonparametric Tests against Smooth Alternatives

no code implementations7 Sep 2019 Tong Li, Ming Yuan

In addition, our analysis also pinpoints the importance of choosing a diverging scaling parameter when using Gaussian kernels and suggests a data-driven choice of the scaling parameter that yields tests optimal, up to an iterated logarithmic factor, over a wide range of smooth alternatives.

Cellular Controlled Delay TCP (C2TCP)

1 code implementation7 Jul 2018 Soheil Abbasloo, Tong Li, Yang Xu, H. Jonathan Chao

To cope with these challenges, we present C2TCP, a flexible end-to-end solution targeting interactive applications requiring high throughput and low delay in cellular networks.

Networking and Internet Architecture

On the Optimality of Kernel-Embedding Based Goodness-of-Fit Tests

no code implementations24 Sep 2017 Krishnakumar Balasubramanian, Tong Li, Ming Yuan

The reproducing kernel Hilbert space (RKHS) embedding of distributions offers a general and flexible framework for testing problems in arbitrary domains and has attracted considerable amount of attention in recent years.

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