1 code implementation • LREC 2022 • Yi Li, Dong Yu, Pengyuan Liu
and literary grace level.
no code implementations • COLING 2022 • Guisheng Liu, Yi Li, Yanqing Guo, Xiangyang Luo, Bo wang
To achieve this, we design a contrastive-generator that can effectively generate texts with more attributes.
no code implementations • 13 Jun 2025 • Yijiang Li, Genpei Zhang, Jiacheng Cheng, Yi Li, Xiaojun Shan, Dashan Gao, Jiancheng Lyu, Yuan Li, Ning Bi, Nuno Vasconcelos
While the rapid proliferation of wearable cameras has raised significant concerns about egocentric video privacy, prior work has largely overlooked the unique privacy threats posed to the camera wearer.
no code implementations • 10 Jun 2025 • Tao Li, Yi Li, Lulin Zhang, Jiuxiang Dong
In this paper, considering the problem of state estimation with unknown but bounded noise disturbances, an Invariant Zonotopic Set-Membership Filter (InZSMF) method on groups is innovatively proposed, which extends the invariant filtering theory to the field of non-statistical filtering represented by set-membership filtering.
no code implementations • 6 Jun 2025 • Long Dang, Thushari Hapuarachchi, Kaiqi Xiong, Yi Li
In an in-vehicle network, these ECUs communicate with one another using an standard protocol called Controller Area Network (CAN).
no code implementations • 15 May 2025 • Yi Li, Haonan Wang, Qixiang Zhang, Boyu Xiao, Chenchang Hu, Hualiang Wang, Xiaomeng Li
However, there is a lack of a unified evaluation framework for these models, which would enable an elegant, simplified, and overall evaluation.
2 code implementations • 13 May 2025 • Zheang Huai, Hui Tang, Yi Li, Zhuangzhuang Chen, Xiaomeng Li
Source-free domain adaptation (SFDA) for segmentation aims at adapting a model trained in the source domain to perform well in the target domain with only the source model and unlabeled target data. Inspired by the recent success of Segment Anything Model (SAM) which exhibits the generality of segmenting images of various modalities and in different domains given human-annotated prompts like bounding boxes or points, we for the first time explore the potentials of Segment Anything Model for SFDA via automatedly finding an accurate bounding box prompt.
1 code implementation • 11 May 2025 • Fei Zhou, Yi Li, Mingqing Zhu
In this paper, the dual-optical attention fusion crowd head point counting model (TAPNet) is proposed to address the problem of the difficulty of accurate counting in complex scenes such as crowd dense occlusion and low light in crowd counting tasks under UAV view.
Ranked #1 on
Crowd Counting
on DroneRGBT
1 code implementation • 7 May 2025 • Yi Li, Zhiyuan Zhang, Jiangnan Xia, Jianghan Cheng, Qilong Wu, Junwei Li, Yibin Tian, Hui Kong
During the aligning stage, CFIs are averaged to create a target-specific CFI$^T$, which is fine-tuned using a small amount of real RAW data to adapt to the noise characteristics of specific cameras.
no code implementations • 12 Apr 2025 • Xuran Meng, Yi Li
While deep neural networks (DNNs) are widely used for prediction, inference on DNN-estimated subject-specific means for categorical or exponential family outcomes remains underexplored.
no code implementations • 9 Apr 2025 • Agil Aghasanli, Yi Li, Plamen Angelov
These mechanisms ensure the retention of previously learned information as well as adaptation to new classes or domain shifts.
no code implementations • 29 Mar 2025 • PengYu Chen, Teng Fei, Yunyan Du, Jiawei Yi, Yi Li, John A. Kupfer
Conflicts between humans and bears on the Tibetan Plateau present substantial threats to local communities and hinder wildlife preservation initiatives.
no code implementations • 4 Mar 2025 • Yuhao Yang, Zhi Ji, Zhaopeng Li, Yi Li, Zhonglin Mo, Yue Ding, Kai Chen, Zijian Zhang, Jie Li, Shuanglong Li, Lin Liu
To address this, we introduce the Cascaded Organized Bi-Represented generAtive retrieval (COBRA) framework, which innovatively integrates sparse semantic IDs and dense vectors through a cascading process.
no code implementations • CVPR 2025 • Lixu Wang, Bingqi Shang, Yi Li, Payal Mohapatra, Wei Dong, Xiao Wang, Qi Zhu
SA, inspired by split learning (SL), segments the pre-trained ViT into a frontend and a backend, with only the frontend shared with the client for data representation extraction.
no code implementations • 1 Mar 2025 • Guanwen Xie, Jingzehua Xu, Yimian Ding, Zhi Zhang, Shuai Zhang, Yi Li
The adaptivity and maneuvering capabilities of Autonomous Underwater Vehicles (AUVs) have drawn significant attention in oceanic research, due to the unpredictable disturbances and strong coupling among the AUV's degrees of freedom.
no code implementations • 25 Feb 2025 • Yi Li, Wai Ming Tai
The active regression problem of the single-index model is to solve $\min_x \lVert f(Ax)-b\rVert_p$, where $A$ is fully accessible and $b$ can only be accessed via entry queries, with the goal of minimizing the number of queries to the entries of $b$.
no code implementations • 20 Feb 2025 • Ye Liu, Yuqing Niu, Chengyan Ma, Ruidong Han, Wei Ma, Yi Li, Debin Gao, David Lo
Smart contracts are highly susceptible to manipulation attacks due to the leakage of sensitive information.
no code implementations • 17 Feb 2025 • Juantao Zhong, Daoyuan Wu, Ye Liu, Maoyi Xie, Yang Liu, Yi Li, Ning Liu
DeFi (Decentralized Finance) is one of the most important applications of today's cryptocurrencies and smart contracts.
no code implementations • 8 Feb 2025 • Yi Li, Yuquan Deng, Jesse Zhang, Joel Jang, Marius Memmel, Raymond Yu, Caelan Reed Garrett, Fabio Ramos, Dieter Fox, Anqi Li, Abhishek Gupta, Ankit Goyal
Large foundation models have shown strong open-world generalization to complex problems in vision and language, but similar levels of generalization have yet to be achieved in robotics.
no code implementations • 30 Jan 2025 • Alessandra Aldieri, Thiranja Prasad Babarenda Gamage, Antonino Amedeo La Mattina, Yi Li, Axel Loewe, Francesco Pappalardo, Marco Viceconti Italy
The rapid integration of machine learning (ML) predictors into in silico medicine has revolutionized the estimation of quantities of interest (QIs) that are otherwise challenging to measure directly.
no code implementations • 15 Jan 2025 • Shuang Cui, Yi Li, Jiangmeng Li, Xiongxin Tang, Bing Su, Fanjiang Xu, Hui Xiong
Extensive experiments demonstrate that CauSiam effectively improves the generalization performance of existing SIDD methods in continuously changing domains.
1 code implementation • 25 Dec 2024 • Gursimran Singh, Xinglu Wang, Yifan Hu, Timothy Yu, Linzi Xing, Wei Jiang, Zhefeng Wang, Xiaolong Bai, Yi Li, Ying Xiong, Yong Zhang, Zhenan Fan
Large Multimodal Models (LMMs) extend Large Language Models (LLMs) by handling diverse inputs such as images, audio, and video, but at the cost of adding a multimodal encoding stage that increases both computational and memory overhead.
no code implementations • 30 Nov 2024 • Chengyu Li, Debo Cheng, Guixian Zhang, Yi Li, Shichao Zhang
To enhance information transfer, we incorporate graph-level distillation to provide an indirect supplement of graph information during training, as well as a node-specific temperature module to improve the comprehensive transfer of fair knowledge.
no code implementations • 28 Nov 2024 • Junwei Feng, Xueyan Fan, Yuyang Chen, Yi Li
Ensuring construction site safety requires accurate and real-time detection of workers' safety helmet use, despite challenges posed by cluttered environments, densely populated work areas, and hard-to-detect small or overlapping objects caused by building obstructions.
no code implementations • 28 Nov 2024 • Zijian Zhang, Kaiyuan Zheng, Zhaorun Chen, Joel Jang, Yi Li, Siwei Han, Chaoqi Wang, Mingyu Ding, Dieter Fox, Huaxiu Yao
Notably, these constraints are flexible and can be customized to align the model with varying objectives, such as safety, efficiency, or task success.
no code implementations • 26 Nov 2024 • Jing-Yang Wei, Hao Huang, Xin Zhang, De-Mao Ye, Yi Li, Le Wang, Yao-Guang Ma, Yang-Hui Li
To provide a lightweight and cost-effective solution for the long-wave infrared imaging using a singlet, we develop a camera by integrating a High-Frequency-Enhancing Cycle-GAN neural network into a metalens imaging system.
no code implementations • 21 Nov 2024 • Fengxin Li, Yi Li, Yue Liu, Chao Zhou, YuAn Wang, Xiaoxiang Deng, Wei Xue, Dapeng Liu, Lei Xiao, Haijie Gu, Jie Jiang, Hongyan Liu, Biao Qin, Jun He
Display advertising provides significant value to advertisers, publishers, and users.
no code implementations • 8 Nov 2024 • Yi Li, Zhichun Guo, Guanpeng Li, Bingzhe Li
Graph neural networks (GNNs) have become essential tools for analyzing non-Euclidean data across various domains.
no code implementations • 15 Oct 2024 • Yimian Ding, Xinqi Wang, Jingzehua Xu, Guanwen Xie, Weiyi Liu, Yi Li
To address these issues and the constraints of turbulent ocean environments, we propose a multi-AUV assisted data collection framework for IoUT based on multi-agent offline RL.
no code implementations • 15 Oct 2024 • Yimian Ding, Jingzehua Xu, Guanwen Xie, Haoyu Wang, Weiyi Liu, Yi Li
Accurate underwater target localization is essential for underwater exploration.
no code implementations • 29 Sep 2024 • Soofiyan Atar, Yi Li, Markus Grotz, Michael Wolf, Dieter Fox, Joshua Smith
In warehouse environments, robots require robust picking capabilities to manage a wide variety of objects.
1 code implementation • 21 Sep 2024 • Yuqing Huang, Rongyang Zhang, Xuesong He, Xuyang Zhi, Hao Wang, Xin Li, Feiyang Xu, Deguang Liu, Huadong Liang, Yi Li, Jian Cui, Zimu Liu, Shijin Wang, Guoping Hu, Guiquan Liu, Qi Liu, Defu Lian, Enhong Chen
To this end, we propose \textbf{\textit{ChemEval}}, which provides a comprehensive assessment of the capabilities of LLMs across a wide range of chemical domain tasks.
no code implementations • 9 Sep 2024 • Yi Li, Heting Gao, Mingde He, Jinqian Liang, Jason Gu, Wei Liu
In scoliosis surgery, the limited field of view of the C-arm X-ray machine restricts the surgeons' holistic analysis of spinal structures . This paper presents an end-to-end efficient and robust intraoperative X-ray image stitching method for scoliosis surgery, named SX-Stitch.
no code implementations • 19 Aug 2024 • Yi Li, Shichao Zhang, Guixian Zhang, Debo Cheng
Graph unlearning technology has become increasingly important since the advent of the `right to be forgotten' and the growing concerns about the privacy and security of artificial intelligence.
no code implementations • 16 Aug 2024 • Yi Li, Honghao Lin, David P. Woodruff
Our algorithm can be extended to the $\ell_p$ sparse recovery problem with the same sketching dimension, which seems to be the first such bound for $p > 2$.
no code implementations • 5 Aug 2024 • Sepehr Dehdashtian, Ruozhen He, Yi Li, Guha Balakrishnan, Nuno Vasconcelos, Vicente Ordonez, Vishnu Naresh Boddeti
Computer vision systems have witnessed rapid progress over the past two decades due to multiple advances in the field.
1 code implementation • 26 Jul 2024 • Bo wang, Shaocong Wang, Ning Lin, Yi Li, Yifei Yu, Yue Zhang, Jichang Yang, Xiaoshan Wu, Yangu He, Songqi Wang, Rui Chen, Guoqi Li, Xiaojuan Qi, Zhongrui Wang, Dashan Shang
To address these fundamental challenges, we introduce pruning optimization for input-aware dynamic memristive spiking neural network (PRIME).
no code implementations • 22 Jul 2024 • Zhe Fei, Yi Li
Epigenetic aging clocks play a pivotal role in estimating an individual's biological age through the examination of DNA methylation patterns at numerous CpG (Cytosine-phosphate-Guanine) sites within their genome.
no code implementations • 5 Jul 2024 • Yi Li, Plamen Angelov, Neeraj Suri
Experimental results show that, compared to various benchmark self-supervised vision learning models and supervised adversarial attack detection methods, the proposed model achieves state-of-the-art performance on the adversarial attack detection task across a wide range of images.
no code implementations • 24 Jun 2024 • Alvaro Lopez Pellicer, Kittipos Giatgong, Yi Li, Neeraj Suri, Plamen Angelov
As the use of Deep Neural Networks (DNNs) becomes pervasive, their vulnerability to adversarial attacks and limitations in handling unseen classes poses significant challenges.
no code implementations • 22 Jun 2024 • Alvaro Lopez Pellcier, Yi Li, Plamen Angelov
Deepfake techniques generate highly realistic data, making it challenging for humans to discern between actual and artificially generated images.
no code implementations • 22 Jun 2024 • Yi Li, Plamen Angelov, Zhengxin Yu, Alvaro Lopez Pellicer, Neeraj Suri
As the development of deep learning techniques in autonomous landing systems continues to grow, one of the major challenges is trust and security in the face of possible adversarial attacks.
no code implementations • 17 Jun 2024 • Jiangmeng Li, Bin Qin, Qirui Ji, Yi Li, Wenwen Qiang, Jianwen Cao, Fanjiang Xu
Leveraging the development of structural causal model (SCM), researchers can establish graphical models for exploring the causal mechanisms behind machine learning techniques.
no code implementations • 17 Jun 2024 • Bin Qin, Jiangmeng Li, Yi Li, Xuesong Wu, Yupeng Wang, Wenwen Qiang, Jianwen Cao
To this end, we explore to build a SCM for representation learning process and further conduct a thorough analysis of the mechanisms underlying spurious correlation.
no code implementations • 17 Jun 2024 • Yi Li, Fei Song, Changwen Zheng, Jiangmeng Li, Fuchun Sun, Hui Xiong
However, our empirical explorations challenge the fundamental idea behind such behavior, and we further conclude that benchmark approaches suffer from certain defects: insufficient theoretical interpretability and limited exploration capability of discriminative knowledge.
1 code implementation • 12 Jun 2024 • Hegan Chen, Jichang Yang, Jia Chen, Songqi Wang, Shaocong Wang, Dingchen Wang, Xinyu Tian, Yifei Yu, Xi Chen, Yinan Lin, Yangu He, Xiaoshan Wu, Xinyuan Zhang, Ning Lin, Meng Xu, Yi Li, Xumeng Zhang, Zhongrui Wang, Han Wang, Dashan Shang, Qi Liu, Kwang-Ting Cheng, Ming Liu
We experimentally validate our approach by developing a digital twin of the HP memristor, which accurately extrapolates its nonlinear dynamics, achieving a 4. 2-fold projected speedup and a 41. 4-fold projected decrease in energy consumption compared to state-of-the-art digital hardware, while maintaining an acceptable error margin.
no code implementations • 23 May 2024 • Sheng-Jun Huang, Yi Li, Yiming Sun, Ying-Peng Tang
Active learning (AL) for multiple target models aims to reduce labeled data querying while effectively training multiple models concurrently.
no code implementations • 15 May 2024 • Aarshvi Gajjar, Wai Ming Tai, Xingyu Xu, Chinmay Hegde, Yi Li, Christopher Musco
We provide two main results on agnostic active learning of single index models.
no code implementations • 8 May 2024 • Zhihan Ju, Wanting Zhou, Longteng Kong, Yu Chen, Yi Li, Zhenan Sun, Caifeng Shan
However, due to the complexity of medical images and similar characteristics of different tissue cells, existing methods face great challenges in meeting their biological consistency.
1 code implementation • 4 May 2024 • Ye Liu, Yue Xue, Daoyuan Wu, Yuqiang Sun, Yi Li, Miaolei Shi, Yang Liu
With recent advances in large language models (LLMs), this paper explores the potential of leveraging state-of-the-art LLMs, such as GPT-4, to transfer existing human-written properties (e. g., those from Certora auditing reports) and automatically generate customized properties for unknown code.
no code implementations • 30 Apr 2024 • Yi Li, Renyou Xie, Chaojie Li, Yi Wang, ZhaoYang Dong
To address these challenges, a federated graph learning approach involving multiple charging stations is proposed to collaboratively train a more generalized deep learning model for demand forecasting while capturing spatial correlations among various stations and enhancing robustness against potential attacks.
no code implementations • 29 Apr 2024 • Nicholas S. Kersting, Yi Li, Aman Mohanty, Oyindamola Obisesan, Raphael Okochu
We introduce Harmonic Robustness, a powerful and intuitive method to test the robustness of any machine-learning model either during training or in black-box real-time inference monitoring without ground-truth labels.
1 code implementation • 23 Apr 2024 • Yi Li, Yunan Wu, Aggelos K. Katsaggelos
In response to this challenge, we introduce the Cross-Temporal Spectrogram Autoencoder (CTSAE), a pioneering unsupervised method for the dimensionality reduction and clustering of gravitational wave glitches.
1 code implementation • 8 Apr 2024 • Jichang Yang, Hegan Chen, Jia Chen, Songqi Wang, Shaocong Wang, Yifei Yu, Xi Chen, Bo wang, Xinyuan Zhang, Binbin Cui, Ning Lin, Meng Xu, Yi Li, Xiaoxin Xu, Xiaojuan Qi, Zhongrui Wang, Xumeng Zhang, Dashan Shang, Han Wang, Qi Liu, Kwang-Ting Cheng, Ming Liu
Demonstrating equivalent generative quality to the software baseline, our system achieved remarkable enhancements in generative speed for both unconditional and conditional generation tasks, by factors of 64. 8 and 156. 5, respectively.
no code implementations • 6 Apr 2024 • Yi Li, Xin Xie, Lina Lei, Haiyan Fu, Yanqing Guo
The generation of smooth and continuous images between domains has recently drawn much attention in image-to-image (I2I) translation.
1 code implementation • 5 Apr 2024 • Toru Shirakawa, Yi Li, Yulun Wu, Sky Qiu, YuXuan Li, Mingduo Zhao, Hiroyasu Iso, Mark van der Laan
We propose Deep Longitudinal Targeted Minimum Loss-based Estimation (Deep LTMLE), a novel approach to estimate the counterfactual mean of outcome under dynamic treatment policies in longitudinal problem settings.
no code implementations • 18 Mar 2024 • Howard Zhang, Yunhao Ba, Ethan Yang, Rishi Upadhyay, Alex Wong, Achuta Kadambi, Yun Guo, Xueyao Xiao, Xiaoxiong Wang, Yi Li, Yi Chang, Luxin Yan, Chaochao Zheng, Luping Wang, Bin Liu, Sunder Ali Khowaja, Jiseok Yoon, Ik-Hyun Lee, Zhao Zhang, Yanyan Wei, Jiahuan Ren, Suiyi Zhao, Huan Zheng
This report reviews the results of the GT-Rain challenge on single image deraining at the UG2+ workshop at CVPR 2023.
1 code implementation • CVPR 2024 • Haonan Wang, Qixiang Zhang, Yi Li, Xiaomeng Li
We further introduce a Semantic Memory along with a Channel Semantic Grouping strategy to ensure that unlabeled features adequately represent labeled features.
1 code implementation • 24 Feb 2024 • Zi Wang, Min Xiao, Yirong Zhou, Chengyan Wang, Naiming Wu, Yi Li, Yiwen Gong, Shufu Chang, Yinyin Chen, Liuhong Zhu, Jianjun Zhou, Congbo Cai, He Wang, Di Guo, Guang Yang, Xiaobo Qu
This challenge necessitates extensive training data in deep learning reconstruction methods.
no code implementations • 4 Feb 2024 • Wuxuan Jiang, Xiangjun Song, Shenbai Hong, Haijun Zhang, Wenxin Liu, Bo Zhao, Wei Xu, Yi Li
Accuracy and efficiency remain challenges for multi-party computation (MPC) frameworks.
1 code implementation • 17 Jan 2024 • Yiqun Lin, Liang Pan, Yi Li, Ziwei Liu, Xiaomeng Li
In this paper, we present a principled framework based on deep learning techniques, namely Hierarchical Chemical and Geometric Feature Interaction Network (HCGNet), for protein surface analysis by bridging chemical and geometric features with hierarchical interactions.
no code implementations • 22 Dec 2023 • Shengnan Wang, Yi Li, Zhou Chen, Yunjie Yang
Three-dimensional electrical capacitance tomography (3D-ECT) has shown promise for visualizing industrial multiphase flows.
no code implementations • 14 Dec 2023 • Shaocong Wang, Yizhao Gao, Yi Li, Woyu Zhang, Yifei Yu, Bo wang, Ning Lin, Hegan Chen, Yue Zhang, Yang Jiang, Dingchen Wang, Jia Chen, Peng Dai, Hao Jiang, Peng Lin, Xumeng Zhang, Xiaojuan Qi, Xiaoxin Xu, Hayden So, Zhongrui Wang, Dashan Shang, Qi Liu, Kwang-Ting Cheng, Ming Liu
Our random resistive memory-based deep extreme point learning machine may pave the way for energy-efficient and training-friendly edge AI across various data modalities and tasks.
no code implementations • 30 Nov 2023 • Yi Li, Aarti Gupta, Sharad Malik
We propose an optimization framework, named COSMA, for mapping DNNs to an accelerator that finds the optimal operator schedule, memory allocation and tensor replacement that minimizes the additional data accesses.
no code implementations • 13 Nov 2023 • Yi Li, Songqi Wang, Yaping Zhao, Shaocong Wang, Woyu Zhang, Yangu He, Ning Lin, Binbin Cui, Xi Chen, Shiming Zhang, Hao Jiang, Peng Lin, Xumeng Zhang, Xiaojuan Qi, Zhongrui Wang, Xiaoxin Xu, Dashan Shang, Qi Liu, Kwang-Ting Cheng, Ming Liu
Here, we report a universal solution, software-hardware co-design using structural plasticity-inspired edge pruning to optimize the topology of a randomly weighted analogue resistive memory neural network.
no code implementations • 4 Nov 2023 • Yi Li, Muru Zhang, Markus Grotz, Kaichun Mo, Dieter Fox
Segmentation and tracking of unseen object instances in discrete frames pose a significant challenge in dynamic industrial robotic contexts, such as distribution warehouses.
no code implementations • 1 Nov 2023 • You Zhou, Xiujing Lin, Xiang Zhang, Maolin Wang, Gangwei Jiang, Huakang Lu, Yupeng Wu, Kai Zhang, Zhe Yang, Kehang Wang, Yongduo Sui, Fengwei Jia, Zuoli Tang, Yao Zhao, Hongxuan Zhang, Tiannuo Yang, Weibo Chen, Yunong Mao, Yi Li, De Bao, Yu Li, Hongrui Liao, Ting Liu, Jingwen Liu, Jinchi Guo, Xiangyu Zhao, Ying WEI, Hong Qian, Qi Liu, Xiang Wang, Wai Kin, Chan, Chenliang Li, Yusen Li, Shiyu Yang, Jining Yan, Chao Mou, Shuai Han, Wuxia Jin, Guannan Zhang, Xiaodong Zeng
To tackle the challenges of computing resources and environmental impact of AI, Green Computing has become a hot research topic.
1 code implementation • 11 Oct 2023 • Yaohua Rong, Sihai Dave Zhao, Xia Zheng, Yi Li
To accurately predict clinical outcomes, it is vital to build an accurate predictive model that relates patients' molecular profiles with patients' survival.
no code implementations • 1 Oct 2023 • Pasquale Balsebre, Weiming Huang, Gao Cong, Yi Li
This can be attributed to the intrinsic heterogeneity of geospatial data, which encompasses different data types, including points, segments and regions, as well as multiple information modalities, such as a spatial position, visual characteristics and textual annotations.
no code implementations • 10 Sep 2023 • Guisheng Liu, Yi Li, Zhengcong Fei, Haiyan Fu, Xiangyang Luo, Yanqing Guo
While impressive performance has been achieved in image captioning, the limited diversity of the generated captions and the large parameter scale remain major barriers to the real-word application of these systems.
1 code implementation • ICCV 2023 • Hualiang Wang, Yi Li, Huifeng Yao, Xiaomeng Li
Subsequently, we introduce two loss functions: the image-text binary-opposite loss and the text semantic-opposite loss, which we use to teach CLIPN to associate images with no prompts, thereby enabling it to identify unknown samples.
1 code implementation • 19 Aug 2023 • WenBo Hu, Yifan Xu, Yi Li, Weiyue Li, Zeyuan Chen, Zhuowen Tu
BLIVA demonstrates significant capability in decoding real-world images, irrespective of text presence.
3 code implementations • 15 Aug 2023 • Zheang Huai, Xinpeng Ding, Yi Li, Xiaomeng Li
To this end, we propose a context-aware pseudo-label refinement method for SF-UDA.
1 code implementation • 22 Jul 2023 • Qixiang Zhang, Yi Li, Cheng Xue, Xiaomeng Li
In this paper, we make a first attempt to explore a deep learning method for unsupervised gland segmentation, where no manual annotations are required.
no code implementations • 11 Jul 2023 • Yi Li, Honghao Lin, David P. Woodruff
We consider the randomized communication complexity of the distributed $\ell_p$-regression problem in the coordinator model, for $p\in (0, 2]$.
no code implementations • 11 Jun 2023 • Yi Li, Honghao Lin, Simin Liu, Ali Vakilian, David P. Woodruff
We fix this issue and propose approaches for learning a sketching matrix for both low-rank approximation and Hessian approximation for second order optimization.
no code implementations • 26 May 2023 • Jianhua Zhang, Jiaxin Lin, Pan Tang, Yuxiang Zhang, Huixin Xu, Tianyang Gao, Haiyang Miao, Zeyong Chai, Zhengfu Zhou, Yi Li, Huiwen Gong, Yameng Liu, Zhiqiang Yuan, Lei Tian, Shaoshi Yang, Liang Xia, Guangyi Liu, Ping Zhang
Then, a survey of the progress of the 6G channel research regarding the above five promising technologies is presented in terms of the latest measurement campaigns, new characteristics, modeling methods, and research prospects.
no code implementations • 17 May 2023 • Ting Li, Chengchun Shi, Zhaohua Lu, Yi Li, Hongtu Zhu
However, assessing dynamic quantile treatment effects (QTE) remains a challenge, particularly when dealing with data from ride-sourcing platforms that involve sequential decision-making across time and space.
1 code implementation • 13 May 2023 • Yun Guo, Xueyao Xiao, Xiaoxiong Wang, Yi Li, Yi Chang, Luxin Yan
Secondly, a transformer-based single image deraining network Uformer is implemented to pre-train on large real rain dataset and then fine-tuned on pseudo GT to further improve image restoration.
1 code implementation • Scientific Data 2023 • Mengye Lyu, Lifeng Mei, Shoujin Huang, Sixing Liu, Yi Li, Kexin Yang, Yilong Liu, Yu Dong, Linzheng Dong, Ed X. Wu
This M4Raw dataset will be valuable for the development of advanced data-driven methods specifically for low-field MRI.
1 code implementation • CVPR 2023 • Yi Li, Kyle Min, Subarna Tripathi, Nuno Vasconcelos
Do video-text transformers learn to model temporal relationships across frames?
Ranked #4 on
Video Question Answering
on AGQA 2.0 balanced
(Average Accuracy metric)
no code implementations • 14 Apr 2023 • YiChun Li, Yi Li, Rajesh Nair, Syed Mohsen Naqvi
Attention Deficit Hyperactivity Disorder (ADHD) is a common neurobehavioral disorder worldwide.
2 code implementations • 12 Apr 2023 • Yi Li, Hualiang Wang, Yiqun Duan, Jiheng Zhang, Xiaomeng Li
These phenomena conflict with conventional explainability methods based on the class attention map (CAM), where the raw model can highlight the local foreground regions using global supervision without alignment.
Ranked #3 on
Open Vocabulary Semantic Segmentation
on COCO-Stuff-171
(mIoU metric)
no code implementations • 9 Mar 2023 • Yuming Sun, Jian Kang, Chinmay Haridas, Nicholas R. Mayne, Alexandra L. Potter, Chi-Fu Jeffrey Yang, David C. Christiani, Yi Li
The National Lung Screening Trial (NLST) employed computed tomography texture analysis, which provides objective measurements of texture patterns on CT scans, to quantify the mortality risks of lung cancer patients.
no code implementations • 1 Feb 2023 • Gaolei Li, YuanYuan Zhao, Yi Li
Most existing studies on trustworthy FL aim to eliminate data poisoning threats that are produced by malicious clients, but in many cases, eliminating model poisoning attacks brought by fake servers is also an important objective.
no code implementations • 22 Dec 2022 • Stephen Salerno, Yi Li
Prognostication for lung cancer, a leading cause of mortality, remains a complex task, as it needs to quantify the associations of risk factors and health events spanning a patient's entire life.
1 code implementation • 28 Oct 2022 • Leyi Zhao, Yi Li
Self-supervised pre-training models have been used successfully in several machine learning domains.
1 code implementation • 1 Oct 2022 • Yiqun Duan, Zhen Wang, Yi Li, Jianhang Tang, Yu-Kai Wang, Chin-Teng Lin
Recently, various neural network approaches have been proposed to improve the accuracy of EEG signal recognition.
1 code implementation • 28 Sep 2022 • Xinyue Chang, Yehua Li, Yi Li
In many longitudinal settings, time-varying covariates may not be measured at the same time as responses and are often prone to measurement error.
no code implementations • 27 Sep 2022 • Yi Li, Huifeng Yao, Hualiang Wang, Xiaomeng Li
We call the proposed framework as FreeSeg, where the mask is freely available from raw feature map of pretraining model.
Ranked #6 on
Zero-Shot Semantic Segmentation
on COCO-Stuff
no code implementations • 19 Sep 2022 • Tan Yu, Jie Liu, Yi Yang, Yi Li, Hongliang Fei, Ping Li
How to pair the video ads with the user search is the core task of Baidu video advertising.
1 code implementation • 15 Sep 2022 • Yi Li, Hualiang Wang, Yiqun Duan, Hang Xu, Xiaomeng Li
For this problem, we propose the Explainable Contrastive Language-Image Pre-training (ECLIP), which corrects the explainability via the Masked Max Pooling.
no code implementations • 30 Aug 2022 • Yi Li, Wenjie Pei, Zhenyu He
In this paper, we attempt to build a deep learning model that mimics all four steps in the traditional homography estimation pipeline.
1 code implementation • 17 Jul 2022 • Xingyu Liu, Gu Wang, Yi Li, Xiangyang Ji
While category-level 9DoF object pose estimation has emerged recently, previous correspondence-based or direct regression methods are both limited in accuracy due to the huge intra-category variances in object shape and color, etc.
no code implementations • 13 Jul 2022 • Cheng Chen, Yi Li, Yiming Sun
Active regression considers a linear regression problem where the learner receives a large number of data points but can only observe a small number of labels.
1 code implementation • 14 Jun 2022 • Yi Li, Yiduo Yu, Yiwen Zou, Tianqi Xiang, Xiaomeng Li
Existing weakly-supervised semantic segmentation methods in computer vision achieve degenerative results for gland segmentation, since the characteristics and problems of glandular datasets are different from general object datasets.
1 code implementation • CVPR 2022 • Yi Li, Rameswar Panda, Yoon Kim, Chun-Fu, Chen, Rogerio Feris, David Cox, Nuno Vasconcelos
In particular, given a source sentence an autoregressive hallucination transformer is used to predict a discrete visual representation from the input text, and the combined text and hallucinated representations are utilized to obtain the target translation.
no code implementations • 27 May 2022 • Yushi Cao, Zhiming Li, Tianpei Yang, Hao Zhang, Yan Zheng, Yi Li, Jianye Hao, Yang Liu
In this paper, we combine the above two paradigms together and propose a novel Generalizable Logic Synthesis (GALOIS) framework to synthesize hierarchical and strict cause-effect logic programs.
no code implementations • 24 May 2022 • Ledan Qian, Xiao Zhou, Yi Li, Zhongyi Hu
As an essential prerequisite for developing a medical intelligent assistant system, medical image segmentation has received extensive research and concentration from the neural network community.
no code implementations • 22 May 2022 • Alejandro Schuler, Yi Li, Mark van der Laan
Gradient boosting performs exceptionally in most prediction problems and scales well to large datasets.
no code implementations • 21 May 2022 • Jingfei Zhang, Yi Li
Gaussian graphical regression is a powerful means that regresses the precision matrix of a Gaussian graphical model on covariates, permitting the numbers of the response variables and covariates to far exceed the sample size.
1 code implementation • 7 May 2022 • Yuming Sun, Jian Kang, Chad Brummett, Yi Li
Preoperative opioid use has been reported to be associated with higher preoperative opioid demand, worse postoperative outcomes, and increased postoperative healthcare utilization and expenditures.
no code implementations • 13 Apr 2022 • Chu Han, Xipeng Pan, Lixu Yan, Huan Lin, Bingbing Li, Su Yao, Shanshan Lv, Zhenwei Shi, Jinhai Mai, Jiatai Lin, Bingchao Zhao, Zeyan Xu, Zhizhen Wang, Yumeng Wang, Yuan Zhang, Huihui Wang, Chao Zhu, Chunhui Lin, Lijian Mao, Min Wu, Luwen Duan, Jingsong Zhu, Dong Hu, Zijie Fang, Yang Chen, Yongbing Zhang, Yi Li, Yiwen Zou, Yiduo Yu, Xiaomeng Li, Haiming Li, Yanfen Cui, Guoqiang Han, Yan Xu, Jun Xu, Huihua Yang, Chunming Li, Zhenbing Liu, Cheng Lu, Xin Chen, Changhong Liang, Qingling Zhang, Zaiyi Liu
According to the technical reports of the top-tier teams, CAM is still the most popular approach in WSSS.
Data Augmentation
Weakly supervised Semantic Segmentation
+1
no code implementations • 25 Mar 2022 • Changfeng Yu, Yi Chang, Yi Li, XiLe Zhao, Luxin Yan
Consequently, we design an optimization model-driven deep CNN in which the unsupervised loss function of the optimization model is enforced on the proposed network for better generalization.
no code implementations • 23 Mar 2022 • Yi Li, Jieming Zhu, Weiwen Liu, Liangcai Su, Guohao Cai, Qi Zhang, Ruiming Tang, Xi Xiao, Xiuqiang He
Specifically, PEAR not only captures feature-level and item-level interactions, but also models item contexts from both the initial ranking list and the historical clicked item list.
1 code implementation • CVPR 2022 • Xin Xie, Yi Li, Huaibo Huang, Haiyan Fu, Wanwan Wang, Yanqing Guo
Style transfer has been well studied in recent years with excellent performance processed.
1 code implementation • CVPR 2022 • Yi Li, Yi Chang, Yan Gao, Changfeng Yu, Luxin Yan
Consequently, we perform inter-domain adaptation between the synthetic and real images by mutually exchanging the background and other two components.
no code implementations • CVPR 2022 • Yi Li, Nuno Vasconcelos
DRL is then formulated as an adversarial learning problem between the video and spatial models, with the objective of maximizing the dynamic score of learned spatiotemporal classifier.
1 code implementation • 14 Dec 2021 • Yi Li, Yiqun Duan, Zhanghui Kuang, Yimin Chen, Wayne Zhang, Xiaomeng Li
So we try to improve WSSS in the aspect of noise mitigation.
Ranked #24 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
1 code implementation • ICCV 2021 • Zhirui Dai, Yuepeng Jiang, Yi Li, Bo Liu, Antoni B. Chan, Nuno Vasconcelos
A dataset of crowd scenes with people annotations under a bird's eye view (BEV) and ground truth for metric distances is introduced, and several measures for the evaluation of social distance detection systems are proposed.
2 code implementations • ICCV 2021 • Yi Li, Zhanghui Kuang, Liyang Liu, Yimin Chen, Wayne Zhang
For these matters, we propose the following designs to push the performance to new state-of-art: (i) Coefficient of Variation Smoothing to smooth the CAMs adaptively; (ii) Proportional Pseudo-mask Generation to project the expanded CAMs to pseudo-mask based on a new metric indicating the importance of each class on each location, instead of the scores trained from binary classifiers.
Ranked #28 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
no code implementations • 17 Aug 2021 • Yi Li, Yan Song, Qin Zhang
We study the problem of learning to cluster data points using an oracle which can answer same-cluster queries.
1 code implementation • 22 Jul 2021 • Zhe Fei, Qi Zheng, Hyokyoung G. Hong, Yi Li
To our knowledge, there is little work available to draw inference on the effects of high dimensional predictors for censored quantile regression.
no code implementations • 16 Jul 2021 • Yifei Jiang, Yi Li, Yiming Sun, Jiaxin Wang, David P. Woodruff
A natural way to do this would be to simply apply $f$ to each entry of $A$, and then compute the matrix decomposition, but this requires storing all of $A$ as well as multiple passes over its entries.
no code implementations • 12 Jul 2021 • Xinyu Gao, Yi Li, Yanqing Qiu, Bangning Mao, Miaogen Chen, Yanlong Meng, Chunliu Zhao, Juan Kang, Yong Guo, Changyu Shen
Multiple optical scattering occurs when light propagates in a non-uniform medium.
no code implementations • 12 Jul 2021 • Xinyu Gao, Tianlang Wang, Jing Yang, Jinchao Tao, Yanqing Qiu, Yanlong Meng, Banging Mao, Pengwei Zhou, Yi Li
Hyperspectral image (HSI) contains both spatial pattern and spectral information which has been widely used in food safety, remote sensing, and medical detection.
no code implementations • 1 Jul 2021 • Zhiming Li, Xiaofei Xie, Haoliang Li, Zhengzi Xu, Yi Li, Yang Liu
Hitherto statistical type inference systems rely thoroughly on supervised learning approaches, which require laborious manual effort to collect and label large amounts of data.
1 code implementation • 20 Jun 2021 • Haifeng Li, Yi Li, Guo Zhang, Ruoyun Liu, Haozhe Huang, Qing Zhu, Chao Tao
Supervised learning for semantic segmentation requires a large number of labeled samples, which is difficult to obtain in the field of remote sensing.
no code implementations • 20 May 2021 • Jingyi Zhang, Huolan Zhu, Yongkai Chen, Chenguang Yang, Huimin Cheng, Yi Li, Wenxuan Zhong, Fang Wang
Background: Extensive clinical evidence suggests that a preventive screening of coronary heart disease (CHD) at an earlier stage can greatly reduce the mortality rate.
no code implementations • 7 May 2021 • Shuang Wang, Dong Zhao, Yi Li, Chi Zhang, Yuwei Guo, Qi Zang, Biao Hou, Licheng Jiao
Feature alignment between domains is one of the mainstream methods for Unsupervised Domain Adaptation (UDA) semantic segmentation.
no code implementations • 24 Feb 2021 • Yi Li, Honghao Lin, David P. Woodruff
We show how to design learned sketches for the Hessian in the context of second order methods.
no code implementations • 19 Jan 2021 • Sisi Jia, Siew Cheng Phua, Yuta Nihongaki, Yizeng Li, Michael Pacella, Yi Li, Abdul M. Mohammed, Sean Sun, Takanari Inoue, Rebecca Schulman
Mesoscale molecular assemblies on the cell surface, such as cilia and filopodia, integrate information, control transport and amplify signals.
no code implementations • 1 Jan 2021 • Xiaojun Ma, Ziyao Li, Lingjun Xu, Guojie Song, Yi Li, Chuan Shi
To address this weakness, we introduce a novel framework of conducting graph convolutions, where nodes are discretely selected among multi-hop neighborhoods to construct adaptive receptive fields (ARFs).
3 code implementations • ICLR 2021 • Liyang Liu, Yi Li, Zhanghui Kuang, Jing-Hao Xue, Yimin Chen, Wenming Yang, Qingmin Liao, Wayne Zhang
Multi-task learning (MTL) has been widely used in representation learning.
no code implementations • 31 Dec 2020 • Kailong Liu, Xiaosong Hu, Zhongbao Wei, Yi Li, Yan Jiang
Experimental results demonstrate that the modified Gaussian process regression model considering the battery electrochemical and empirical ageing signature outperforms other counterparts and is able to achieve satisfactory results for both one-step and multi-step predictions.
no code implementations • 28 Dec 2020 • Yi Li
For a modified version of cutoff AdS holography which is supposed to work only in the sector of classical pure gravity, we show that the flow equation of the metric and one point function of energy-momentum tensor in $T\bar{T}$ deformation corresponds to the flow equation of the boundary metric and Brown-York tensor on a cutoff surface in AdS space as the cutoff surface moves in the direction of normal geodesics.
High Energy Physics - Theory
no code implementations • 28 Dec 2020 • Hilal Saglam, Changjiang Liu, Yi Li, Joseph Sklenar, Jonathan Gibbons, Deshun Hong, Vedat Karakas, John E. Pearson, Ozhan Ozatay, Wei zhang, Anand Bhattacharya, Axel Hoffmann
Antiferromagnets with tunable phase transitions are promising for future spintronics applications.
Materials Science
no code implementations • 14 Dec 2020 • Zihao Qi, Eric Bobrow, Yi Li
Flat bands in lattice models have provided useful platforms for studying strong correlation and topological physics.
Mesoscale and Nanoscale Physics Strongly Correlated Electrons
no code implementations • 26 Nov 2020 • Chunzhen Li, Yi Li, Yongnan Li
There is a maximum number of distinguished Bell states, i. e. distinguising limit which is very important for increasing the channel capacity of quantum communications.
Quantum Physics
no code implementations • 5 Nov 2020 • Hao Zhu, Yi Li, Feixia Zhu, Aihua Zheng, Ran He
We propose a new task named Audio-driven Per-formance Video Generation (APVG), which aims to synthesizethe video of a person playing a certain instrument guided bya given music audio clip.
no code implementations • NeurIPS 2020 • Pedro Morgado, Yi Li, Nuno Vasconcelos
To learn from these spatial cues, we tasked a network to perform contrastive audio-visual spatial alignment of 360{\deg} video and spatial audio.
no code implementations • 25 Aug 2020 • Yi Li, Jing Lin, Kaiqi Xiong
In a modern vehicle, there are over seventy Electronics Control Units (ECUs).
no code implementations • 7 Jul 2020 • Alexandr Andoni, Collin Burns, Yi Li, Sepideh Mahabadi, David P. Woodruff
We show that, for both problems, for dimensions $d=1, 2$, one can obtain streaming algorithms with space polynomially smaller than $\frac{1}{\lambda\epsilon}$, which is the complexity of SGD for strongly convex functions like the bias-regularized SVM, and which is known to be tight in general, even for $d=1$.
1 code implementation • 25 Jun 2020 • Qingqing Long, Yilun Jin, Guojie Song, Yi Li, Wei. Lin
Specifically, we build topic models upon graphs using anonymous walks and Graph Anchor LDA, an LDA variant that selects significant structural patterns first, so as to alleviate the complexity and generate structural topics efficiently.
no code implementations • ICML 2020 • Yi Li, Ruosong Wang, Lin Yang, Hanrui Zhang
We give a row sampling algorithm for the quantile loss function with sample complexity nearly linear in the dimensionality of the data, improving upon the previous best algorithm whose sampling complexity has at least cubic dependence on the dimensionality.
1 code implementation • CVPR 2020 • Yi Li, Nuno Vasconcelos
The problem of learning an image classifier that allows detection of out-of-distribution (OOD) examples, with the help of auxiliary background datasets, is studied.
1 code implementation • 29 May 2020 • Wenwu Ye, Jin Yao, Hui Xue, Yi Li
Localizing thoracic diseases on chest X-ray plays a critical role in clinical practices such as diagnosis and treatment planning.
no code implementations • ICLR 2020 • Tanqiu Jiang, Yi Li, Honghao Lin, Yisong Ruan, David P. Woodruff
For estimating the $p$-th frequency moment for $0 < p < 2$ we obtain the first algorithms with optimal update time.
no code implementations • 20 Apr 2020 • Yi Li, Huaibo Huang, Junchi Yu, Ran He, Tieniu Tan
Face verification aims at determining whether a pair of face images belongs to the same identity.
1 code implementation • 27 Mar 2020 • Jianpeng Zhang, Yutong Xie, Guansong Pang, Zhibin Liao, Johan Verjans, Wenxin Li, Zongji Sun, Jian He, Yi Li, Chunhua Shen, Yong Xia
In this paper, we formulate the task of differentiating viral pneumonia from non-viral pneumonia and healthy controls into an one-class classification-based anomaly detection problem, and thus propose the confidence-aware anomaly detection (CAAD) model, which consists of a shared feature extractor, an anomaly detection module, and a confidence prediction module.
no code implementations • ECCV 2020 • Jie Cao, Huaibo Huang, Yi Li, Ran He, Zhenan Sun
The performance of multi-domain image-to-image translation has been significantly improved by recent progress in deep generative models.
no code implementations • 21 Dec 2019 • Xin Ma, Yi Li, Huaibo Huang, Mandi Luo, Ran He
Real-world image super-resolution (SR) is a challenging image translation problem.
1 code implementation • 19 Dec 2019 • David Rushing Dewhurst, Yi Li, Alexander Bogdan, Jasmine Geng
Securities markets are quintessential complex adaptive systems in which heterogeneous agents compete in an attempt to maximize returns.
1 code implementation • Geoscientific Model Development 2019 • Xiaomeng Huang, Xing Huang, Dong Wang, Qi Wu, Yi Li, Shixun Zhang, YuWen Chen, Mingqing Wang, Yuan Gao, Qiang Tang, Yue Chen, Zheng Fang, Zhenya Song, Guangwen Yang
In this work, we design a simple computing library to bridge the gap and decouple the work of ocean modeling from parallel computing.
no code implementations • 30 Oct 2019 • Yi Li, Yevgeniy Vorobeychik
Path planning is a fundamental and extensively explored problem in robotic control.
no code implementations • 21 Oct 2019 • Ke Zhan, Shimiao Jiang, Yu Bai, Yi Li, Xu Liu, Zhuoran Xu
Eltwise layer is a commonly used structure in the multi-branch deep learning network.
no code implementations • CVPR 2020 • Boyan Duan, Chaoyou Fu, Yi Li, Xingguang Song, Ran He
The cross-sensor gap is one of the challenges that have aroused much research interests in Heterogeneous Face Recognition (HFR).
1 code implementation • CVPR 2019 • Yi Li, Zhanghui Kuang, Yimin Chen, Wayne Zhang
The most informative output neurons in each block are preserved while others are discarded, and thus neurons for multiple scales are competitively and adaptively allocated.
Ranked #763 on
Image Classification
on ImageNet
1 code implementation • CVPR 2019 • Yi Li, Nuno Vasconcelos
An experimental set-up is also introduced to measure the bias of any dataset for a given representation, and the impact of this bias on the performance of recognition models.
no code implementations • 14 Apr 2019 • Jie Cao, Huaibo Huang, Yi Li, Jingtuo Liu, Ran He, Zhenan Sun
In this work, we present a novel training framework for GANs, namely biphasic learning, to achieve image-to-image translation in multiple visual domains at $1024^2$ resolution.
1 code implementation • 11 Mar 2019 • Zhe Fei, Yi Li
In modern biomedical studies, focus has been shifted to estimate and explain the joint effects of high dimensional predictors (for example, molecular biomarkers) on a disease outcome (for example, onset of cancer).
Methodology
1 code implementation • 25 Feb 2019 • Yi Li
Instead of directly regressing the rotation angle of the ellipse as the common practice, GPN represents bounding ellipses as 2D Gaussian distributions on the image plain and minimizes the Kullback-Leibler (KL) divergence between the proposed Gaussian and the ground truth Gaussian for object localization.
no code implementations • 26 Dec 2018 • Xin Zheng, Yanqing Guo, Huaibo Huang, Yi Li, Ran He
Deep learning based facial attribute analysis consists of two basic sub-issues: facial attribute estimation (FAE), which recognizes whether facial attributes are present in given images, and facial attribute manipulation (FAM), which synthesizes or removes desired facial attributes.
no code implementations • 17 Dec 2018 • Hao Zhu, Huaibo Huang, Yi Li, Aihua Zheng, Ran He
Talking face generation aims to synthesize a face video with precise lip synchronization as well as a smooth transition of facial motion over the entire video via the given speech clip and facial image.
no code implementations • 13 Dec 2018 • Xiaoning Du, Xiaofei Xie, Yi Li, Lei Ma, Jianjun Zhao, Yang Liu
Our in-depth evaluation on a state-of-the-art speech-to-text DL system demonstrates the effectiveness of our technique in improving quality and reliability of stateful DL systems.
no code implementations • 18 Oct 2018 • Maria-Florina Balcan, Yi Li, David P. Woodruff, Hongyang Zhang
This improves upon the previous $O(d^2/\epsilon^2)$ bound (SODA'03), and bypasses an $\Omega(d^2/\epsilon^2)$ lower bound of (KDD'14) which holds if the algorithm is required to read a submatrix.
no code implementations • ECCV 2018 • Yingwei Li, Yi Li, Nuno Vasconcelos
The notion of the representation bias of a dataset is proposed to combat this problem.
no code implementations • EMNLP 2018 • Jiaji Huang, Yi Li, Wei Ping, Liang Huang
We propose a large margin criterion for training neural language models.
1 code implementation • 19 Jun 2018 • Yi Li, Wei Ping
Compared to the baseline method without considering spatial correlations, we show that the proposed NCRF framework obtains probability maps of patch predictions with better visual quality.
no code implementations • 17 May 2018 • Kevin He, Jian Kang, Hyokyoung Grace Hong, Ji Zhu, Yanming Li, Huazhen Lin, Han Xu, Yi Li
Modern bio-technologies have produced a vast amount of high-throughput data with the number of predictors far greater than the sample size.
2 code implementations • ECCV 2018 • Yi Li, Gu Wang, Xiangyang Ji, Yu Xiang, Dieter Fox
Estimating the 6D pose of objects from images is an important problem in various applications such as robot manipulation and virtual reality.
Ranked #3 on
6D Pose Estimation using RGBD
on YCB-Video
no code implementations • 27 Oct 2017 • Yan-Feng Lu, Li-Hao Jia, Hong Qaio, Yi Li
Although the performance of BIM for image recognition is robust, it takes the randomly selected ways for the patch selection, which is sightless, and results in heavy computing burden.
no code implementations • 12 Sep 2017 • Yi Li, Lingxiao Song, Xiang Wu, Ran He, Tieniu Tan
This paper proposes a learning from generation approach for makeup-invariant face verification by introducing a bi-level adversarial network (BLAN).
no code implementations • 24 Jul 2017 • Eric Battenberg, Jitong Chen, Rewon Child, Adam Coates, Yashesh Gaur, Yi Li, Hairong Liu, Sanjeev Satheesh, David Seetapun, Anuroop Sriram, Zhenyao Zhu
In this work, we perform an empirical comparison among the CTC, RNN-Transducer, and attention-based Seq2Seq models for end-to-end speech recognition.
1 code implementation • 27 Apr 2017 • Zhiwei Lin, Yi Li, Xiaolian Guo
The consensus measure can be used to evaluate rankings in many information systems, as quite often there is not ground truth available for evaluation.
38 code implementations • ICCV 2017 • Jifeng Dai, Haozhi Qi, Yuwen Xiong, Yi Li, Guodong Zhang, Han Hu, Yichen Wei
Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules.
Ranked #3 on
Vessel Detection
on Vessel detection Dateset
no code implementations • 3 Jan 2017 • Xinyu Wang, Hanxi Li, Yi Li, Fumin Shen, Fatih Porikli
Visual tracking is a fundamental problem in computer vision.
3 code implementations • CVPR 2017 • Yi Li, Haozhi Qi, Jifeng Dai, Xiangyang Ji, Yichen Wei
It inherits all the merits of FCNs for semantic segmentation and instance mask proposal.
Ranked #100 on
Instance Segmentation
on COCO test-dev
no code implementations • 4 Nov 2016 • Yanming Li, Hyokyoung Hong, Jian Kang, Kevin He, Ji Zhu, Yi Li
Although much progress has been made in classification with high-dimensional features \citep{Fan_Fan:2008, JGuo:2010, CaiSun:2014, PRXu:2014}, classification with ultrahigh-dimensional features, wherein the features much outnumber the sample size, defies most existing work.
48 code implementations • NeurIPS 2016 • Jifeng Dai, Yi Li, Kaiming He, Jian Sun
In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almost all computation shared on the entire image.
Ranked #4 on
Real-Time Object Detection
on PASCAL VOC 2007
no code implementations • 29 Mar 2016 • Jifeng Dai, Kaiming He, Yi Li, Shaoqing Ren, Jian Sun
In contrast to the previous FCN that generates one score map, our FCN is designed to compute a small set of instance-sensitive score maps, each of which is the outcome of a pixel-wise classifier of a relative position to instances.
no code implementations • 10 Dec 2015 • Yezhou Yang, Yi Li, Cornelia Fermuller, Yiannis Aloimonos
In this paper we consider the problem of continuously discovering image contents by actively asking image based questions and subsequently answering the questions being asked.
no code implementations • 18 Nov 2015 • Aiwen Jiang, Fang Wang, Fatih Porikli, Yi Li
We then feed the episodes to a standard question answering module together with the contextual visual information and linguistic information.
no code implementations • 9 Oct 2015 • Yi Li, Yi-Zhe Song, Timothy Hospedales, Shaogang Gong
We present a generative model which can automatically summarize the stroke composition of free-hand sketches of a given category.
no code implementations • CVPR 2015 • Yezhou Yang, Cornelia Fermuller, Yi Li, Yiannis Aloimonos
The grasp type provides crucial information about human action.
no code implementations • CVPR 2015 • Yonggang Qi, Yi-Zhe Song, Tao Xiang, Honggang Zhang, Timothy Hospedales, Yi Li, Jun Guo
We propose a perceptual grouping framework that organizes image edges into meaningful structures and demonstrate its usefulness on various computer vision tasks.
no code implementations • CVPR 2015 • Fang Wang, Le Kang, Yi Li
Almost always in state of the art approaches a large amount of "best views" are computed for 3D models, with the hope that the query sketch matches one of these 2D projections of 3D models using predefined features.
no code implementations • 28 Feb 2015 • Hanxi Li, Yi Li, Fatih Porikli
In this work, we present an efficient and very robust tracking algorithm using a single Convolutional Neural Network (CNN) for learning effective feature representations of the target object, in a purely online manner.
no code implementations • 13 Jan 2015 • Yi Wang, Yi Li, Momiao Xiong, Li Jin
To improve accuracy and speed of regressions and classifications, we present a data-based prediction method, Random Bits Regression (RBR).
no code implementations • 11 Aug 2014 • Yi Li, Qi Wei, Fei Qiao, Huazhong Yang
In this paper, we propose an active circuit network to implement multi-scale Gaussian filter, which is also called Gaussian Pyramid in image preprocessing.
no code implementations • CVPR 2014 • Qiuhong Ke, Yi Li
and 3) how to use rotation unaware local features for rotation aware shape recognition?
no code implementations • CVPR 2014 • Le Kang, Peng Ye, Yi Li, David Doermann
In this work we describe a Convolutional Neural Network (CNN) to accurately predict image quality without a reference image.
no code implementations • CVPR 2014 • Le Kang, Yi Li, David Doermann
In this paper, higher-order correlation clustering (HOCC) is used for text line detection in natural images.
no code implementations • CVPR 2013 • Fang Wang, Yi Li
Our method outperformed the state of the art on the LSP, both in the scenarios when the training images are from the same dataset and from the PARSE dataset.
no code implementations • 23 Apr 2013 • Fang Wang, Yi Li
When the structure of the compositional parts is a tree, we derive an efficient approach to estimating human poses in images.