Search Results for author: Xiaokang Yang

Found 79 papers, 29 papers with code

Layered Neighborhood Expansion for Incremental Multiple Graph Matching

1 code implementation ECCV 2020 Zixuan Chen, Zhihui Xie, Junchi Yan Yinqiang Zheng, Xiaokang Yang

In this paper, we treat the graphs as graphs on a super-graph, and propose a novel breadth first search based method for expanding the neighborhood on the super-graph for a new coming graph, such that the matching with the new graph can be efficiently performed within the constructed neighborhood.

Graph Matching

Efficient Person Search: An Anchor-Free Approach

1 code implementation1 Sep 2021 Yichao Yan, Jinpeng Li, Jie Qin, Shengcai Liao, Xiaokang Yang

Third, by investigating the advantages of both anchor-based and anchor-free models, we further augment AlignPS with an ROI-Align head, which significantly improves the robustness of re-id features while still keeping our model highly efficient.

Person Search

Learning to Track Objects from Unlabeled Videos

1 code implementation28 Aug 2021 Jilai Zheng, Chao Ma, Houwen Peng, Xiaokang Yang

In this paper, we propose to learn an Unsupervised Single Object Tracker (USOT) from scratch.

Object Discovery Optical Flow Estimation

Task-Specific Normalization for Continual Learning of Blind Image Quality Models

no code implementations28 Jul 2021 Weixia Zhang, Kede Ma, Guangtao Zhai, Xiaokang Yang

In this paper, we present a simple yet effective continual learning method for BIQA with improved quality prediction accuracy, plasticity-stability trade-off, and task-order/length robustness.

Blind Image Quality Assessment Continual Learning

PointAugmenting: Cross-Modal Augmentation for 3D Object Detection

no code implementations CVPR 2021 Chunwei Wang, Chao Ma, Ming Zhu, Xiaokang Yang

On one hand, PointAugmenting decorates point clouds with corresponding point-wise CNN features extracted by pretrained 2D detection models, and then performs 3D object detection over the decorated point clouds.

3D Object Detection Autonomous Driving +2

Exploring Visual Context for Weakly Supervised Person Search

1 code implementation19 Jun 2021 Yichao Yan, Jinpeng Li, Shengcai Liao, Jie Qin, Bingbing Ni, Xiaokang Yang, Ling Shao

We proposed the first framework to address this novel task, namely Context-Guided Person Search (CGPS), by investigating three levels of context clues (i. e., detection, memory and scene) in unconstrained natural images.

Pedestrian Detection Person Re-Identification +1

Context-Aware Image Inpainting with Learned Semantic Priors

1 code implementation14 Jun 2021 Wendong Zhang, Junwei Zhu, Ying Tai, Yunbo Wang, Wenqing Chu, Bingbing Ni, Chengjie Wang, Xiaokang Yang

Based on the semantic priors, we further propose a context-aware image inpainting model, which adaptively integrates global semantics and local features in a unified image generator.

Image Inpainting Knowledge Distillation

Making CNNs Interpretable by Building Dynamic Sequential Decision Forests with Top-down Hierarchy Learning

no code implementations5 Jun 2021 Yilin Wang, Shaozuo Yu, Xiaokang Yang, Wei Shen

In this paper, we propose a generic model transfer scheme to make Convlutional Neural Networks (CNNs) interpretable, while maintaining their high classification accuracy.

Classification

Learning Multi-Attention Context Graph for Group-Based Re-Identification

1 code implementation29 Apr 2021 Yichao Yan, Jie Qin, Bingbing Ni, Jiaxin Chen, Li Liu, Fan Zhu, Wei-Shi Zheng, Xiaokang Yang, Ling Shao

Extensive experiments on the novel dataset as well as three existing datasets clearly demonstrate the effectiveness of the proposed framework for both group-based re-id tasks.

Person Re-Identification

Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction

1 code implementation CVPR 2021 Shanyan Guan, Jingwei Xu, Yunbo Wang, Bingbing Ni, Xiaokang Yang

This paper considers a new problem of adapting a pre-trained model of human mesh reconstruction to out-of-domain streaming videos.

3D Human Pose Estimation

Learning Comprehensive Motion Representation for Action Recognition

no code implementations23 Mar 2021 Mingyu Wu, Boyuan Jiang, Donghao Luo, Junchi Yan, Yabiao Wang, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Xiaokang Yang

For action recognition learning, 2D CNN-based methods are efficient but may yield redundant features due to applying the same 2D convolution kernel to each frame.

Action Recognition

Continual Learning for Blind Image Quality Assessment

1 code implementation19 Feb 2021 Weixia Zhang, Dingquan Li, Chao Ma, Guangtao Zhai, Xiaokang Yang, Kede Ma

Specifically, based on a shared backbone network, we add a prediction head for a new dataset, and enforce a regularizer to allow all prediction heads to evolve with new data while being resistant to catastrophic forgetting of old data.

Blind Image Quality Assessment Continual Learning

Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting

no code implementations31 Jan 2021 Longyuan Li, Junchi Yan, Xiaokang Yang, Yaohui Jin

We propose a deep state space model for probabilistic time series forecasting whereby the non-linear emission model and transition model are parameterized by networks and the dependency is modeled by recurrent neural nets.

Decision Making Probabilistic Time Series Forecasting +1

Self-supervised representation learning via adaptive hard-positive mining

no code implementations1 Jan 2021 Shaofeng Zhang, Junchi Yan, Xiaokang Yang

Despite their success in perception over the last decade, deep neural networks are also known ravenous to labeled data for training, which limits their applicability to real-world problems.

Contrastive Learning Representation Learning +1

Rethinking Pseudo-labeled Sample Mining for Semi-Supervised Object Detection

no code implementations1 Jan 2021 Duo Li, Sanli Tang, Zhanzhan Cheng, ShiLiang Pu, Yi Niu, Wenming Tan, Fei Wu, Xiaokang Yang

However, the impact of the pseudo-labeled samples' quality as well as the mining strategies for high quality training sample have rarely been studied in SSL.

Object Detection Semi-Supervised Object Detection

DS-Net: Dynamic Spatiotemporal Network for Video Salient Object Detection

1 code implementation9 Dec 2020 Yuting Su, Weikang Wang, Jing Liu, Peiguang Jing, Xiaokang Yang

In this paper, we investigate the complimentary roles of spatial and temporal information and propose a novel dynamic spatiotemporal network (DS-Net) for more effective fusion of spatiotemporal information.

Optical Flow Estimation Saliency Detection +2

Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning

1 code implementation NeurIPS 2020 Runzhong Wang, Junchi Yan, Xiaokang Yang

This paper considers the setting of jointly matching and clustering multiple graphs belonging to different groups, which naturally rises in many realistic problems.

Graph Matching

Combinatorial Learning of Graph Edit Distance via Dynamic Embedding

no code implementations CVPR 2021 Runzhong Wang, Tianqi Zhang, Tianshu Yu, Junchi Yan, Xiaokang Yang

This paper presents a hybrid approach by combing the interpretability of traditional search-based techniques for producing the edit path, as well as the efficiency and adaptivity of deep embedding models to achieve a cost-effective GED solver.

ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradients Accumulation

no code implementations23 Nov 2020 Xiaoxing Wang, Xiangxiang Chu, Yuda Fan, Zhexi Zhang, Xiaolin Wei, Junchi Yan, Xiaokang Yang

Single-path based differentiable neural architecture search has great strengths for its low computational cost and memory-friendly nature.

Neural Architecture Search

Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning

no code implementations22 Nov 2020 Weixia Zhang, Chao Ma, Qi Wu, Xiaokang Yang

We then propose to recursively alternate the learning schemes of imitation and exploration to narrow the discrepancy between training and inference.

Imitation Learning Vision and Language Navigation

Hierarchical Style-based Networks for Motion Synthesis

no code implementations ECCV 2020 Jingwei Xu, Huazhe Xu, Bingbing Ni, Xiaokang Yang, Xiaolong Wang, Trevor Darrell

Generating diverse and natural human motion is one of the long-standing goals for creating intelligent characters in the animated world.

motion synthesis

Cross-Modality 3D Object Detection

no code implementations16 Aug 2020 Ming Zhu, Chao Ma, Pan Ji, Xiaokang Yang

In this paper, we focus on exploring the fusion of images and point clouds for 3D object detection in view of the complementary nature of the two modalities, i. e., images possess more semantic information while point clouds specialize in distance sensing.

3D Classification 3D Object Detection +2

Robust Tracking against Adversarial Attacks

1 code implementation ECCV 2020 Shuai Jia, Chao Ma, Yibing Song, Xiaokang Yang

On one hand, we add the temporal perturbations into the original video sequences as adversarial examples to greatly degrade the tracking performance.

Adversarial Attack

Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering

1 code implementation ECCV 2020 Ruixue Tang, Chao Ma, Wei Emma Zhang, Qi Wu, Xiaokang Yang

However, there are few works studying the data augmentation problem for VQA and none of the existing image based augmentation schemes (such as rotation and flipping) can be directly applied to VQA due to its semantic structure -- an $\langle image, question, answer\rangle$ triplet needs to be maintained correctly.

Adversarial Attack Data Augmentation +2

Collaborative Learning for Faster StyleGAN Embedding

no code implementations3 Jul 2020 Shanyan Guan, Ying Tai, Bingbing Ni, Feida Zhu, Feiyue Huang, Xiaokang Yang

The latent code of the recent popular model StyleGAN has learned disentangled representations thanks to the multi-layer style-based generator.

Video Prediction via Example Guidance

1 code implementation ICML 2020 Jingwei Xu, Huazhe Xu, Bingbing Ni, Xiaokang Yang, Trevor Darrell

In video prediction tasks, one major challenge is to capture the multi-modal nature of future contents and dynamics.

Video Prediction

Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild

1 code implementation28 May 2020 Weixia Zhang, Kede Ma, Guangtao Zhai, Xiaokang Yang

Nevertheless, due to the distributional shift between images simulated in the laboratory and captured in the wild, models trained on databases with synthetic distortions remain particularly weak at handling realistic distortions (and vice versa).

Blind Image Quality Assessment Learning-To-Rank

Permutation Matters: Anisotropic Convolutional Layer for Learning on Point Clouds

1 code implementation27 May 2020 Zhongpai Gao, Guangtao Zhai, Junchi Yan, Xiaokang Yang

Various point neural networks have been developed with isotropic filters or using weighting matrices to overcome the structure inconsistency on point clouds.

Representation Learning Semantic Segmentation

Toward Better Understanding of Saliency Prediction in Augmented 360 Degree Videos

no code implementations12 Dec 2019 Yucheng Zhu, Xiongkuo Min, Dandan Zhu, Ke Gu, Jiantao Zhou, Guangtao Zhai, Xiaokang Yang, Wenjun Zhang

The saliency annotations of head and eye movements for both original and augmented videos are collected and together constitute the ARVR dataset.

Object Recognition Optical Flow Estimation +2

Robust Invisible Hyperlinks in Physical Photographs Based on 3D Rendering Attacks

no code implementations3 Dec 2019 Jun Jia, Zhongpai Gao, Kang Chen, Menghan Hu, Guangtao Zhai, Guodong Guo, Xiaokang Yang

To train a robust decoder against the physical distortion from the real world, a distortion network based on 3D rendering is inserted between the encoder and the decoder to simulate the camera imaging process.

Decoding Spiking Mechanism with Dynamic Learning on Neuron Population

no code implementations21 Nov 2019 Zhijie Chen, Junchi Yan, Longyuan Li, Xiaokang Yang

Our model is aimed to reconstruct neuron information while inferring representations of neuron spiking states.

Deep Unsupervised Clustering with Clustered Generator Model

no code implementations19 Nov 2019 Dandan Zhu, Tian Han, Linqi Zhou, Xiaokang Yang, Ying Nian Wu

We propose the clustered generator model for clustering which contains both continuous and discrete latent variables.

Learning to Blindly Assess Image Quality in the Laboratory and Wild

1 code implementation1 Jul 2019 Weixia Zhang, Kede Ma, Guangtao Zhai, Xiaokang Yang

Computational models for blind image quality assessment (BIQA) are typically trained in well-controlled laboratory environments with limited generalizability to realistically distorted images.

Blind Image Quality Assessment Learning-To-Rank

Gated-GAN: Adversarial Gated Networks for Multi-Collection Style Transfer

2 code implementations4 Apr 2019 Xinyuan Chen, Chang Xu, Xiaokang Yang, Li Song, DaCheng Tao

We propose adversarial gated networks (Gated GAN) to transfer multiple styles in a single model.

Style Transfer

Learning Combinatorial Embedding Networks for Deep Graph Matching

1 code implementation ICCV 2019 Runzhong Wang, Junchi Yan, Xiaokang Yang

In addition with its NP-completeness nature, another important challenge is effective modeling of the node-wise and structure-wise affinity across graphs and the resulting objective, to guide the matching procedure effectively finding the true matching against noises.

Graph Embedding Graph Matching

Video Prediction via Selective Sampling

1 code implementation NeurIPS 2018 Jingwei Xu, Bingbing Ni, Xiaokang Yang

Most adversarial learning based video prediction methods suffer from image blur, since the commonly used adversarial and regression loss pair work rather in a competitive way than collaboration, yielding compromised blur effect.

Video Prediction

Correlation Propagation Networks for Scene Text Detection

no code implementations30 Sep 2018 Zichuan Liu, Guosheng Lin, Wang Ling Goh, Fayao Liu, Chunhua Shen, Xiaokang Yang

In this work, we propose a novel hybrid method for scene text detection namely Correlation Propagation Network (CPN).

Scene Text Scene Text Detection

Deep Regression Tracking with Shrinkage Loss

1 code implementation ECCV 2018 Xiankai Lu, Chao Ma, Bingbing Ni, Xiaokang Yang, Ian Reid, Ming-Hsuan Yang

Regression trackers directly learn a mapping from regularly dense samples of target objects to soft labels, which are usually generated by a Gaussian function, to estimate target positions.

Crowd Counting via Adversarial Cross-Scale Consistency Pursuit

1 code implementation CVPR 2018 Zan Shen, Yi Xu, Bingbing Ni, Minsi Wang, Jianguo Hu, Xiaokang Yang

Crowd counting or density estimation is a challenging task in computer vision due to large scale variations, perspective distortions and serious occlusions, etc.

Crowd Counting Density Estimation

Fine-Grained Video Captioning for Sports Narrative

no code implementations CVPR 2018 Huanyu Yu, Shuo Cheng, Bingbing Ni, Minsi Wang, Jian Zhang, Xiaokang Yang

First, to facilitate this novel research of fine-grained video caption, we collected a novel dataset called Fine-grained Sports Narrative dataset (FSN) that contains 2K sports videos with ground-truth narratives from YouTube. com.

Video Captioning

Multiple Granularity Group Interaction Prediction

no code implementations CVPR 2018 Taiping Yao, Minsi Wang, Bingbing Ni, Huawei Wei, Xiaokang Yang

Most human activity analysis works (i. e., recognition or prediction) only focus on a single granularity, i. e., either modelling global motion based on the coarse level movement such as human trajectories or forecasting future detailed action based on body parts’ movement such as skeleton motion.

Structure Preserving Video Prediction

no code implementations CVPR 2018 Jingwei Xu, Bingbing Ni, Zefan Li, Shuo Cheng, Xiaokang Yang

Despite recent emergence of adversarial based methods for video prediction, existing algorithms often produce unsatisfied results in image regions with rich structural information (i. e., object boundary) and detailed motion (i. e., articulated body movement).

Video Prediction

Decoupled Learning for Factorial Marked Temporal Point Processes

no code implementations21 Jan 2018 Weichang Wu, Junchi Yan, Xiaokang Yang, Hongyuan Zha

In conventional (multi-dimensional) marked temporal point process models, event is often encoded by a single discrete variable i. e. a marker.

Point Processes

Robust Visual Tracking via Hierarchical Convolutional Features

1 code implementation12 Jul 2017 Chao Ma, Jia-Bin Huang, Xiaokang Yang, Ming-Hsuan Yang

Specifically, we learn adaptive correlation filters on the outputs from each convolutional layer to encode the target appearance.

Object Recognition Visual Tracking

Terahertz Security Image Quality Assessment by No-reference Model Observers

no code implementations12 Jul 2017 Menghan Hu, Xiongkuo Min, Guangtao Zhai, Wenhan Zhu, Yucheng Zhu, Zhaodi Wang, Xiaokang Yang, Guang Tian

Subsequently, the existing no-reference IQA algorithms, which were 5 opinion-aware approaches viz., NFERM, GMLF, DIIVINE, BRISQUE and BLIINDS2, and 8 opinion-unaware approaches viz., QAC, SISBLIM, NIQE, FISBLIM, CPBD, S3 and Fish_bb, were executed for the evaluation of the THz security image quality.

Image Quality Assessment

Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking

1 code implementation7 Jul 2017 Chao Ma, Jia-Bin Huang, Xiaokang Yang, Ming-Hsuan Yang

Second, we learn a correlation filter over a feature pyramid centered at the estimated target position for predicting scale changes.

Object Tracking

Recurrent Modeling of Interaction Context for Collective Activity Recognition

no code implementations CVPR 2017 Minsi Wang, Bingbing Ni, Xiaokang Yang

However, most of the previous activity recognition methods do not offer a flexible and scalable scheme to handle the high order context modeling problem.

Group Activity Recognition

Image Matching via Loopy RNN

no code implementations10 Jun 2017 Donghao Luo, Bingbing Ni, Yichao Yan, Xiaokang Yang

Towards this end, we propose a novel loopy recurrent neural network (Loopy RNN), which is capable of aggregating relationship information of two input images in a progressive/iterative manner and outputting the consolidated matching score in the final iteration.

Depth Structure Preserving Scene Image Generation

no code implementations1 Jun 2017 Wendong Zhang, Bingbing Ni, Yichao Yan, Jingwei Xu, Xiaokang Yang

Key to automatically generate natural scene images is to properly arrange among various spatial elements, especially in the depth direction.

Image Generation Scene Generation

Predicting Human Interaction via Relative Attention Model

no code implementations26 May 2017 Yichao Yan, Bingbing Ni, Xiaokang Yang

Predicting human interaction is challenging as the on-going activity has to be inferred based on a partially observed video.

Modeling The Intensity Function Of Point Process Via Recurrent Neural Networks

no code implementations24 May 2017 Shuai Xiao, Junchi Yan, Stephen M. Chu, Xiaokang Yang, Hongyuan Zha

In this paper, we model the background by a Recurrent Neural Network (RNN) with its units aligned with time series indexes while the history effect is modeled by another RNN whose units are aligned with asynchronous events to capture the long-range dynamics.

Point Processes Time Series

Joint Modeling of Event Sequence and Time Series with Attentional Twin Recurrent Neural Networks

no code implementations24 Mar 2017 Shuai Xiao, Junchi Yan, Mehrdad Farajtabar, Le Song, Xiaokang Yang, Hongyuan Zha

A variety of real-world processes (over networks) produce sequences of data whose complex temporal dynamics need to be studied.

Point Processes Time Series

Person Re-Identification via Recurrent Feature Aggregation

1 code implementation23 Jan 2017 Yichao Yan, Bingbing Ni, Zhichao Song, Chao Ma, Yan Yan, Xiaokang Yang

We address the person re-identification problem by effectively exploiting a globally discriminative feature representation from a sequence of tracked human regions/patches.

Patch Matching Person Re-Identification

Learning a No-Reference Quality Metric for Single-Image Super-Resolution

1 code implementation18 Dec 2016 Chao Ma, Chih-Yuan Yang, Xiaokang Yang, Ming-Hsuan Yang

Numerous single-image super-resolution algorithms have been proposed in the literature, but few studies address the problem of performance evaluation based on visual perception.

Image Super-Resolution

Progressively Parsing Interactional Objects for Fine Grained Action Detection

no code implementations CVPR 2016 Bingbing Ni, Xiaokang Yang, Shenghua Gao

Fine grained video action analysis often requires reliable detection and tracking of various interacting objects and human body parts, denoted as interactional object parsing.

Action Recognition Fine-Grained Action Detection +1

Cascaded Interactional Targeting Network for Egocentric Video Analysis

no code implementations CVPR 2016 Yang Zhou, Bingbing Ni, Richang Hong, Xiaokang Yang, Qi Tian

Firstly, a novel EM-like learning framework is proposed to train the pixel-level deep convolutional neural network (DCNN) by seamlessly integrating weakly supervised data (i. e., massive bounding box annotations) with a small set of strongly supervised data (i. e., fully annotated hand segmentation maps) to achieve state-of-the-art hand segmentation performance.

Action Recognition Hand Segmentation

Factors in Finetuning Deep Model for object detection

no code implementations20 Jan 2016 Wanli Ouyang, Xiaogang Wang, Cong Zhang, Xiaokang Yang

Our analysis and empirical results show that classes with more samples have higher impact on the feature learning.

Object Detection

Hierarchical Convolutional Features for Visual Tracking

no code implementations ICCV 2015 Chao Ma, Jia-Bin Huang, Xiaokang Yang, Ming-Hsuan Yang

The outputs of the last convolutional layers encode the semantic information of targets and such representations are robust to significant appearance variations.

Object Recognition Visual Object Tracking +1

Cross-Scene Crowd Counting via Deep Convolutional Neural Networks

no code implementations CVPR 2015 Cong Zhang, Hongsheng Li, Xiaogang Wang, Xiaokang Yang

To address this problem, we propose a deep convolutional neural network (CNN) for crowd counting, and it is trained alternatively with two related learning objectives, crowd density and crowd count.

Crowd Counting

Discrete Hyper-Graph Matching

no code implementations CVPR 2015 Junchi Yan, Chao Zhang, Hongyuan Zha, Wei Liu, Xiaokang Yang, Stephen M. Chu

Evaluations on both synthetic and real-world data corroborate the efficiency of our method.

Graph Matching

Motion Part Regularization: Improving Action Recognition via Trajectory Selection

no code implementations CVPR 2015 Bingbing Ni, Pierre Moulin, Xiaokang Yang, Shuicheng Yan

Inspired by the recent advance in sentence regularization for text classification, we introduce a Motion Part Regularization framework to mining discriminative semi-local groups of dense trajectories.

Action Recognition Text Classification

Long-Term Correlation Tracking

no code implementations CVPR 2015 Chao Ma, Xiaokang Yang, Chongyang Zhang, Ming-Hsuan Yang

In this paper, we address the problem of long-term visual tracking where the target objects undergo significant appearance variation due to deformation, abrupt motion, heavy occlusion and out-of-the-view.

Visual Tracking

A General Multi-Graph Matching Approach via Graduated Consistency-regularized Boosting

no code implementations20 Feb 2015 Junchi Yan, Minsu Cho, Hongyuan Zha, Xiaokang Yang, Stephen Chu

We propose multi-graph matching methods to incorporate the two aspects by boosting the affinity score, meanwhile gradually infusing the consistency as a regularizer.

Graph Matching

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