Search Results for author: JunJie Huang

Found 51 papers, 29 papers with code

Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection

no code implementations CVPR 2025 Yifan Chang, JunJie Huang, XiaoFeng Wang, Yun Ye, Zhujin Liang, Yi Shan, Dalong Du, Xingang Wang

Although sparse-point methods lower computational load and maintain high accuracy in complex lane geometries, current methods fail to fully leverage the geometric structure of lanes in both lane geometry representations and model design.

3D Lane Detection Autonomous Driving

Beyond Graph Convolution: Multimodal Recommendation with Topology-aware MLPs

1 code implementation16 Dec 2024 JunJie Huang, Jiarui Qin, Yong Yu, Weinan Zhang

Given the large volume of side information from different modalities, multimodal recommender systems have become increasingly vital, as they exploit richer semantic information beyond user-item interactions.

Multimodal Recommendation

Unleashing the Potential of Multi-Channel Fusion in Retrieval for Personalized Recommendations

no code implementations21 Oct 2024 JunJie Huang, Jiarui Qin, Jianghao Lin, Ziming Feng, Yong Yu, Weinan Zhang

Despite advancements in individual retrieval methods, multi-channel fusion, the process of efficiently merging multi-channel retrieval results, remains underexplored.

Bayesian Optimization Recommendation Systems +1

Demystifying and Extracting Fault-indicating Information from Logs for Failure Diagnosis

2 code implementations20 Sep 2024 JunJie Huang, Zhihan Jiang, Jinyang Liu, Yintong Huo, Jiazhen Gu, Zhuangbin Chen, Cong Feng, Hui Dong, Zengyin Yang, Michael R. Lyu

In the second stage, LoFI leverages a pre-trained language model with a novel prompt-based tuning method to extract fine-grained information of interest from the collected logs.

Anomaly Detection Fault Diagnosis +2

Contextualized Data-Wrangling Code Generation in Computational Notebooks

1 code implementation20 Sep 2024 JunJie Huang, Daya Guo, Chenglong Wang, Jiazhen Gu, Shuai Lu, Jeevana Priya Inala, Cong Yan, Jianfeng Gao, Nan Duan, Michael R. Lyu

With CoCoMine, we construct CoCoNote, a dataset containing 58, 221 examples for Contextualized Data-wrangling Code generation in Notebooks.

Code Generation

From 2015 to 2023: How Machine Learning Aids Natural Product Analysis

no code implementations18 Jul 2024 Suwen Shi, Ziwei Huang, Xingxin Gu, Xu Lin, Chaoying Zhong, Junjie Hang, Jianli Lin, Claire Chenwen Zhong, Lin Zhang, Yu Li, JunJie Huang

In recent years, conventional chemistry techniques have faced significant challenges due to their inherent limitations, struggling to cope with the increasing complexity and volume of data generated in contemporary research endeavors.

A Comprehensive Survey on Retrieval Methods in Recommender Systems

no code implementations11 Jul 2024 JunJie Huang, Jizheng Chen, Jianghao Lin, Jiarui Qin, Ziming Feng, Weinan Zhang, Yong Yu

By detailing the retrieval stage, which is fundamental for effective recommendation, this survey aims to bridge the existing knowledge gap and serve as a cornerstone for researchers interested in optimizing this critical component of cascade recommender systems.

Benchmarking Recommendation Systems +2

ToCoAD: Two-Stage Contrastive Learning for Industrial Anomaly Detection

no code implementations1 Jul 2024 Yun Liang, Zhiguang Hu, JunJie Huang, Donglin Di, Anyang Su, Lei Fan

Current unsupervised anomaly detection approaches perform well on public datasets but struggle with specific anomaly types due to the domain gap between pre-trained feature extractors and target-specific domains.

Contrastive Learning Self-Supervised Learning +1

Recall-Augmented Ranking: Enhancing Click-Through Rate Prediction Accuracy with Cross-Stage Data

no code implementations15 Apr 2024 JunJie Huang, Guohao Cai, Jieming Zhu, Zhenhua Dong, Ruiming Tang, Weinan Zhang, Yong Yu

RAR consists of two key sub-modules, which synergistically gather information from a vast pool of look-alike users and recall items, resulting in enriched user representations.

Click-Through Rate Prediction

FaultProfIT: Hierarchical Fault Profiling of Incident Tickets in Large-scale Cloud Systems

no code implementations27 Feb 2024 JunJie Huang, Jinyang Liu, Zhuangbin Chen, Zhihan Jiang, Yichen Li, Jiazhen Gu, Cong Feng, Zengyin Yang, Yongqiang Yang, Michael R. Lyu

To date, FaultProfIT has analyzed 10, 000+ incidents from 30+ cloud services, successfully revealing several fault trends that have informed system improvements.

Contrastive Learning

Detecting As Labeling: Rethinking LiDAR-camera Fusion in 3D Object Detection

1 code implementation13 Nov 2023 JunJie Huang, Yun Ye, Zhujin Liang, Yi Shan, Dalong Du

3D object Detection with LiDAR-camera encounters overfitting in algorithm development which is derived from the violation of some fundamental rules.

3D Object Detection object-detection

Distillation Improves Visual Place Recognition for Low Quality Images

1 code implementation10 Oct 2023 Anbang Yang, Ge Jin, JunJie Huang, Yao Wang, John-Ross Rizzo, Chen Feng

Real-time visual localization often utilizes online computing, for which query images or videos are transmitted to remote servers for visual place recognition (VPR).

Knowledge Distillation Quantization +3

ReLoop2: Building Self-Adaptive Recommendation Models via Responsive Error Compensation Loop

2 code implementations15 Jun 2023 Jieming Zhu, Guohao Cai, JunJie Huang, Zhenhua Dong, Ruiming Tang, Weinan Zhang

The error memory module is designed with fast access capabilities and undergoes continual refreshing with newly observed data samples during the model serving phase to support fast model adaptation.

Recommendation Systems

Adversarial Learning Data Augmentation for Graph Contrastive Learning in Recommendation

1 code implementation5 Feb 2023 JunJie Huang, Qi Cao, Ruobing Xie, Shaoliang Zhang, Feng Xia, HuaWei Shen, Xueqi Cheng

To reduce the influence of data sparsity, Graph Contrastive Learning (GCL) is adopted in GNN-based CF methods for enhancing performance.

Contrastive Learning Data Augmentation

BEVPoolv2: A Cutting-edge Implementation of BEVDet Toward Deployment

1 code implementation30 Nov 2022 JunJie Huang, Guan Huang

We offer an example of deployment to the TensorRT backend in branch dev2. 0 and show how fast the BEVDet paradigm can be processed on it.

Imperceptible Adversarial Attack via Invertible Neural Networks

1 code implementation28 Nov 2022 Zihan Chen, Ziyue Wang, JunJie Huang, Wentao Zhao, Xiao Liu, Dejian Guan

Adding perturbations via utilizing auxiliary gradient information or discarding existing details of the benign images are two common approaches for generating adversarial examples.

Adversarial Attack

CodeExp: Explanatory Code Document Generation

1 code implementation25 Nov 2022 Haotian Cui, Chenglong Wang, JunJie Huang, Jeevana Priya Inala, Todd Mytkowicz, Bo wang, Jianfeng Gao, Nan Duan

Our experiments show that (1) our refined training dataset lets models achieve better performance in the explanation generation tasks compared to larger unrefined data (15x larger), and (2) fine-tuned models can generate well-structured long docstrings comparable to human-written ones.

Explanation Generation Text Generation

Execution-based Evaluation for Data Science Code Generation Models

1 code implementation17 Nov 2022 JunJie Huang, Chenglong Wang, Jipeng Zhang, Cong Yan, Haotian Cui, Jeevana Priya Inala, Colin Clement, Nan Duan, Jianfeng Gao

Code generation models can benefit data scientists' productivity by automatically generating code from context and text descriptions.

Code Generation Form +1

Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA

1 code implementation11 Oct 2022 JunJie Huang, Wanjun Zhong, Qian Liu, Ming Gong, Daxin Jiang, Nan Duan

However, training an effective dense table-text retriever is difficult due to the challenges of table-text discrepancy and data sparsity problem.

Open-Domain Question Answering Representation Learning +1

Understanding or Manipulation: Rethinking Online Performance Gains of Modern Recommender Systems

no code implementations11 Oct 2022 Zhengbang Zhu, Rongjun Qin, JunJie Huang, Xinyi Dai, Yang Yu, Yong Yu, Weinan Zhang

The increase in the measured performance, however, can have two possible attributions: a better understanding of user preferences, and a more proactive ability to utilize human bounded rationality to seduce user over-consumption.

Benchmarking Sequential Recommendation

WebFace260M: A Benchmark for Million-Scale Deep Face Recognition

no code implementations21 Apr 2022 Zheng Zhu, Guan Huang, Jiankang Deng, Yun Ye, JunJie Huang, Xinze Chen, Jiagang Zhu, Tian Yang, Dalong Du, Jiwen Lu, Jie zhou

For a comprehensive evaluation of face matchers, three recognition tasks are performed under standard, masked and unbiased settings, respectively.

Face Recognition

HFT: Lifting Perspective Representations via Hybrid Feature Transformation

1 code implementation11 Apr 2022 Jiayu Zou, Junrui Xiao, Zheng Zhu, JunJie Huang, Guan Huang, Dalong Du, Xingang Wang

In order to reap the benefits and avoid the drawbacks of CBFT and CFFT, we propose a novel framework with a Hybrid Feature Transformation module (HFT).

Autonomous Driving Decision Making +2

BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection

1 code implementation31 Mar 2022 JunJie Huang, Guan Huang

Single frame data contains finite information which limits the performance of the existing vision-based multi-camera 3D object detection paradigms.

3D Object Detection object-detection

PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs

1 code implementation22 Feb 2022 Yixuan He, Xitong Zhang, JunJie Huang, Benedek Rozemberczki, Mihai Cucuringu, Gesine Reinert

While many networks are signed or directed, or both, there is a lack of unified software packages on graph neural networks (GNNs) specially designed for signed and directed networks.

Time Series Time Series Analysis

Learn over Past, Evolve for Future: Search-based Time-aware Recommendation with Sequential Behavior Data

no code implementations7 Feb 2022 Jiarui Jin, Xianyu Chen, Weinan Zhang, JunJie Huang, Ziming Feng, Yong Yu

More concretely, we first design a search-based module to retrieve a user's relevant historical behaviors, which are then mixed up with her recent records to be fed into a time-aware sequential network for capturing her time-sensitive demands.

Click-Through Rate Prediction

Reasoning over Hybrid Chain for Table-and-Text Open Domain QA

no code implementations15 Jan 2022 Wanjun Zhong, JunJie Huang, Qian Liu, Ming Zhou, Jiahai Wang, Jian Yin, Nan Duan

CARP utilizes hybrid chain to model the explicit intermediate reasoning process across table and text for question answering.

Open-Domain Question Answering

Face-NMS: A Core-set Selection Approach for Efficient Face Recognition

no code implementations10 Sep 2021 Yunze Chen, JunJie Huang, Jiagang Zhu, Zheng Zhu, Tian Yang, Guan Huang, Dalong Du

The current research on this problem mainly focuses on designing an efficient Fully-connected layer (FC) to reduce GPU memory consumption caused by a large number of identities.

Face Recognition GPU +2

Single Node Injection Attack against Graph Neural Networks

1 code implementation30 Aug 2021 Shuchang Tao, Qi Cao, HuaWei Shen, JunJie Huang, Yunfan Wu, Xueqi Cheng

In this paper, we focus on an extremely limited scenario of single node injection evasion attack, i. e., the attacker is only allowed to inject one single node during the test phase to hurt GNN's performance.

Signed Bipartite Graph Neural Networks

1 code implementation22 Aug 2021 JunJie Huang, HuaWei Shen, Qi Cao, Shuchang Tao, Xueqi Cheng

Signed bipartite networks are different from classical signed networks, which contain two different node sets and signed links between two node sets.

Link Sign Prediction Network Embedding

SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation

no code implementations6 Apr 2021 Jiabin Zhang, Zheng Zhu, Jiwen Lu, JunJie Huang, Guan Huang, Jie zhou

To make a better trade-off between accuracy and efficiency, we propose a novel multi-person pose estimation framework, SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation (SIMPLE).

Human Detection Multi-Person Pose Estimation

WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition

no code implementations CVPR 2021 Zheng Zhu, Guan Huang, Jiankang Deng, Yun Ye, JunJie Huang, Xinze Chen, Jiagang Zhu, Tian Yang, Jiwen Lu, Dalong Du, Jie zhou

In this paper, we contribute a new million-scale face benchmark containing noisy 4M identities/260M faces (WebFace260M) and cleaned 2M identities/42M faces (WebFace42M) training data, as well as an elaborately designed time-constrained evaluation protocol.

 Ranked #1 on Face Verification on IJB-C (training dataset metric)

Attribute Face Recognition +1

SDGNN: Learning Node Representation for Signed Directed Networks

1 code implementation7 Jan 2021 JunJie Huang, HuaWei Shen, Liang Hou, Xueqi Cheng

Guided by related sociological theories, we propose a novel Signed Directed Graph Neural Networks model named SDGNN to learn node embeddings for signed directed networks.

Network Embedding

AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation

2 code implementations17 Aug 2020 Junjie Huang, Zheng Zhu, Guan Huang, Dalong Du

As AID successfully pushes the performance boundary of human pose estimation problem by considerable margin and sets a new state-of-the-art, we hope AID to be a regular configuration for training human pose estimators.

Multi-Person Pose Estimation

The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation

3 code implementations CVPR 2020 Junjie Huang, Zheng Zhu, Feng Guo, Guan Huang, Dalong Du

Specifically, by investigating the standard data processing in state-of-the-art approaches mainly including coordinate system transformation and keypoint format transformation (i. e., encoding and decoding), we find that the results obtained by common flipping strategy are unaligned with the original ones in inference.

Pose Estimation

Multi-Stage HRNet: Multiple Stage High-Resolution Network for Human Pose Estimation

no code implementations14 Oct 2019 Junjie Huang, Zheng Zhu, Guan Huang

Human pose estimation are of importance for visual understanding tasks such as action recognition and human-computer interaction.

Action Recognition Multi-Person Pose Estimation +1

Signed Graph Attention Networks

1 code implementation26 Jun 2019 Junjie Huang, Hua-Wei Shen, Liang Hou, Xue-Qi Cheng

We evaluate the proposed SiGAT method by applying it to the signed link prediction task.

Graph Attention Graph Neural Network +4

COS960: A Chinese Word Similarity Dataset of 960 Word Pairs

1 code implementation1 Jun 2019 Junjie Huang, Fanchao Qi, Chenghao Yang, Zhiyuan Liu, Maosong Sun

Word similarity computation is a widely recognized task in the field of lexical semantics.

POS Word Similarity

Optical Flow Based Online Moving Foreground Analysis

no code implementations18 Nov 2018 Junjie Huang, Wei Zou, Zheng Zhu, Jiagang Zhu

Obtained by moving object detection, the foreground mask result is unshaped and can not be directly used in most subsequent processes.

Clustering Moving Object Detection +2

An Efficient Optical Flow Based Motion Detection Method for Non-stationary Scenes

no code implementations18 Nov 2018 Junjie Huang, Wei Zou, Zheng Zhu, Jiagang Zhu

Real-time motion detection in non-stationary scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource.

Motion Detection Motion Detection In Non-Stationary Scenes +1

Optical Flow Based Real-time Moving Object Detection in Unconstrained Scenes

no code implementations13 Jul 2018 Junjie Huang, Wei Zou, Jiagang Zhu, Zheng Zhu

Real-time moving object detection in unconstrained scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource.

Moving Object Detection object-detection +1

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