Search Results for author: Changsheng Xu

Found 49 papers, 17 papers with code

Learning Muti-expert Distribution Calibration for Long-tailed Video Classification

no code implementations22 May 2022 Yufan Hu, Junyu Gao, Changsheng Xu

However, video data in the real world typically exhibit long-tail class distribution and imbalance, which extensively results in a model bias towards head class and leads to relatively low performance on tail class.

Classification Image Classification +1

Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning

1 code implementation19 May 2022 Yuxin Zhang, Fan Tang, WeiMing Dong, Haibin Huang, Chongyang Ma, Tong-Yee Lee, Changsheng Xu

Our framework consists of three key components, i. e., a multi-layer style projector for style code encoding, a domain enhancement module for effective learning of style distribution, and a generative network for image style transfer.

Contrastive Learning Image Stylization +1

MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering

1 code implementation5 Apr 2022 Jun Hu, Shengsheng Qian, Quan Fang, Changsheng Xu

Different from these research, we investigate the GNN-based CF from the perspective of Markov processes for distance learning with a unified framework named Markov Graph Diffusion Collaborative Filtering (MGDCF).

Collaborative Filtering Recommendation Systems

Learning Commonsense-aware Moment-Text Alignment for Fast Video Temporal Grounding

1 code implementation4 Apr 2022 Ziyue Wu, Junyu Gao, Shucheng Huang, Changsheng Xu

Then, a commonsense-aware interaction module is designed to obtain bridged visual and text features by utilizing the learned commonsense concepts.

Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization

1 code implementation31 Mar 2022 Junyu Gao, Mengyuan Chen, Changsheng Xu

We target at the task of weakly-supervised action localization (WSAL), where only video-level action labels are available during model training.

Classification Contrastive Learning +3

Dual Cluster Contrastive learning for Object Re-Identification

1 code implementation9 Dec 2021 Hantao Yao, Changsheng Xu

Unlike the individual-based updating mechanism, the centroid-based updating mechanism that applies the mean feature of each cluster to update the cluster memory can reduce the impact of individual samples.

Contrastive Learning Person Re-Identification

SSAGCN: Social Soft Attention Graph Convolution Network for Pedestrian Trajectory Prediction

no code implementations5 Dec 2021 Pei Lv, Wentong Wang, Yunxin Wang, Yuzhen Zhang, Mingliang Xu, Changsheng Xu

In detail, when modeling social interaction, we propose a new \emph{social soft attention function}, which fully considers various interaction factors among pedestrians.

Autonomous Driving Pedestrian Trajectory Prediction +1

Contrastive Adaptive Propagation Graph Neural Networks for Efficient Graph Learning

1 code implementation2 Dec 2021 Jun Hu, Shengsheng Qian, Quan Fang, Changsheng Xu

Recently the field has advanced from local propagation schemes that focus on local neighbors towards extended propagation schemes that can directly deal with extended neighbors consisting of both local and high-order neighbors.

Graph Learning Self-Supervised Learning

Weakly-Supervised Video Object Grounding via Causal Intervention

no code implementations1 Dec 2021 Wei Wang, Junyu Gao, Changsheng Xu

With this in mind, we design a unified causal framework to learn the deconfounded object-relevant association for more accurate and robust video object grounding.

Contrastive Learning

GRecX: An Efficient and Unified Benchmark for GNN-based Recommendation

1 code implementation19 Nov 2021 Desheng Cai, Jun Hu, Quan Zhao, Shengsheng Qian, Quan Fang, Changsheng Xu

In this paper, we present GRecX, an open-source TensorFlow framework for benchmarking GNN-based recommendation models in an efficient and unified way.

Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object Detection

no code implementations14 Oct 2021 Pei Lv, Suqi Hu, Tianran Hao, Haohan Ji, Lisha Cui, Haoyi Fan, Mingliang Xu, Changsheng Xu

Inspired by the habit of observing things by the human, we propose a new method by comparing the initial proposals and the extension ones to optimize those initial proposals.

Multiple Instance Learning Weakly Supervised Object Detection

Towards Predictable Feature Attribution: Revisiting and Improving Guided BackPropagation

no code implementations29 Sep 2021 Guanhua Zheng, Jitao Sang, Wang Haonan, Changsheng Xu

Recently, backpropagation(BP)-based feature attribution methods have been widely adopted to interpret the internal mechanisms of convolutional neural networks (CNNs), and expected to be human-understandable (lucidity) and faithful to decision-making processes (fidelity).

Decision Making

Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer

1 code implementation3 Aug 2021 Yifan Xu, Zhijie Zhang, Mengdan Zhang, Kekai Sheng, Ke Li, WeiMing Dong, Liqing Zhang, Changsheng Xu, Xing Sun

Vision transformers (ViTs) have recently received explosive popularity, but the huge computational cost is still a severe issue.

Image Classification

DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering

1 code implementation10 Jul 2021 Jianyu Wang, Bing-Kun Bao, Changsheng Xu

However, existing graph-based methods fail to perform multi-step reasoning well, neglecting two properties of VideoQA: (1) Even for the same video, different questions may require different amount of video clips or objects to infer the answer with relational reasoning; (2) During reasoning, appearance and motion features have complicated interdependence which are correlated and complementary to each other.

Graph Attention Question Answering +3

ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning

no code implementations CVPR 2021 Chaofan Chen, Xiaoshan Yang, Changsheng Xu, Xuhui Huang, Zhe Ma

Specifically, we first employ the comparison module to explore the pairwise sample relations to learn rich sample representations in the instance-level graph.

Few-Shot Learning

User-Guided Personalized Image Aesthetic Assessment based on Deep Reinforcement Learning

no code implementations14 Jun 2021 Pei Lv, Jianqi Fan, Xixi Nie, WeiMing Dong, Xiaoheng Jiang, Bing Zhou, Mingliang Xu, Changsheng Xu

This framework leverages user interactions to retouch and rank images for aesthetic assessment based on deep reinforcement learning (DRL), and generates personalized aesthetic distribution that is more in line with the aesthetic preferences of different users.

Image Enhancement reinforcement-learning

StyTr$^2$: Image Style Transfer with Transformers

2 code implementations30 May 2021 Yingying Deng, Fan Tang, WeiMing Dong, Chongyang Ma, Xingjia Pan, Lei Wang, Changsheng Xu

The goal of image style transfer is to render an image with artistic features guided by a style reference while maintaining the original content.

Style Transfer

Towards Corruption-Agnostic Robust Domain Adaptation

no code implementations21 Apr 2021 Yifan Xu, Kekai Sheng, WeiMing Dong, Baoyuan Wu, Changsheng Xu, Bao-Gang Hu

However, due to unpredictable corruptions (e. g., noise and blur) in real data like web images, domain adaptation methods are increasingly required to be corruption robust on target domains.

Domain Adaptation

Health Status Prediction with Local-Global Heterogeneous Behavior Graph

no code implementations23 Mar 2021 Xuan Ma, Xiaoshan Yang, Junyu Gao, Changsheng Xu

However, these data streams are multi-source and heterogeneous, containing complex temporal structures with local contextual and global temporal aspects, which makes the feature learning and data joint utilization challenging.

Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization

1 code implementation CVPR 2021 Xingjia Pan, Yingguo Gao, Zhiwen Lin, Fan Tang, WeiMing Dong, Haolei Yuan, Feiyue Huang, Changsheng Xu

Weakly supervised object localization(WSOL) remains an open problem given the deficiency of finding object extent information using a classification network.

Classification General Classification +1

Efficient Graph Deep Learning in TensorFlow with tf_geometric

1 code implementation27 Jan 2021 Jun Hu, Shengsheng Qian, Quan Fang, Youze Wang, Quan Zhao, Huaiwen Zhang, Changsheng Xu

We introduce tf_geometric, an efficient and friendly library for graph deep learning, which is compatible with both TensorFlow 1. x and 2. x.

General Classification Graph Classification +4

Active Universal Domain Adaptation

no code implementations ICCV 2021 Xinhong Ma, Junyu Gao, Changsheng Xu

This paper proposes a new paradigm for unsupervised domain adaptation, termed as Active Universal Domain Adaptation (AUDA), which removes all label set assumptions and aims for not only recognizing target samples from source classes but also inferring those from target-private classes by using active learning to annotate a small budget of target data.

Active Learning Universal Domain Adaptation +1

Fast Video Moment Retrieval

no code implementations ICCV 2021 Junyu Gao, Changsheng Xu

To tackle this issue, we replace the cross-modal interaction module with a cross-modal common space, in which moment-query alignment is learned and efficient moment search can be performed.

Moment Retrieval

Effective Label Propagation for Discriminative Semi-Supervised Domain Adaptation

no code implementations4 Dec 2020 Zhiyong Huang, Kekai Sheng, WeiMing Dong, Xing Mei, Chongyang Ma, Feiyue Huang, Dengwen Zhou, Changsheng Xu

For intra-domain propagation, we propose an effective self-training strategy to mitigate the noises in pseudo-labeled target domain data and improve the feature discriminability in the target domain.

Domain Adaptation Image Classification

Arbitrary Video Style Transfer via Multi-Channel Correlation

no code implementations17 Sep 2020 Yingying Deng, Fan Tang, Wei-Ming Dong, Haibin Huang, Chongyang Ma, Changsheng Xu

Towards this end, we propose Multi-Channel Correction network (MCCNet), which can be trained to fuse the exemplar style features and input content features for efficient style transfer while naturally maintaining the coherence of input videos.

Style Transfer Video Style Transfer

MMCGAN: Generative Adversarial Network with Explicit Manifold Prior

no code implementations18 Jun 2020 Guanhua Zheng, Jitao Sang, Changsheng Xu

Since the basic assumption of conventional manifold learning fails in case of sparse and uneven data distribution, we introduce a new target, Minimum Manifold Coding (MMC), for manifold learning to encourage simple and unfolded manifold.

Distribution Aligned Multimodal and Multi-Domain Image Stylization

no code implementations2 Jun 2020 Minxuan Lin, Fan Tang, Wei-Ming Dong, Xiao Li, Chongyang Ma, Changsheng Xu

Currently, there are few methods that can perform both multimodal and multi-domain stylization simultaneously.

Image Stylization

Attribute-Induced Bias Eliminating for Transductive Zero-Shot Learning

no code implementations31 May 2020 Hantao Yao, Shaobo Min, Yongdong Zhang, Changsheng Xu

Then, an attentional graph attribute embedding is proposed to reduce the semantic bias between seen and unseen categories, which utilizes the graph operation to capture the semantic relationship between categories.

Transfer Learning Zero-Shot Learning

Joint Person Objectness and Repulsion for Person Search

no code implementations30 May 2020 Hantao Yao, Changsheng Xu

Based on this repulsion constraint, the repulsion term is proposed to reduce the similarity of distractor images that are not most similar to the probe person.

Human Detection Person Search

Arbitrary Style Transfer via Multi-Adaptation Network

1 code implementation27 May 2020 Yingying Deng, Fan Tang, Wei-Ming Dong, Wen Sun, Feiyue Huang, Changsheng Xu

Arbitrary style transfer is a significant topic with research value and application prospect.

Disentanglement Style Transfer

Adaptive Adversarial Logits Pairing

no code implementations25 May 2020 Shangxi Wu, Jitao Sang, Kaiyuan Xu, Guanhua Zheng, Changsheng Xu

Specifically, AALP consists of an adaptive feature optimization module with Guided Dropout to systematically pursue fewer high-contribution features, and an adaptive sample weighting module by setting sample-specific training weights to balance between logits pairing loss and classification loss.

Classification General Classification +1

Dynamic Refinement Network for Oriented and Densely Packed Object Detection

1 code implementation CVPR 2020 Xingjia Pan, Yuqiang Ren, Kekai Sheng, Wei-Ming Dong, Haolei Yuan, Xiaowei Guo, Chongyang Ma, Changsheng Xu

However, the detection of oriented and densely packed objects remains challenging because of following inherent reasons: (1) receptive fields of neurons are all axis-aligned and of the same shape, whereas objects are usually of diverse shapes and align along various directions; (2) detection models are typically trained with generic knowledge and may not generalize well to handle specific objects at test time; (3) the limited dataset hinders the development on this task.

feature selection Object Detection In Aerial Images +1

Multi-Attribute Guided Painting Generation

no code implementations26 Feb 2020 Minxuan Lin, Yingying Deng, Fan Tang, Wei-Ming Dong, Changsheng Xu

Controllable painting generation plays a pivotal role in image stylization.

Image Stylization

A Generalization Theory based on Independent and Task-Identically Distributed Assumption

no code implementations28 Nov 2019 Guanhua Zheng, Jitao Sang, Houqiang Li, Jian Yu, Changsheng Xu

The derived generalization bound based on the ITID assumption identifies the significance of hypothesis invariance in guaranteeing generalization performance.

Image Classification

Time-Guided High-Order Attention Model of Longitudinal Heterogeneous Healthcare Data

no code implementations28 Nov 2019 Yi Huang, Xiaoshan Yang, Changsheng Xu

(1) It can model longitudinal heterogeneous EHRs data via capturing the 3-order correlations of different modalities and the irregular temporal impact of historical events.

Mortality Prediction

Adversarial Multimodal Network for Movie Question Answering

no code implementations24 Jun 2019 Zhaoquan Yuan, Siyuan Sun, Lixin Duan, Xiao Wu, Changsheng Xu

In AMN, as inspired by generative adversarial networks, we propose to learn multimodal feature representations by finding a more coherent subspace for video clips and the corresponding texts (e. g., subtitles and questions).

Question Answering Video Question Answering +1

Joint Pose and Expression Modeling for Facial Expression Recognition

no code implementations CVPR 2018 Feifei Zhang, Tianzhu Zhang, Qirong Mao, Changsheng Xu

First, the encoder-decoder structure of the generator can learn a generative and discriminative identity representation for face images.

Facial Expression Recognition Image Generation

Depth Information Guided Crowd Counting for Complex Crowd Scenes

no code implementations3 Mar 2018 Mingliang Xu, Zhaoyang Ge, Xiaoheng Jiang, Gaoge Cui, Pei Lv, Bing Zhou, Changsheng Xu

DigCrowd first uses the depth information of an image to segment the scene into a far-view region and a near-view region.

Crowd Counting

Understanding Deep Learning Generalization by Maximum Entropy

no code implementations ICLR 2018 Guanhua Zheng, Jitao Sang, Changsheng Xu

DNN is then regarded as approximating the feature conditions with multilayer feature learning, and proved to be a recursive solution towards maximum entropy principle.

Structural Correlation Filter for Robust Visual Tracking

no code implementations CVPR 2016 Si Liu, Tianzhu Zhang, Xiaochun Cao, Changsheng Xu

In this paper, we propose a novel structural correlation filter (SCF) model for robust visual tracking.

Visual Tracking

Structural Sparse Tracking

no code implementations CVPR 2015 Tianzhu Zhang, Si Liu, Changsheng Xu, Shuicheng Yan, Bernard Ghanem, Narendra Ahuja, Ming-Hsuan Yang

Sparse representation has been applied to visual tracking by finding the best target candidate with minimal reconstruction error by use of target templates.

Visual Tracking

Matching-CNN Meets KNN: Quasi-Parametric Human Parsing

no code implementations CVPR 2015 Si Liu, Xiaodan Liang, Luoqi Liu, Xiaohui Shen, Jianchao Yang, Changsheng Xu, Liang Lin, Xiaochun Cao, Shuicheng Yan

Under the classic K Nearest Neighbor (KNN)-based nonparametric framework, the parametric Matching Convolutional Neural Network (M-CNN) is proposed to predict the matching confidence and displacements of the best matched region in the testing image for a particular semantic region in one KNN image.

Human Parsing

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