Search Results for author: Zheng Fang

Found 48 papers, 12 papers with code

TEBNER: Domain Specific Named Entity Recognition with Type Expanded Boundary-aware Network

no code implementations EMNLP 2021 Zheng Fang, Yanan Cao, Tai Li, Ruipeng Jia, Fang Fang, Yanmin Shang, Yuhai Lu

To alleviate label scarcity in Named Entity Recognition (NER) task, distantly supervised NER methods are widely applied to automatically label data and identify entities.

named-entity-recognition Named Entity Recognition +1

SeqTrack3D: Exploring Sequence Information for Robust 3D Point Cloud Tracking

no code implementations26 Feb 2024 Yu Lin, Zhiheng Li, Yubo Cui, Zheng Fang

Most existing methods perform tracking between two consecutive frames while ignoring the motion patterns of the target over a series of frames, which would cause performance degradation in the scenes with sparse points.

3D Single Object Tracking Autonomous Driving +1

Inductive Graph Alignment Prompt: Bridging the Gap between Graph Pre-training and Inductive Fine-tuning From Spectral Perspective

no code implementations21 Feb 2024 Yuchen Yan, Peiyan Zhang, Zheng Fang, Qingqing Long

Based on the insight of graph pre-training, we propose to bridge the graph signal gap and the graph structure gap with learnable prompts in the spectral space.

General Knowledge Graph Classification

Model Composition for Multimodal Large Language Models

no code implementations20 Feb 2024 Chi Chen, Yiyang Du, Zheng Fang, Ziyue Wang, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu

In this paper, we propose a new paradigm through the model composition of existing MLLMs to create a new model that retains the modal understanding capabilities of each original model.

Multi-Agent Generative Adversarial Interactive Self-Imitation Learning for AUV Formation Control and Obstacle Avoidance

no code implementations21 Jan 2024 Zheng Fang, Tianhao Chen, Dong Jiang, Zheng Zhang, Guangliang Li

Multi-agent generative adversarial imitation learning (MAGAIL) allows multi-AUV to learn from expert demonstration instead of pre-defined reward functions, but suffers from the deficiency of requiring optimal demonstrations and not surpassing provided expert demonstrations.

Imitation Learning Multi-agent Reinforcement Learning

DevEval: Evaluating Code Generation in Practical Software Projects

no code implementations12 Jan 2024 Jia Li, Ge Li, YunFei Zhao, Yongmin Li, Zhi Jin, Hao Zhu, Huanyu Liu, Kaibo Liu, Lecheng Wang, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yihong Dong, Yuqi Zhu, Bin Gu, Mengfei Yang

Compared to previous benchmarks, DevEval aligns to practical projects in multiple dimensions, e. g., real program distributions, sufficient dependencies, and enough-scale project contexts.

Code Generation

Motion-to-Matching: A Mixed Paradigm for 3D Single Object Tracking

1 code implementation23 Aug 2023 Zhiheng Li, Yu Lin, Yubo Cui, Shuo Li, Zheng Fang

3D single object tracking with LiDAR points is an important task in the computer vision field.

3D Single Object Tracking Object Tracking

Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search

no code implementations2 Aug 2023 Kun-Peng Ning, Ming Pang, Zheng Fang, Xue Jiang, Xi-Wei Zhao, Chang-Ping Peng, Zhan-Gang Lin, Jing-He Hu, Jing-Ping Shao

To overcome this challenge, in this paper, we propose knowledge condensation (KC), a simple yet effective knowledge distillation framework to boost the classification performance of the online FastText model under strict low latency constraints.

Knowledge Distillation

STTracker: Spatio-Temporal Tracker for 3D Single Object Tracking

no code implementations30 Jun 2023 Yubo Cui, Zhiheng Li, Zheng Fang

Previous methods usually input the last two frames and use the predicted box to get the template point cloud in previous frame and the search area point cloud in the current frame respectively, then use similarity-based or motion-based methods to predict the current box.

3D Single Object Tracking Object +1

BERTTM: Leveraging Contextualized Word Embeddings from Pre-trained Language Models for Neural Topic Modeling

no code implementations16 May 2023 Zheng Fang, Yulan He, Rob Procter

Contextualized word embeddings from pre-trained language models show superiority in the ability of word sense disambiguation and prove to be effective in dealing with OOV words.

Document Classification Language Modelling +5

EV-MGRFlowNet: Motion-Guided Recurrent Network for Unsupervised Event-based Optical Flow with Hybrid Motion-Compensation Loss

no code implementations13 May 2023 Hao Zhuang, XinJie Huang, Kuanxu Hou, Delei Kong, Chenming Hu, Zheng Fang

In this paper, we propose EV-MGRFlowNet, an unsupervised event-based optical flow estimation pipeline with motion-guided recurrent networks using a hybrid motion-compensation loss.

Event-based Optical Flow Motion Compensation +1

MMF-Track: Multi-modal Multi-level Fusion for 3D Single Object Tracking

no code implementations11 May 2023 Zhiheng Li, Yubo Cui, Yu Lin, Zheng Fang

To overcome the limitations of geometry matching, we propose a Multi-modal Multi-level Fusion Tracker (MMF-Track), which exploits the image texture and geometry characteristic of point clouds to track 3D target.

3D Single Object Tracking Object Tracking

A Comprehensive Survey on Deep Graph Representation Learning

no code implementations11 Apr 2023 Wei Ju, Zheng Fang, Yiyang Gu, Zequn Liu, Qingqing Long, Ziyue Qiao, Yifang Qin, Jianhao Shen, Fang Sun, Zhiping Xiao, Junwei Yang, Jingyang Yuan, Yusheng Zhao, Yifan Wang, Xiao Luo, Ming Zhang

Graph representation learning aims to effectively encode high-dimensional sparse graph-structured data into low-dimensional dense vectors, which is a fundamental task that has been widely studied in a range of fields, including machine learning and data mining.

Graph Embedding Graph Representation Learning

A User-Centered, Interactive, Human-in-the-Loop Topic Modelling System

no code implementations4 Apr 2023 Zheng Fang, Lama Alqazlan, Du Liu, Yulan He, Rob Procter

Human-in-the-loop topic modelling incorporates users' knowledge into the modelling process, enabling them to refine the model iteratively.

Topic Models

FastRecon: Few-shot Industrial Anomaly Detection via Fast Feature Reconstruction

no code implementations ICCV 2023 Zheng Fang, Xiaoyang Wang, Haocheng Li, Jiejie Liu, Qiugui Hu, Jimin Xiao

In this paper, we propose a few-shot anomaly detection strategy that works in a low-data regime and can generalize across products at no cost.

Anomaly Detection

FE-Fusion-VPR: Attention-based Multi-Scale Network Architecture for Visual Place Recognition by Fusing Frames and Events

no code implementations22 Nov 2022 Kuanxu Hou, Delei Kong, Junjie Jiang, Hao Zhuang, XinJie Huang, Zheng Fang

To our knowledge, this is the first end-to-end network that goes beyond the existing event-based and frame-based SOTA methods to fuse frame and events directly for VPR.

Visual Place Recognition

Exploiting More Information in Sparse Point Cloud for 3D Single Object Tracking

1 code implementation2 Oct 2022 Yubo Cui, Jiayao Shan, Zuoxu Gu, Zhiheng Li, Zheng Fang

Meanwhile, the encoder applies the attention on multi-scale features to compensate for the lack of information caused by the sparsity of point cloud and the single scale of features.

3D Single Object Tracking Object +1

Real-time 3D Single Object Tracking with Transformer

1 code implementation2 Sep 2022 Jiayao Shan, Sifan Zhou, Yubo Cui, Zheng Fang

PTT module in the voting stage could model the interactions among point patches, which learns context-dependent features.

3D Single Object Tracking Autonomous Driving +2

A New Adjacency Matrix Configuration in GCN-based Models for Skeleton-based Action Recognition

no code implementations29 Jun 2022 Zheng Fang, Xiongwei Zhang, Tieyong Cao, Yunfei Zheng, Meng Sun

Comprehensive experimental results and analysis reveals that 1) the most widely used human natural skeleton structure adjacency matrix is unsuitable in skeleton-based action recognition; 2) The proposed adjacency matrix is superior in model performance, noise robustness and transferability.

Action Recognition Skeleton Based Action Recognition

Image Augmentation Based Momentum Memory Intrinsic Reward for Sparse Reward Visual Scenes

no code implementations19 May 2022 Zheng Fang, Biao Zhao, Guizhong Liu

For visual representation, a representation driven by a combination of the imageaugmented forward dynamics and the reward is acquired.

Image Augmentation Representation Learning +1

Disentangled Learning of Stance and Aspect Topics for Vaccine Attitude Detection in Social Media

1 code implementation NAACL 2022 Lixing Zhu, Zheng Fang, Gabriele Pergola, Rob Procter, Yulan He

Building models to detect vaccine attitudes on social media is challenging because of the composite, often intricate aspects involved, and the limited availability of annotated data.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1

3D Object Tracking with Transformer

1 code implementation28 Oct 2021 Yubo Cui, Zheng Fang, Jiayao Shan, Zuoxu Gu, Sifan Zhou

By using cross-attention, the transformer decoder fuses features and includes more target cues into the current point cloud feature to compute the region attentions, which makes the similarity computing more efficient.

3D Object Tracking Object +1

3D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloud

no code implementations12 Aug 2021 Zheng Fang, Sifan Zhou, Yubo Cui, Sebastian Scherer

Then, to fuse the information of features in the two branches and obtain their similarity, we propose two cross correlation modules, named Pointcloud-wise and Point-wise respectively.

3D Single Object Tracking Object +2

Deep Differential Amplifier for Extractive Summarization

no code implementations ACL 2021 Ruipeng Jia, Yanan Cao, Fang Fang, Yuchen Zhou, Zheng Fang, Yanbing Liu, Shi Wang

In this paper, we conceptualize the single-document extractive summarization as a rebalance problem and present a deep differential amplifier framework.

Extractive Summarization imbalanced classification +1

Implementing an Improved Test of Matrix Rank in Stata

no code implementations1 Aug 2021 Qihui Chen, Zheng Fang, Xun Huang

We develop a Stata command, bootranktest, for implementing the matrix rank test of Chen and Fang (2019) in linear instrumental variable regression models.

regression Test +1

A Unifying Framework for Testing Shape Restrictions

no code implementations26 Jul 2021 Zheng Fang

This paper makes the following original contributions.


Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting

1 code implementation24 Jun 2021 Zheng Fang, Qingqing Long, Guojie Song, Kunqing Xie

However, the representation ability of such models is limited due to: (1) shallow GNNs are incapable to capture long-range spatial correlations, (2) only spatial connections are considered and a mass of semantic connections are ignored, which are of great importance for a comprehensive understanding of traffic networks.

Traffic Prediction

NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection

1 code implementation4 Jun 2021 Zekun Luo, Zheng Fang, Sixiao Zheng, Yabiao Wang, Yanwei Fu

Non-Maximum Suppression (NMS) is essential for object detection and affects the evaluation results by incorporating False Positives (FP) and False Negatives (FN), especially in crowd occlusion scenes.

object-detection Object Detection +1

A Query-Driven Topic Model

no code implementations Findings (ACL) 2021 Zheng Fang, Yulan He, Rob Procter

Topic modeling is an unsupervised method for revealing the hidden semantic structure of a corpus.

Topic Models

Improved Signed Distance Function for 2D Real-time SLAM and Accurate Localization

no code implementations20 Jan 2021 Xingyin Fu, Zheng Fang, Xizhen Xiao, Yijia He, Xiao Liu

In this paper, we propose an improved Signed Distance Function (SDF) for both 2D SLAM and pure localization to improve the accuracy of mapping and localization.

Pose Estimation

TSSRGCN: Temporal Spectral Spatial Retrieval Graph Convolutional Network for Traffic Flow Forecasting

no code implementations30 Nov 2020 Xu Chen, Yuanxing Zhang, Lun Du, Zheng Fang, Yi Ren, Kaigui Bian, Kunqing Xie

Further analysis indicates that the locality and globality of the traffic networks are critical to traffic flow prediction and the proposed TSSRGCN model can adapt to the various temporal traffic patterns.


Event-VPR: End-to-End Weakly Supervised Network Architecture for Event-based Visual Place Recognition

no code implementations6 Nov 2020 Delei Kong, Zheng Fang, Haojia Li, Kuanxu Hou, Sonya Coleman, Dermot Kerr

In this paper, we propose an end-to-end visual place recognition network for event cameras, which can achieve good place recognition performance in challenging environments.

Visual Place Recognition

Inference for Large-Scale Linear Systems with Known Coefficients

no code implementations18 Sep 2020 Zheng Fang, Andres Santos, Azeem M. Shaikh, Alexander Torgovitsky

This paper considers the problem of testing whether there exists a non-negative solution to a possibly under-determined system of linear equations with known coefficients.

Discrete Choice Models Test

A Projection Framework for Testing Shape Restrictions That Form Convex Cones

no code implementations17 Oct 2019 Zheng Fang, Juwon Seo

Based on a monotonicity property afforded by such a geometric structure, we construct a bootstrap procedure that, unlike many studies in nonstandard settings, dispenses with estimation of local parameter spaces, and the critical values are obtained in a way as simple as computing the test statistic.

Test valid

DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image

2 code implementations25 Mar 2019 Pengfei Yao, Zheng Fang, Fan Wu, Yao Feng, Jiwei Li

Recovering 3D human body shape and pose from 2D images is a challenging task due to high complexity and flexibility of human body, and relatively less 3D labeled data.

Machine Learning of Time Series Using Time-delay Embedding and Precision Annealing

no code implementations12 Feb 2019 Alexander J. A. Ty, Zheng Fang, Rivver A. Gonzalez, Paul J. Rozdeba, Henry D. I. Abarbanel

We proceed from a scalar time series $s(t_n); t_n = t_0 + n \Delta t$ and using methods of nonlinear time series analysis show how to produce a $D_E > 1$ dimensional time delay embedding space in which the time series has no false neighbors as does the observed $s(t_n)$ time series.

BIG-bench Machine Learning Time Series +1

Parallel and Scalable Heat Methods for Geodesic Distance Computation

1 code implementation14 Dec 2018 Jiong Tao, Juyong Zhang, Bailin Deng, Zheng Fang, Yue Peng, Ying He

In this paper, we propose a parallel and scalable approach for geodesic distance computation on triangle meshes.


RGB-D SLAM in Dynamic Environments Using Point Correlations

no code implementations8 Nov 2018 Weichen Dai, Yu Zhang, Ping Li, Zheng Fang, Sebastian Scherer

This method utilizes the correlation between map points to separate points that are part of the static scene and points that are part of different moving objects into different groups.

Motion Estimation Simultaneous Localization and Mapping

Efficient Image Categorization with Sparse Fisher Vector

no code implementations15 Oct 2014 Xiankai Lu, Zheng Fang, Tao Xu, Haiting Zhang, Hongya Tuo

In object recognition, Fisher vector (FV) representation is one of the state-of-art image representations ways at the expense of dense, high dimensional features and increased computation time.

Image Categorization Object Recognition

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