Search Results for author: Le Wang

Found 53 papers, 18 papers with code

Merging Parameter Estimation and Classification Using LASSO

no code implementations6 May 2024 Le Wang, Ying Wang, Yu Qiu, Mian Li, Håkan Hjalmarsson

There may be sensors irrelevant for the estimation as well as sensors for which the information is very poor.

Classification

Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection

1 code implementation3 May 2024 Canhui Tang, Sanping Zhou, Yizhe Li, Yonghao Dong, Le Wang

The success of knowledge distillation mainly relies on how to keep the feature discrepancy between the teacher and student model, in which it assumes that: (1) the teacher model can jointly represent two different distributions for the normal and abnormal patterns, while (2) the student model can only reconstruct the normal distribution.

Anomaly Detection Attribute +1

Learning Discriminative Spatio-temporal Representations for Semi-supervised Action Recognition

no code implementations25 Apr 2024 Yu Wang, Sanping Zhou, Kun Xia, Le Wang

Semi-supervised action recognition aims to improve spatio-temporal reasoning ability with a few labeled data in conjunction with a large amount of unlabeled data.

Action Recognition Contrastive Learning

Robust Noisy Label Learning via Two-Stream Sample Distillation

no code implementations16 Apr 2024 Sihan Bai, Sanping Zhou, Zheng Qin, Le Wang, Nanning Zheng

Noisy label learning aims to learn robust networks under the supervision of noisy labels, which plays a critical role in deep learning.

Boosting Semi-Supervised Temporal Action Localization by Learning from Non-Target Classes

no code implementations17 Mar 2024 Kun Xia, Le Wang, Sanping Zhou, Gang Hua, Wei Tang

To this end, we first devise innovative strategies to adaptively select high-quality positive and negative classes from the label space, by modeling both the confidence and rank of a class in relation to those of the target class.

Temporal Action Localization

Recurrent Aligned Network for Generalized Pedestrian Trajectory Prediction

no code implementations9 Mar 2024 Yonghao Dong, Le Wang, Sanping Zhou, Gang Hua, Changyin Sun

Previous studies have tried to tackle this problem by leveraging a portion of the trajectory data from the target domain to adapt the model.

Domain Adaptation Pedestrian Trajectory Prediction +1

Sparse Pedestrian Character Learning for Trajectory Prediction

no code implementations27 Nov 2023 Yonghao Dong, Le Wang, Sanpin Zhou, Gang Hua, Changyin Sun

Specifically, TSNet learns the negative-removed characters in the sparse character representation stream to improve the trajectory embedding obtained in the trajectory representation stream.

Autonomous Driving Pedestrian Trajectory Prediction +1

Single-Shot and Multi-Shot Feature Learning for Multi-Object Tracking

no code implementations17 Nov 2023 Yizhe Li, Sanping Zhou, Zheng Qin, Le Wang, Jinjun Wang, Nanning Zheng

In this paper, we propose a simple yet effective two-stage feature learning paradigm to jointly learn single-shot and multi-shot features for different targets, so as to achieve robust data association in the tracking process.

Multi-Object Tracking

Designing a Better Asymmetric VQGAN for StableDiffusion

2 code implementations7 Jun 2023 Zixin Zhu, Xuelu Feng, Dongdong Chen, Jianmin Bao, Le Wang, Yinpeng Chen, Lu Yuan, Gang Hua

The training cost of our asymmetric VQGAN is cheap, and we only need to retrain a new asymmetric decoder while keeping the vanilla VQGAN encoder and StableDiffusion unchanged.

Decoder Image Inpainting

MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking

no code implementations CVPR 2023 Zheng Qin, Sanping Zhou, Le Wang, Jinghai Duan, Gang Hua, Wei Tang

For dense crowds, we design a novel Interaction Module to learn interaction-aware motions from short-term trajectories, which can estimate the complex movement of each target.

motion prediction Multi-Object Tracking

Parallel Attention Interaction Network for Few-Shot Skeleton-Based Action Recognition

no code implementations ICCV 2023 Xingyu Liu, Sanping Zhou, Le Wang, Gang Hua

Learning discriminative features from very few labeled samples to identify novel classes has received increasing attention in skeleton-based action recognition.

Action Recognition Skeleton Based Action Recognition

Sparse Instance Conditioned Multimodal Trajectory Prediction

no code implementations ICCV 2023 Yonghao Dong, Le Wang, Sanping Zhou, Gang Hua

Specifically, SICNet learns comprehensive sparse instances, i. e., representative points of the future trajectory, through a mask generated by a long short-term memory encoder and uses the memory mechanism to store and retrieve such sparse instances.

Future prediction Pedestrian Trajectory Prediction +1

Learning from Noisy Pseudo Labels for Semi-Supervised Temporal Action Localization

1 code implementation ICCV 2023 Kun Xia, Le Wang, Sanping Zhou, Gang Hua, Wei Tang

To this end, we propose a unified framework, termed Noisy Pseudo-Label Learning, to handle both location biases and category errors.

Pseudo Label Temporal Action Localization

Exploring Discrete Diffusion Models for Image Captioning

1 code implementation21 Nov 2022 Zixin Zhu, Yixuan Wei, JianFeng Wang, Zhe Gan, Zheng Zhang, Le Wang, Gang Hua, Lijuan Wang, Zicheng Liu, Han Hu

The image captioning task is typically realized by an auto-regressive method that decodes the text tokens one by one.

Image Captioning Image Generation

Physical Logic Enhanced Network for Small-Sample Bi-Layer Metallic Tubes Bending Springback Prediction

no code implementations20 Sep 2022 Chang Sun, Zili Wang, Shuyou Zhang, Le Wang, Jianrong Tan

In the second stage, under the physical logic, the PE-NET is assembled by ES-NET and SP-NET and then fine-tuned with the small sample BMT dataset and composite loss function.

Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization

no code implementations CVPR 2022 Kun Xia, Le Wang, Sanping Zhou, Nanning Zheng, Wei Tang

The main challenge of Temporal Action Localization is to retrieve subtle human actions from various co-occurring ingredients, e. g., context and background, in an untrimmed video.

Temporal Action Localization

Improving robustness of language models from a geometry-aware perspective

no code implementations Findings (ACL) 2022 Bin Zhu, Zhaoquan Gu, Le Wang, Jinyin Chen, Qi Xuan

On top of FADA, we propose geometry-aware adversarial training (GAT) to perform adversarial training on friendly adversarial data so that we can save a large number of search steps.

Data Augmentation

Progressive Backdoor Erasing via connecting Backdoor and Adversarial Attacks

no code implementations CVPR 2023 Bingxu Mu, Zhenxing Niu, Le Wang, Xue Wang, Rong Jin, Gang Hua

Deep neural networks (DNNs) are known to be vulnerable to both backdoor attacks as well as adversarial attacks.

backdoor defense

Diffractive deep neural network based adaptive optics scheme for vortex beam in oceanic turbulence

no code implementations6 Feb 2022 Haichao Zhan, Le Wang, Wennai Wang, Shengmei Zhao

The intensity pattern of the distorted vortex beam obtained in the experiment is input to the DDNN model, and the predicted phase screen can be used to compensate the distortion in real time.

TREATED:Towards Universal Defense against Textual Adversarial Attacks

no code implementations13 Sep 2021 Bin Zhu, Zhaoquan Gu, Le Wang, Zhihong Tian

Recent work shows that deep neural networks are vulnerable to adversarial examples.

Adversarial Defense

GeneAnnotator: A Semi-automatic Annotation Tool for Visual Scene Graph

1 code implementation6 Sep 2021 Zhixuan Zhang, Chi Zhang, Zhenning Niu, Le Wang, Yuehu Liu

In this manuscript, we introduce a semi-automatic scene graph annotation tool for images, the GeneAnnotator.

Graph Generation Graph Learning +3

Unified Regularity Measures for Sample-wise Learning and Generalization

no code implementations9 Aug 2021 Chi Zhang, Xiaoning Ma, Yu Liu, Le Wang, Yuanqi SU, Yuehu Liu

Fundamental machine learning theory shows that different samples contribute unequally both in learning and testing processes.

Learning Theory Memorization

Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction

1 code implementation ICCV 2021 Fang Zheng, Le Wang, Sanping Zhou, Wei Tang, Zhenxing Niu, Nanning Zheng, Gang Hua

Specifically, the proposed unlimited neighborhood interaction module generates the fused-features of all agents involved in an interaction simultaneously, which is adaptive to any number of agents and any range of interaction area.

Graph Attention Trajectory Prediction

Two-Stream Consensus Network: Submission to HACS Challenge 2021 Weakly-Supervised Learning Track

no code implementations21 Jun 2021 Yuanhao Zhai, Le Wang, David Doermann, Junsong Yuan

The base model training encourages the model to predict reliable predictions based on single modality (i. e., RGB or optical flow), based on the fusion of which a pseudo ground truth is generated and in turn used as supervision to train the base models.

Optical Flow Estimation Weakly-supervised Learning +2

SGCN: Sparse Graph Convolution Network for Pedestrian Trajectory Prediction

no code implementations CVPR 2021 Liushuai Shi, Le Wang, Chengjiang Long, Sanping Zhou, Mo Zhou, Zhenxing Niu, Gang Hua

Specifically, the SGCN explicitly models the sparse directed interaction with a sparse directed spatial graph to capture adaptive interaction pedestrians.

Pedestrian Trajectory Prediction Trajectory Prediction

Adversarial Attack and Defense in Deep Ranking

1 code implementation7 Jun 2021 Mo Zhou, Le Wang, Zhenxing Niu, Qilin Zhang, Nanning Zheng, Gang Hua

In this paper, we propose two attacks against deep ranking systems, i. e., Candidate Attack and Query Attack, that can raise or lower the rank of chosen candidates by adversarial perturbations.

Adversarial Attack Adversarial Robustness

Video Imprint

no code implementations7 Jun 2021 Zhanning Gao, Le Wang, Nebojsa Jojic, Zhenxing Niu, Nanning Zheng, Gang Hua

In the proposed framework, a dedicated feature alignment module is incorporated for redundancy removal across frames to produce the tensor representation, i. e., the video imprint.

Language Modelling Retrieval

SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction

4 code implementations4 Apr 2021 Liushuai Shi, Le Wang, Chengjiang Long, Sanping Zhou, Mo Zhou, Zhenxing Niu, Gang Hua

Meanwhile, we use a sparse directed temporal graph to model the motion tendency, thus to facilitate the prediction based on the observed direction.

Pedestrian Trajectory Prediction Trajectory Prediction

Density-aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement

no code implementations11 Mar 2021 Chi Zhang, Zihang Lin, Liheng Xu, Zongliang Li, Wei Tang, Yuehu Liu, Gaofeng Meng, Le Wang, Li Li

The key procedure of haze image translation through adversarial training lies in the disentanglement between the feature only involved in haze synthesis, i. e. style feature, and the feature representing the invariant semantic content, i. e. content feature.

Disentanglement Image Generation +1

Practical Relative Order Attack in Deep Ranking

2 code implementations ICCV 2021 Mo Zhou, Le Wang, Zhenxing Niu, Qilin Zhang, Yinghui Xu, Nanning Zheng, Gang Hua

In this paper, we formulate a new adversarial attack against deep ranking systems, i. e., the Order Attack, which covertly alters the relative order among a selected set of candidates according to an attacker-specified permutation, with limited interference to other unrelated candidates.

Adversarial Attack

Probing quasi-long-range ordering by magnetostriction in monolayer CoPS3

no code implementations4 Jan 2021 Qiye Liu, Le Wang, Ying Fu, Xi Zhang, Lianglong Huang, Huimin Su, Junhao Lin, Xiaobin Chen, Dapeng Yu, Xiaodong Cui, Jia-Wei Mei, Jun-Feng Dai

Mermin-Wagner-Coleman theorem predicts no long-range magnetic order at finite temperature in the two-dimensional (2D) isotropic systems, but a quasi-long-range order with a divergent correlation length at the Kosterlitz-Thouless (KT) transition for planar magnets.

Mesoscale and Nanoscale Physics

Practical Order Attack in Deep Ranking

no code implementations1 Jan 2021 Mo Zhou, Le Wang, Zhenxing Niu, Qilin Zhang, Xu Yinghui, Nanning Zheng, Gang Hua

The objective of this paper is to formalize and practically implement a new adversarial attack against deep ranking systems, i. e., the Order Attack, which covertly alters the relative order of a selected set of candidates according to a permutation vector predefined by the attacker, with only limited interference to other unrelated candidates.

Adversarial Attack Image Retrieval

The Unreasonable Effectiveness of the Class-reversed Sampling in Tail Sample Memorization

no code implementations1 Jan 2021 Benyi Hu, Chi Zhang, Yuehu Liu, Le Wang, Li Liu

Long-tailed visual class recognition poses significant challenges to traditional machine learning and emerging deep networks due to its inherent class imbalance.

Memorization

Meta Corrupted Pixels Mining for Medical Image Segmentation

no code implementations7 Jul 2020 Jixin Wang, Sanping Zhou, Chaowei Fang, Le Wang, Jinjun Wang

However the training of deep neural network requires a large amount of samples with high-quality annotations.

Image Segmentation Medical Image Segmentation +2

Ghost Handwritten Digit Recognition based on Deep Learning

no code implementations5 Apr 2020 Xing He, Shengmei Zhao, Le Wang

We present a ghost handwritten digit recognition method for the unknown handwritten digits based on ghost imaging (GI) with deep neural network, where a few detection signals from the bucket detector, generated by the Cosine Transform speckle, are used as the characteristic information and the input of the designed deep neural network (DNN), and the classification is designed as the output of the DNN.

Handwritten Digit Recognition

Adversarial Ranking Attack and Defense

3 code implementations ECCV 2020 Mo Zhou, Zhenxing Niu, Le Wang, Qilin Zhang, Gang Hua

In this paper, we propose two attacks against deep ranking systems, i. e., Candidate Attack and Query Attack, that can raise or lower the rank of chosen candidates by adversarial perturbations.

Adversarial Attack Image Retrieval

Ladder Loss for Coherent Visual-Semantic Embedding

2 code implementations18 Nov 2019 Mo Zhou, Zhenxing Niu, Le Wang, Zhanning Gao, Qilin Zhang, Gang Hua

For visual-semantic embedding, the existing methods normally treat the relevance between queries and candidates in a bipolar way -- relevant or irrelevant, and all "irrelevant" candidates are uniformly pushed away from the query by an equal margin in the embedding space, regardless of their various proximity to the query.

Retrieval

Bimodal Stereo: Joint Shape and Pose Estimation from Color-Depth Image Pair

no code implementations16 May 2019 Chi Zhang, Yuehu Liu, Ying Wu, Qilin Zhang, Le Wang

In the pipeline, the estimated shape is refined by the shape prior from the given depth map under the estimated pose.

Pose Estimation

NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval

1 code implementation EMNLP 2018 Canjia Li, Yingfei Sun, Ben He, Le Wang, Kai Hui, Andrew Yates, Le Sun, Jungang Xu

Pseudo-relevance feedback (PRF) is commonly used to boost the performance of traditional information retrieval (IR) models by using top-ranked documents to identify and weight new query terms, thereby reducing the effect of query-document vocabulary mismatches.

Ad-Hoc Information Retrieval Information Retrieval +1

Attention-based Temporal Weighted Convolutional Neural Network for Action Recognition

no code implementations19 Mar 2018 Jinliang Zang, Le Wang, Ziyi Liu, Qilin Zhang, Zhenxing Niu, Gang Hua, Nanning Zheng

Research in human action recognition has accelerated significantly since the introduction of powerful machine learning tools such as Convolutional Neural Networks (CNNs).

Action Recognition Temporal Action Localization

Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding

no code implementations ICCV 2017 Zhenxing Niu, Mo Zhou, Le Wang, Xinbo Gao, Gang Hua

We address the problem of dense visual-semantic embedding that maps not only full sentences and whole images but also phrases within sentences and salient regions within images into a multimodal embedding space.

Sentence

Ordinal Regression With Multiple Output CNN for Age Estimation

no code implementations CVPR 2016 Zhenxing Niu, Mo Zhou, Le Wang, Xinbo Gao, Gang Hua

To address the non-stationary property of aging patterns, age estimation can be cast as an ordinal regression problem.

Age Estimation Binary Classification +3

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