no code implementations • 24 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.
1 code implementation • 7 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
no code implementations • 15 Mar 2019 • Wei Feng, Wentao Liu, Tong Li, Jing Peng, Chen Qian, Xiaolin Hu
Human-object interactions (HOI) recognition and pose estimation are two closely related tasks.
no code implementations • 7 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.
no code implementations • 26 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.
no code implementations • 25 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.
no code implementations • 19 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.
no code implementations • 1 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.
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)
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.
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.
no code implementations • 11 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
no code implementations • 7 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.
1 code implementation • 14 May 2021 • Brantly Callaway, Tong Li
National and local governments have implemented a large number of policies in response to the Covid-19 pandemic.
no code implementations • 20 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.
no code implementations • 20 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.
no code implementations • EMNLP 2021 • Jingqing Zhang, Luis Bolanos, Tong Li, Ashwani Tanwar, Guilherme Freire, Xian Yang, Julia Ive, Vibhor Gupta, Yike Guo
Contextualised word embeddings is a powerful tool to detect contextual synonyms.
no code implementations • 15 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.
no code implementations • 18 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.
no code implementations • 24 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.
1 code implementation • 19 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.
1 code implementation • 27 Jul 2022 • Jie Lei, Zhao Liu, Zeyu Zou, Tong Li, Xu Juan, Shuaiwei Wang, Guoyu Yang, Zunlei Feng
On the other hand, GUS is introduced to suppress the feature ambiguity in the representation space.
Facial Expression Recognition Facial Expression Recognition (FER) +1
1 code implementation • 14 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.
no code implementations • 12 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.
1 code implementation • 6 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.
Ranked #3 on Mathematical Reasoning on PGPS9K
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.
no code implementations • 25 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.
1 code implementation • 10 Mar 2023 • Yingguang Yang, Renyu Yang, Hao Peng, Yangyang Li, Tong Li, Yong Liao, Pengyuan Zhou
In particular, a global generator is used to extract the knowledge of global data distribution and distill it into each client's local model.
1 code implementation • 24 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.
1 code implementation • 31 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.
no code implementations • 14 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.
1 code implementation • 8 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.
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.
1 code implementation • 1 Aug 2023 • Yanxin Xi, Yu Liu, Tong Li, Jintao Ding, Yunke Zhang, Sasu Tarkoma, Yong Li, Pan Hui
Especially satellite imagery is a potential data source for studying sustainable urban development.
1 code implementation • 13 Oct 2023 • Harsh Kumar, Tong Li, Jiakai Shi, Ilya Musabirov, Rachel Kornfield, Jonah Meyerhoff, Ananya Bhattacharjee, Chris Karr, Theresa Nguyen, David Mohr, Anna Rafferty, Sofia Villar, Nina Deliu, Joseph Jay Williams
Digital mental health (DMH) interventions, such as text-message-based lessons and activities, offer immense potential for accessible mental health support.
no code implementations • 9 Dec 2023 • Sumedha Rai, Tong Li, Bella Lyu
Speech recognition has become an important task in the development of machine learning and artificial intelligence.
no code implementations • 9 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.
1 code implementation • 11 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.
1 code implementation • 23 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.
no code implementations • 1 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.