Search Results for author: Feng Li

Found 89 papers, 48 papers with code

LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models

1 code implementation5 Dec 2023 Hao Zhang, Hongyang Li, Feng Li, Tianhe Ren, Xueyan Zou, Shilong Liu, Shijia Huang, Jianfeng Gao, Lei Zhang, Chunyuan Li, Jianwei Yang

To address this issue, we have created GVC data that allows for the combination of grounding and chat capabilities.

Convolutional Neural Networks for Segmentation of Malignant Pleural Mesothelioma: Analysis of Probability Map Thresholds (CALGB 30901, Alliance)

no code implementations30 Nov 2023 Mena Shenouda, Eyjólfur Gudmundsson, Feng Li, Christopher M. Straus, Hedy L. Kindler, Arkadiusz Z. Dudek, Thomas Stinchcombe, Xiaofei Wang, Adam Starkey, Samuel G. Armato III

Percent difference of tumor volume and overlap using the Dice Similarity Coefficient (DSC) were compared between the standard reference provided by the radiologist and CNN outputs for thresholds ranging from 0. 001 to 0. 9.

Computed Tomography (CT)

T-Rex: Counting by Visual Prompting

no code implementations22 Nov 2023 Qing Jiang, Feng Li, Tianhe Ren, Shilong Liu, Zhaoyang Zeng, Kent Yu, Lei Zhang

Guided by the visual feedback from T-Rex, users can also interactively refine the counting results by prompting on missing or falsely-detected objects.

Object Counting object-detection +3

Visual In-Context Prompting

1 code implementation22 Nov 2023 Feng Li, Qing Jiang, Hao Zhang, Tianhe Ren, Shilong Liu, Xueyan Zou, Huaizhe xu, Hongyang Li, Chunyuan Li, Jianwei Yang, Lei Zhang, Jianfeng Gao

In-context prompting in large language models (LLMs) has become a prevalent approach to improve zero-shot capabilities, but this idea is less explored in the vision domain.

Segmentation Visual Prompting

Infinite forecast combinations based on Dirichlet process

no code implementations21 Nov 2023 Yinuo Ren, Feng Li, Yanfei Kang, Jue Wang

Forecast combination integrates information from various sources by consolidating multiple forecast results from the target time series.

Time Series

Probabilistic Forecast Reconciliation with Kullback-Leibler Divergence Regularization

1 code implementation21 Nov 2023 Guanyu Zhang, Feng Li, Yanfei Kang

As the popularity of hierarchical point forecast reconciliation methods increases, there is a growing interest in probabilistic forecast reconciliation.

Time Series

An Approach for Multi-Object Tracking with Two-Stage Min-Cost Flow

no code implementations5 Nov 2023 Huining Li, Yalong Jiang, Xianlin Zeng, Feng Li, Zhipeng Wang

Specifically, we employ the minimum network flow algorithm with high-confidence detections as input in the first stage to obtain the candidate tracklets that need correction.

Multi-Object Tracking

Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V

3 code implementations17 Oct 2023 Jianwei Yang, Hao Zhang, Feng Li, Xueyan Zou, Chunyuan Li, Jianfeng Gao

We present Set-of-Mark (SoM), a new visual prompting method, to unleash the visual grounding abilities of large multimodal models (LMMs), such as GPT-4V.

Interactive Segmentation Referring Expression +4

Forecasting large collections of time series: feature-based methods

1 code implementation25 Sep 2023 Li Li, Feng Li, Yanfei Kang

In economics and many other forecasting domains, the real world problems are too complex for a single model that assumes a specific data generation process.

Model Selection Time Series

Incentivizing Massive Unknown Workers for Budget-Limited Crowdsensing: From Off-Line and On-Line Perspectives

no code implementations21 Sep 2023 Feng Li, Yuqi Chai, Huan Yang, Pengfei Hu, Lingjie Duan

Moreover, the standard CMAB usually assumes the workers always stay in the system, whereas the workers may join in or depart from the system over time, such that what we have learnt for an individual worker cannot be applied after the worker leaves.

Neural Interactive Keypoint Detection

1 code implementation ICCV 2023 Jie Yang, Ailing Zeng, Feng Li, Shilong Liu, Ruimao Zhang, Lei Zhang

Click-Pose explores how user feedback can cooperate with a neural keypoint detector to correct the predicted keypoints in an interactive way for a faster and more effective annotation process.

Keypoint Detection

A Forecaster's Review of Judea Pearl's Causality: Models, Reasoning and Inference, Second Edition, 2009

no code implementations10 Aug 2023 Feng Li

With the big popularity and success of Judea Pearl's original causality book, this review covers the main topics updated in the second edition in 2009 and illustrates an easy-to-follow causal inference strategy in a forecast scenario.

Causal Inference Time Series +1

DFA3D: 3D Deformable Attention For 2D-to-3D Feature Lifting

no code implementations ICCV 2023 Hongyang Li, Hao Zhang, Zhaoyang Zeng, Shilong Liu, Feng Li, Tianhe Ren, Lei Zhang

Existing feature lifting approaches, such as Lift-Splat-based and 2D attention-based, either use estimated depth to get pseudo LiDAR features and then splat them to a 3D space, which is a one-pass operation without feature refinement, or ignore depth and lift features by 2D attention mechanisms, which achieve finer semantics while suffering from a depth ambiguity problem.

3D Object Detection object-detection

Semantic-SAM: Segment and Recognize Anything at Any Granularity

1 code implementation10 Jul 2023 Feng Li, Hao Zhang, Peize Sun, Xueyan Zou, Shilong Liu, Jianwei Yang, Chunyuan Li, Lei Zhang, Jianfeng Gao

In this paper, we introduce Semantic-SAM, a universal image segmentation model to enable segment and recognize anything at any desired granularity.

Image Segmentation Segmentation +1

You Can Mask More For Extremely Low-Bitrate Image Compression

1 code implementation27 Jun 2023 Anqi Li, Feng Li, Jiaxin Han, Huihui Bai, Runmin Cong, Chunjie Zhang, Meng Wang, Weisi Lin, Yao Zhao

Extensive experiments have demonstrated that our approach outperforms recent state-of-the-art methods in R-D performance, visual quality, and downstream applications, at very low bitrates.

Image Compression

Exploring Resolution Fields for Scalable Image Compression with Uncertainty Guidance

1 code implementation15 Jun 2023 Dongyi Zhang, Feng Li, Man Liu, Runmin Cong, Huihui Bai, Meng Wang, Yao Zhao

In this work, we explore the potential of resolution fields in scalable image compression and propose the reciprocal pyramid network (RPN) that fulfills the need for more adaptable and versatile compression.

Image Compression

detrex: Benchmarking Detection Transformers

1 code implementation12 Jun 2023 Tianhe Ren, Shilong Liu, Feng Li, Hao Zhang, Ailing Zeng, Jie Yang, Xingyu Liao, Ding Jia, Hongyang Li, He Cao, Jianan Wang, Zhaoyang Zeng, Xianbiao Qi, Yuhui Yuan, Jianwei Yang, Lei Zhang

To address this issue, we develop a unified, highly modular, and lightweight codebase called detrex, which supports a majority of the mainstream DETR-based instance recognition algorithms, covering various fundamental tasks, including object detection, segmentation, and pose estimation.

Benchmarking object-detection +2

A Strong and Reproducible Object Detector with Only Public Datasets

2 code implementations25 Apr 2023 Tianhe Ren, Jianwei Yang, Shilong Liu, Ailing Zeng, Feng Li, Hao Zhang, Hongyang Li, Zhaoyang Zeng, Lei Zhang

This work presents Focal-Stable-DINO, a strong and reproducible object detection model which achieves 64. 6 AP on COCO val2017 and 64. 8 AP on COCO test-dev using only 700M parameters without any test time augmentation.

object-detection Object Detection +1

Segment Everything Everywhere All at Once

1 code implementation NeurIPS 2023 Xueyan Zou, Jianwei Yang, Hao Zhang, Feng Li, Linjie Li, JianFeng Wang, Lijuan Wang, Jianfeng Gao, Yong Jae Lee

In SEEM, we propose a novel decoding mechanism that enables diverse prompting for all types of segmentation tasks, aiming at a universal segmentation interface that behaves like large language models (LLMs).

Image Segmentation Interactive Segmentation +4

Detection Transformer with Stable Matching

1 code implementation ICCV 2023 Shilong Liu, Tianhe Ren, Jiayu Chen, Zhaoyang Zeng, Hao Zhang, Feng Li, Hongyang Li, Jun Huang, Hang Su, Jun Zhu, Lei Zhang

We point out that the unstable matching in DETR is caused by a multi-optimization path problem, which is highlighted by the one-to-one matching design in DETR.

Exploring Data Geometry for Continual Learning

no code implementations CVPR 2023 Zhi Gao, Chen Xu, Feng Li, Yunde Jia, Mehrtash Harandi, Yuwei Wu

Our method dynamically expands the geometry of the underlying space to match growing geometric structures induced by new data, and prevents forgetting by keeping geometric structures of old data into account.

Continual Learning

Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning

1 code implementation CVPR 2023 Man Liu, Feng Li, Chunjie Zhang, Yunchao Wei, Huihui Bai, Yao Zhao

Generalized Zero-Shot Learning (GZSL) identifies unseen categories by knowledge transferred from the seen domain, relying on the intrinsic interactions between visual and semantic information.

Generalized Zero-Shot Learning

A Simple Framework for Open-Vocabulary Segmentation and Detection

2 code implementations ICCV 2023 Hao Zhang, Feng Li, Xueyan Zou, Shilong Liu, Chunyuan Li, Jianfeng Gao, Jianwei Yang, Lei Zhang

We present OpenSeeD, a simple Open-vocabulary Segmentation and Detection framework that jointly learns from different segmentation and detection datasets.

Ranked #2 on Instance Segmentation on ADE20K val (using extra training data)

Instance Segmentation Panoptic Segmentation +2

Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

4 code implementations9 Mar 2023 Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, Lei Zhang

To effectively fuse language and vision modalities, we conceptually divide a closed-set detector into three phases and propose a tight fusion solution, which includes a feature enhancer, a language-guided query selection, and a cross-modality decoder for cross-modality fusion.

 Ranked #1 on Zero-Shot Object Detection on ODinW (using extra training data)

object-detection Referring Expression +3

Introducing Depth into Transformer-based 3D Object Detection

no code implementations25 Feb 2023 Hao Zhang, Hongyang Li, Ailing Zeng, Feng Li, Shilong Liu, Xingyu Liao, Lei Zhang

To address the second issue, we introduce an auxiliary learning task called Depth-aware Negative Suppression loss.

3D Object Detection Auxiliary Learning +2

Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation

3 code implementations3 Feb 2023 Jie Yang, Ailing Zeng, Shilong Liu, Feng Li, Ruimao Zhang, Lei Zhang

This paper presents a novel end-to-end framework with Explicit box Detection for multi-person Pose estimation, called ED-Pose, where it unifies the contextual learning between human-level (global) and keypoint-level (local) information.

2D Human Pose Estimation Human Detection +3

Technical Report -- Competition Solution for Prompt Tuning using Pretrained Language Model

no code implementations13 Dec 2022 Jiang-Long Song, Wu-He Zou, Feng Li, Xiao-Lei Qin, Wei-Dong Zhang

Prompt tuning recently becomes a hot-spot in the applications of large pretrained language models on specific downstream tasks.

Few-Shot Learning Language Modelling

Integrated optimization of train timetables rescheduling and response vehicles on a disrupted metro line

no code implementations12 Dec 2022 Hui Wang, Jialin Liu, Feng Li, Hao Ji, Bin Jia, Ziyou Gao

Numerical cases of Beijing Metro Line 9 verify the efficiency and effectiveness of our proposed model, and results show that: (1) when occurring a disruption event during peak hours, the impact on the normal timetable is greater, and passengers in the direction with fewer train services are more affected; (2) if passengers stranded at the terminal stations of disruption area are not transported in time, they will rapidly increase at a speed of more than 300 passengers per minute; (3) compared with the fixed shortest path, using the response vehicles reduces the total travel time about 7%.

Bridging Component Learning with Degradation Modelling for Blind Image Super-Resolution

1 code implementation3 Dec 2022 Yixuan Wu, Feng Li, Huihui Bai, Weisi Lin, Runmin Cong, Yao Zhao

In this paper, we analyze the degradation of a high-resolution (HR) image from image intrinsic components according to a degradation-based formulation model.

Image Super-Resolution

DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding

1 code implementation28 Nov 2022 Shilong Liu, Yaoyuan Liang, Feng Li, Shijia Huang, Hao Zhang, Hang Su, Jun Zhu, Lei Zhang

As phrase extraction can be regarded as a $1$D text segmentation problem, we formulate PEG as a dual detection problem and propose a novel DQ-DETR model, which introduces dual queries to probe different features from image and text for object prediction and phrase mask prediction.

object-detection Object Detection +4

Cloud removal Using Atmosphere Model

no code implementations5 Oct 2022 Yi Guo, Feng Li, Zhuo Wang

Cloud removal is an essential task in remote sensing data analysis.

Cloud Removal

Intelligent detect for substation insulator defects based on CenterMask

no code implementations31 Aug 2022 Bo Ye, Feng Li, Mingxuan Li, Peipei Yan, Huiting Yang, Lihua Wang

Based on the end-to-end learning paradigm, this paper proposes an intelligent detection method for substation insulator defects based on CenterMask.

Defect Detection

Machine Learning Prediction of COVID-19 Severity Levels From Salivaomics Data

no code implementations15 Jul 2022 Aaron Wang, Feng Li, Samantha Chiang, Jennifer Fulcher, Otto Yang, David Wong, Fang Wei

The clinical spectrum of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the strain of coronavirus that caused the COVID-19 pandemic, is broad, extending from asymptomatic infection to severe immunopulmonary reactions that, if not categorized properly, may be life-threatening.

BIG-bench Machine Learning

Forecast combinations: an over 50-year review

no code implementations9 May 2022 Xiaoqian Wang, Rob J Hyndman, Feng Li, Yanfei Kang

Forecast combinations have flourished remarkably in the forecasting community and, in recent years, have become part of the mainstream of forecasting research and activities.

Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine Translation

no code implementations Findings (NAACL) 2022 Yukun Feng, Feng Li, Ziang Song, Boyuan Zheng, Philipp Koehn

We conduct experiments on three popular datasets for document-level machine translation and our model has an average improvement of 0. 91 s-BLEU over the sentence-level baseline.

Document Level Machine Translation Machine Translation +1

Optimal reconciliation with immutable forecasts

1 code implementation20 Apr 2022 Bohan Zhang, Yanfei Kang, Anastasios Panagiotelis, Feng Li

In this paper, we formulate reconciliation methodology that keeps forecasts of a pre-specified subset of variables unchanged or "immutable".

APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction

1 code implementation30 Mar 2022 Bencheng Yan, Pengjie Wang, Kai Zhang, Feng Li, Hongbo Deng, Jian Xu, Bo Zheng

In many web applications, deep learning-based CTR prediction models (deep CTR models for short) are widely adopted.

Click-Through Rate Prediction

DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection

14 code implementations7 Mar 2022 Hao Zhang, Feng Li, Shilong Liu, Lei Zhang, Hang Su, Jun Zhu, Lionel M. Ni, Heung-Yeung Shum

Compared to other models on the leaderboard, DINO significantly reduces its model size and pre-training data size while achieving better results.

Real-Time Object Detection

Vision-Language Intelligence: Tasks, Representation Learning, and Large Models

no code implementations3 Mar 2022 Feng Li, Hao Zhang, Yi-Fan Zhang, Shilong Liu, Jian Guo, Lionel M. Ni, Pengchuan Zhang, Lei Zhang

This survey is inspired by the remarkable progress in both computer vision and natural language processing, and recent trends shifting from single modality processing to multiple modality comprehension.

Few-Shot Learning Representation Learning

DN-DETR: Accelerate DETR Training by Introducing Query DeNoising

16 code implementations CVPR 2022 Feng Li, Hao Zhang, Shilong Liu, Jian Guo, Lionel M. Ni, Lei Zhang

Our method is universal and can be easily plugged into any DETR-like methods by adding dozens of lines of code to achieve a remarkable improvement.

Object Detection

A resource-efficient deep learning framework for low-dose brain PET image reconstruction and analysis

no code implementations14 Feb 2022 Yu Fu, Shunjie Dong, Yi Liao, Le Xue, Yuanfan Xu, Feng Li, Qianqian Yang, Tianbai Yu, Mei Tian, Cheng Zhuo

18F-fluorodeoxyglucose (18F-FDG) Positron Emission Tomography (PET) imaging usually needs a full-dose radioactive tracer to obtain satisfactory diagnostic results, which raises concerns about the potential health risks of radiation exposure, especially for pediatric patients.

Image Reconstruction

Collaborative Learning in General Graphs with Limited Memorization: Complexity, Learnability, and Reliability

no code implementations29 Jan 2022 Feng Li, Xuyang Yuan, Lina Wang, Huan Yang, Dongxiao Yu, Weifeng Lv, Xiuzhen Cheng

The efficacy of our proposed three-staged collaborative learning algorithm is finally verified by extensive experiments on both synthetic and real datasets.


DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

7 code implementations ICLR 2022 Shilong Liu, Feng Li, Hao Zhang, Xiao Yang, Xianbiao Qi, Hang Su, Jun Zhu, Lei Zhang

We present in this paper a novel query formulation using dynamic anchor boxes for DETR (DEtection TRansformer) and offer a deeper understanding of the role of queries in DETR.

Object Detection

Upright-Net: Learning Upright Orientation for 3D Point Cloud

no code implementations CVPR 2022 Xufang Pang, Feng Li, Ning Ding, Xiaopin Zhong

A mass of experiments shows that the pose of the input 3D models exerts a tremendous influence on automatic 3D shape analysis.

Encoding Spatial Distribution of Convolutional Features for Texture Representation

1 code implementation NeurIPS 2021 Yong Xu, Feng Li, Zhile Chen, Jinxiu Liang, Yuhui Quan

Existing convolutional neural networks (CNNs) often use global average pooling (GAP) to aggregate feature maps into a single representation.

Material Recognition Retrieval +1

Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning

1 code implementation10 Oct 2021 Shaohua Wu, Xudong Zhao, Tong Yu, Rongguo Zhang, Chong Shen, Hongli Liu, Feng Li, Hong Zhu, Jiangang Luo, Liang Xu, Xuanwei Zhang

With this method, Yuan 1. 0, the current largest singleton language model with 245B parameters, achieves excellent performance on thousands GPUs during training, and the state-of-the-art results on NLP tasks.

Few-Shot Learning Language Modelling +1

Generalizable Person Re-identification Without Demographics

no code implementations29 Sep 2021 Yifan Zhang, Feng Li, Zhang Zhang, Liang Wang, DaCheng Tao, Tieniu Tan

However, the convex condition of KL DRO may not hold for overparameterized neural networks, such that applying KL DRO often fails to generalize under distribution shifts in real scenarios.

Generalizable Person Re-identification

The Report on China-Spain Joint Clinical Testing for Rapid COVID-19 Risk Screening by Eye-region Manifestations

no code implementations18 Sep 2021 Yanwei Fu, Feng Li, Paula boned Fustel, Lei Zhao, Lijie Jia, Haojie Zheng, Qiang Sun, Shisong Rong, Haicheng Tang, xiangyang xue, Li Yang, Hong Li, Jiao Xie Wenxuan Wang, Yuan Li, Wei Wang, Yantao Pei, Jianmin Wang, Xiuqi Wu, Yanhua Zheng, Hongxia Tian, Mengwei Gu

The image-level performance of COVID-19 prescreening model in the China-Spain multicenter study achieved an AUC of 0. 913 (95% CI, 0. 898-0. 927), with a sensitivity of 0. 695 (95% CI, 0. 643-0. 748), a specificity of 0. 904 (95% CI, 0. 891 -0. 919), an accuracy of 0. 875(0. 861-0. 889), and a F1 of 0. 611(0. 568-0. 655).

Binary Classification Specificity

Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection

1 code implementation4 Aug 2021 Chen Zhang, Runmin Cong, Qinwei Lin, Lin Ma, Feng Li, Yao Zhao, Sam Kwong

For the cross-modality interaction in feature encoder, existing methods either indiscriminately treat RGB and depth modalities, or only habitually utilize depth cues as auxiliary information of the RGB branch.

object-detection RGB-D Salient Object Detection +1

Bayesian forecast combination using time-varying features

no code implementations4 Aug 2021 Li Li, Yanfei Kang, Feng Li

In this work, we propose a novel framework for density forecast combination by constructing time-varying weights based on time series features, which is called Feature-based Bayesian Forecasting Model Averaging (FEBAMA).

Time Series Time Series Analysis +1

Deep Texture Recognition via Exploiting Cross-Layer Statistical Self-Similarity

no code implementations CVPR 2021 Zhile Chen, Feng Li, Yuhui Quan, Yong Xu, Hui Ji

In recent years, convolutional neural networks (CNNs) have become a prominent tool for texture recognition.

Rapid COVID-19 Risk Screening by Eye-region Manifestations

no code implementations12 Jun 2021 Yanwei Fu, Lei Zhao, Haojie Zheng, Qiang Sun, Li Yang, Hong Li, Jiao Xie, xiangyang xue, Feng Li, Yuan Li, Wei Wang, Yantao Pei, Jianmin Wang, Xiuqi Wu, Yanhua Zheng, Hongxia Tian Mengwei Gu1

It is still nontrivial to develop a new fast COVID-19 screening method with the easier access and lower cost, due to the technical and cost limitations of the current testing methods in the medical resource-poor districts.


Graph Intention Network for Click-through Rate Prediction in Sponsored Search

no code implementations30 Mar 2021 Feng Li, Zhenrui Chen, Pengjie Wang, Yi Ren, Di Zhang, Xiaoyu Zhu

Moreover, it is difficult for user to jump out of their specific historical behaviors for possible interest exploration, namely weak generalization problem.

Click-Through Rate Prediction Graph Learning

Hierarchical forecasting with a top-down alignment of independent level forecasts

1 code implementation15 Mar 2021 Matthias Anderer, Feng Li

In this paper, we present a \emph{hierarchical-forecasting-with-alignment} approach that treats the bottom level forecasts as mutable to ensure higher forecasting accuracy on the upper levels of the hierarchy.

Time Series Time Series Analysis

Spectrum Sharing for 6G Integrated Satellite-Terrestrial Communication Networks Based on NOMA and Cognitive Radio

no code implementations27 Jan 2021 Xin Liu, Kwok-Yan Lam, Feng Li, Jun Zhao, Li Wang

ISTCN aims to provide high speed and pervasive network services by integrating broadband terrestrial mobile networks with satellite communication networks.


Towards Complete Scene and Regular Shape for Distortion Rectification by Curve-Aware Extrapolation

no code implementations ICCV 2021 Kang Liao, Chunyu Lin, Yunchao Wei, Feng Li, Shangrong Yang, Yao Zhao

To our knowledge, we are the first to tackle the challenging rectification via outpainting, and our curve-aware strategy can reach a rectification construction with complete content and regular shape.

Forecast with Forecasts: Diversity Matters

no code implementations3 Dec 2020 Yanfei Kang, Wei Cao, Fotios Petropoulos, Feng Li

In this work, we suggest a change of focus from the historical data to the produced forecasts to extract features.

Meta-Learning Prediction Intervals +2

A Distributed Privacy-Preserving Learning Dynamics in General Social Networks

no code implementations15 Nov 2020 Youming Tao, Shuzhen Chen, Feng Li, Dongxiao Yu, Jiguo Yu, Hao Sheng

In this paper, we study a distributed privacy-preserving learning problem in social networks with general topology.

Privacy Preserving

Learning Deep Interleaved Networks with Asymmetric Co-Attention for Image Restoration

1 code implementation29 Oct 2020 Feng Li, Runmin Cong, Huihui Bai, Yifan He, Yao Zhao, Ce Zhu

In this paper, we present a deep interleaved network (DIN) that learns how information at different states should be combined for high-quality (HQ) images reconstruction.

Deblurring Image Deblurring +2

No Perfect Outdoors: Towards A Deep Profiling of GNSS-based Location Contexts

no code implementations28 Oct 2020 Feng Li, Jin Wang, Jun Luo

On one hand, we offer a more fine-grained semantic classification than binary indoor-outdoor detection.

Networking and Internet Architecture

A New Screening Method for COVID-19 based on Ocular Feature Recognition by Machine Learning Tools

no code implementations4 Sep 2020 Yanwei Fu, Feng Li, Wenxuan Wang, Haicheng Tang, Xuelin Qian, Mengwei Gu, xiangyang xue

After more than four months study, we found that the confirmed cases of COVID-19 present the consistent ocular pathological symbols; and we propose a new screening method of analyzing the eye-region images, captured by common CCD and CMOS cameras, could reliably make a rapid risk screening of COVID-19 with very high accuracy.

BIG-bench Machine Learning Ethics +2

SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration

1 code implementation4 Aug 2020 Mengzuo Huang, Feng Li, Wuhe Zou, Weidong Zhang

Dialogue systems in open domain have achieved great success due to the easily obtained single-turn corpus and the development of deep learning, but the multi-turn scenario is still a challenge because of the frequent coreference and information omission.

 Ranked #1 on Dialogue Rewriting on Multi-Rewrite (BLEU-1 metric)

Dialogue Rewriting Text Generation

Distributed ARIMA Models for Ultra-long Time Series

1 code implementation19 Jul 2020 Xiaoqian Wang, Yanfei Kang, Rob J. Hyndman, Feng Li

Providing forecasts for ultra-long time series plays a vital role in various activities, such as investment decisions, industrial production arrangements, and farm management.

Applications Computation

Deep Interleaved Network for Image Super-Resolution With Asymmetric Co-Attention

1 code implementation24 Apr 2020 Feng Li, Runming Cong, Huihui Bai, Yifan He

Recently, Convolutional Neural Networks (CNN) based image super-resolution (SR) have shown significant success in the literature.

Image Super-Resolution

Cost-Effective Testing of a Deep Learning Model through Input Reduction

1 code implementation25 Sep 2019 Jianyi Zhou, Feng Li, Jinhao Dong, Hongyu Zhang, Dan Hao

Experiments with various DL models and datasets show that our approach can reduce the whole testing data to 4. 6\% on average, and can reliably estimate the performance of DL models.

Déjà vu: forecasting with similarity

2 code implementations31 Aug 2019 Yanfei Kang, Evangelos Spiliotis, Fotios Petropoulos, Nikolaos Athiniotis, Feng Li, Vassilios Assimakopoulos

Instead of extrapolating, the future paths of the similar reference series are aggregated and serve as the basis for the forecasts of the target series.

Methodology Applications

FFORMPP: Feature-based forecast model performance prediction

1 code implementation30 Aug 2019 Thiyanga S. Talagala, Feng Li, Yanfei Kang

We model the forecast error as a function of time series features calculated from the historical time series with an efficient Bayesian multivariate surface regression approach.


Least Squares Approximation for a Distributed System

2 code implementations14 Aug 2019 Xuening Zhu, Feng Li, Hansheng Wang

The finite sample performance and computational efficiency are further illustrated by an extensive numerical study and an airline dataset.


Que será será? The uncertainty estimation of feature-based time series forecasts

2 code implementations8 Aug 2019 Xiaoqian Wang, Yanfei Kang, Fotios Petropoulos, Feng Li

In the training part, we use a collection of time series to train a model to explore how time series features affect the interval forecasting accuracy of different forecasting methods, which makes our proposed framework interpretable in terms of the contribution of each feature to the models' uncertainty prediction.

Methodology Applications Computation

Remove Cosine Window from Correlation Filter-based Visual Trackers: When and How

1 code implementation16 May 2019 Feng Li, Xiaohe Wu, WangMeng Zuo, David Zhang, Lei Zhang

Therefore, we in this paper investigate the feasibility to remove cosine window from CF trackers with spatial regularization.

Forecasting with time series imaging

3 code implementations17 Apr 2019 Xixi Li, Yanfei Kang, Feng Li

Recently, the use of time series features for forecast model averaging has been an emerging research focus in the forecasting community.

Model Selection Time Series +1

GRATIS: GeneRAting TIme Series with diverse and controllable characteristics

5 code implementations7 Mar 2019 Yanfei Kang, Rob J. Hyndman, Feng Li

The explosion of time series data in recent years has brought a flourish of new time series analysis methods, for forecasting, clustering, classification and other tasks.

Benchmarking Clustering +3

Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking

1 code implementation CVPR 2018 Feng Li, Cheng Tian, WangMeng Zuo, Lei Zhang, Ming-Hsuan Yang

Compared with SRDCF, STRCF with hand-crafted features provides a 5 times speedup and achieves a gain of 5. 4% and 3. 6% AUC score on OTB-2015 and Temple-Color, respectively.

Visual Object Tracking Visual Tracking

Mixed-Resolution Image Representation and Compression with Convolutional Neural Networks

no code implementations2 Feb 2018 Lijun Zhao, Huihui Bai, Feng Li, Anhong Wang, Yao Zhao

Firstly, given one input image, feature description neural network (FDNN) is used to generate a new representation of this image, so that this image representation can be more efficiently compressed by standard codec, as compared to the input image.

Image Compression Quantization

A Modified Sigma-Pi-Sigma Neural Network with Adaptive Choice of Multinomials

no code implementations1 Feb 2018 Feng Li, Yan Liu, Khidir Shaib Mohamed, Wei Wu

We propose in this paper a modified Sigma-Pi-Sigma neural network (MSPSNN) with an adaptive approach to find a better multinomial for a given problem.

Extreme Learning Machine with Local Connections

no code implementations22 Jan 2018 Feng Li, Sibo Yang, Huanhuan Huang, Wei Wu

This paper is concerned with the sparsification of the input-hidden weights of ELM (Extreme Learning Machine).

Deep Models for Engagement Assessment With Scarce Label Information

no code implementations21 Oct 2016 Feng Li, Guangfan Zhang, Wei Wang, Roger Xu, Tom Schnell, Jonathan Wen, Frederic McKenzie, Jiang Li

We compared performances of the new data representations with the original EEG features for engagement assessment.

EEG Electroencephalogram (EEG)

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