Search Results for author: xiangyang xue

Found 92 papers, 34 papers with code

Local Slot Attention for Vision-and-Language Navigation

no code implementations17 Jun 2022 Yifeng Zhuang, Qiang Sun, Yanwei Fu, Lifeng Chen, xiangyang xue

Since the attention mechanism in the transformer architecture can better integrate inter- and intra-modal information of vision and language.

Natural Language Processing Vision and Language Navigation

I Know What You Draw: Learning Grasp Detection Conditioned on a Few Freehand Sketches

no code implementations9 May 2022 Haitao Lin, Chilam Cheang, Yanwei Fu, xiangyang xue

The physical robot experiments confirm the utility of our method in object-cluttered scenes.

Density-preserving Deep Point Cloud Compression

no code implementations CVPR 2022 Yun He, Xinlin Ren, Danhang Tang, yinda zhang, xiangyang xue, Yanwei Fu

To address this, we propose a novel deep point cloud compression method that preserves local density information.

One-shot Federated Learning without Server-side Training

no code implementations26 Apr 2022 Shangchao Su, Bin Li, xiangyang xue

Federated Learning (FL) has recently made significant progress as a new machine learning paradigm for privacy protection.

Federated Learning Knowledge Distillation

Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Images

no code implementations21 Apr 2022 Chao Wen, yinda zhang, Chenjie Cao, Zhuwen Li, xiangyang xue, Yanwei Fu

We study the problem of shape generation in 3D mesh representation from a small number of color images with or without camera poses.

DST: Dynamic Substitute Training for Data-free Black-box Attack

no code implementations CVPR 2022 Wenxuan Wang, Xuelin Qian, Yanwei Fu, xiangyang xue

With the wide applications of deep neural network models in various computer vision tasks, more and more works study the model vulnerability to adversarial examples.

Knowledge Distillation

ImpDet: Exploring Implicit Fields for 3D Object Detection

no code implementations31 Mar 2022 Xuelin Qian, Li Wang, Yi Zhu, Li Zhang, Yanwei Fu, xiangyang xue

Conventional 3D object detection approaches concentrate on bounding boxes representation learning with several parameters, i. e., localization, dimension, and orientation.

3D Object Detection object-detection +1

QS-Craft: Learning to Quantize, Scrabble and Craft for Conditional Human Motion Animation

no code implementations22 Mar 2022 Yuxin Hong, Xuelin Qian, Simian Luo, xiangyang xue, Yanwei Fu

To this end, this paper proposes a novel model of learning to Quantize, Scrabble, and Craft (QS-Craft) for conditional human motion animation.

H4D: Human 4D Modeling by Learning Neural Compositional Representation

no code implementations CVPR 2022 Boyan Jiang, yinda zhang, Xingkui Wei, xiangyang xue, Yanwei Fu

A simple yet effective linear motion model is proposed to provide a rough and regularized motion estimation, followed by per-frame compensation for pose and geometry details with the residual encoded in the auxiliary code.

3D Reconstruction Future prediction +2

Compositional Scene Representation Learning via Reconstruction: A Survey

no code implementations15 Feb 2022 Jinyang Yuan, Tonglin Chen, Bin Li, xiangyang xue

Visual scene representation learning is an important research problem in the field of computer vision.

Representation Learning

Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study

1 code implementation30 Dec 2021 Jingye Chen, Haiyang Yu, jianqi ma, Mengnan Guan, Xixi Xu, Xiaocong Wang, Shaobo Qu, Bin Li, xiangyang xue

Based on our observations, we attribute the scarce attention on Chinese text recognition to the lack of reasonable dataset construction standards, unified evaluation methods, and results of the existing baselines.

Text Classification

Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints

no code implementations7 Dec 2021 Jinyang Yuan, Bin Li, xiangyang xue

When observing a visual scene that contains multiple objects from multiple viewpoints, humans are able to perceive the scene in a compositional way from each viewpoint, while achieving the so-called "object constancy" across different viewpoints, even though the exact viewpoints are untold.

SGM3D: Stereo Guided Monocular 3D Object Detection

1 code implementation3 Dec 2021 Zheyuan Zhou, Liang Du, Xiaoqing Ye, Zhikang Zou, Xiao Tan, Li Zhang, xiangyang xue, Jianfeng Feng

Monocular 3D object detection aims to predict the object location, dimension and orientation in 3D space alongside the object category given only a monocular image.

Autonomous Driving Depth Estimation +3

The Report on China-Spain Joint Clinical Testing for Rapid COVID-19 Risk Screening by Eye-region Manifestations

no code implementations18 Sep 2021 Yanwei Fu, Feng Li, Paula boned Fustel, Lei Zhao, Lijie Jia, Haojie Zheng, Qiang Sun, Shisong Rong, Haicheng Tang, xiangyang xue, Li Yang, Hong Li, Jiao Xie Wenxuan Wang, Yuan Li, Wei Wang, Yantao Pei, Jianmin Wang, Xiuqi Wu, Yanhua Zheng, Hongxia Tian, Mengwei Gu

The image-level performance of COVID-19 prescreening model in the China-Spain multicenter study achieved an AUC of 0. 913 (95% CI, 0. 898-0. 927), with a sensitivity of 0. 695 (95% CI, 0. 643-0. 748), a specificity of 0. 904 (95% CI, 0. 891 -0. 919), an accuracy of 0. 875(0. 861-0. 889), and a F1 of 0. 611(0. 568-0. 655).

SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimation

no code implementations CVPR 2022 Haitao Lin, Zichang Liu, Chilam Cheang, Yanwei Fu, Guodong Guo, xiangyang xue

The concatenation of the observed point cloud and symmetric one reconstructs a coarse object shape, thus facilitating object center (3D translation) and 3D size estimation.

Optical Character Recognition

Zero-Shot Chinese Character Recognition with Stroke-Level Decomposition

1 code implementation22 Jun 2021 Jingye Chen, Bin Li, xiangyang xue

Inspired by the fact that humans can generalize to know how to write characters unseen before if they have learned stroke orders of some characters, we propose a stroke-based method by decomposing each character into a sequence of strokes, which are the most basic units of Chinese characters.

Rapid COVID-19 Risk Screening by Eye-region Manifestations

no code implementations12 Jun 2021 Yanwei Fu, Lei Zhao, Haojie Zheng, Qiang Sun, Li Yang, Hong Li, Jiao Xie, xiangyang xue, Feng Li, Yuan Li, Wei Wang, Yantao Pei, Jianmin Wang, Xiuqi Wu, Yanhua Zheng, Hongxia Tian Mengwei Gu1

It is still nontrivial to develop a new fast COVID-19 screening method with the easier access and lower cost, due to the technical and cost limitations of the current testing methods in the medical resource-poor districts.

The Image Local Autoregressive Transformer

1 code implementation NeurIPS 2021 Chenjie Cao, Yuxin Hong, Xiang Li, Chengrong Wang, Chengming Xu, xiangyang xue, Yanwei Fu

To address these limitations, we propose a novel model -- image Local Autoregressive Transformer (iLAT), to better facilitate the locally guided image synthesis.

Image Generation

Delving into Data: Effectively Substitute Training for Black-box Attack

no code implementations CVPR 2021 Wenxuan Wang, Bangjie Yin, Taiping Yao, Li Zhang, Yanwei Fu, Shouhong Ding, Jilin Li, Feiyue Huang, xiangyang xue

Previous substitute training approaches focus on stealing the knowledge of the target model based on real training data or synthetic data, without exploring what kind of data can further improve the transferability between the substitute and target models.

Adversarial Attack

Learning Dynamic Alignment via Meta-filter for Few-shot Learning

2 code implementations CVPR 2021 Chengming Xu, Chen Liu, Li Zhang, Chengjie Wang, Jilin Li, Feiyue Huang, xiangyang xue, Yanwei Fu

Our insight is that these methods would lead to poor adaptation with redundant matching, and leveraging channel-wise adjustment is the key to well adapting the learned knowledge to new classes.

Few-Shot Learning

Raven's Progressive Matrices Completion with Latent Gaussian Process Priors

1 code implementation22 Mar 2021 Fan Shi, Bin Li, xiangyang xue

In this paper we aim to solve the latter one by proposing a deep latent variable model, in which multiple Gaussian processes are employed as priors of latent variables to separately learn underlying abstract concepts from RPMs; thus the proposed model is interpretable in terms of concept-specific latent variables.

Answer Selection Gaussian Processes +1

Knowledge-Guided Object Discovery with Acquired Deep Impressions

1 code implementation19 Mar 2021 Jinyang Yuan, Bin Li, xiangyang xue

The proposed ADI framework focuses on the acquisition and utilization of knowledge, and is complementary to existing deep generative models proposed for compositional scene representation.

Object Discovery Scene Understanding

Learning Compositional Representation for 4D Captures with Neural ODE

no code implementations CVPR 2021 Boyan Jiang, yinda zhang, Xingkui Wei, xiangyang xue, Yanwei Fu

To model the motion, a neural Ordinary Differential Equation (ODE) is trained to update the initial state conditioned on the learned motion code, and a decoder takes the shape code and the updated state code to reconstruct the 3D model at each time stamp.

Is normalization indispensable for training deep neural network?

1 code implementation NeurIPS 2020 Jie Shao, Kai Hu, Changhu Wang, xiangyang xue, Bhiksha Raj

In this paper, we study what would happen when normalization layers are removed from the network, and show how to train deep neural networks without normalization layers and without performance degradation.

General Classification Image Classification +5

Nonlinear Monte Carlo Method for Imbalanced Data Learning

no code implementations27 Oct 2020 Xuli Shen, Qing Xu, xiangyang xue

and the mean value of loss function is used as the empirical risk by Law of Large Numbers (LLN).

imbalanced classification

M3Lung-Sys: A Deep Learning System for Multi-Class Lung Pneumonia Screening from CT Imaging

no code implementations7 Oct 2020 Xuelin Qian, Huazhu Fu, Weiya Shi, Tao Chen, Yanwei Fu, Fei Shan, xiangyang xue

To counter the outbreak of COVID-19, the accurate diagnosis of suspected cases plays a crucial role in timely quarantine, medical treatment, and preventing the spread of the pandemic.

A New Screening Method for COVID-19 based on Ocular Feature Recognition by Machine Learning Tools

no code implementations4 Sep 2020 Yanwei Fu, Feng Li, Wenxuan Wang, Haicheng Tang, Xuelin Qian, Mengwei Gu, xiangyang xue

After more than four months study, we found that the confirmed cases of COVID-19 present the consistent ocular pathological symbols; and we propose a new screening method of analyzing the eye-region images, captured by common CCD and CMOS cameras, could reliably make a rapid risk screening of COVID-19 with very high accuracy.

Temporal Context Aggregation for Video Retrieval with Contrastive Learning

1 code implementation4 Aug 2020 Jie Shao, Xin Wen, Bingchen Zhao, xiangyang xue

The current research focus on Content-Based Video Retrieval requires higher-level video representation describing the long-range semantic dependencies of relevant incidents, events, etc.

Contrastive Learning Representation Learning +1

Long-Term Cloth-Changing Person Re-identification

no code implementations26 May 2020 Xuelin Qian, Wenxuan Wang, Li Zhang, Fangrui Zhu, Yanwei Fu, Tao Xiang, Yu-Gang Jiang, xiangyang xue

Specifically, we consider that under cloth-changes, soft-biometrics such as body shape would be more reliable.

Person Re-Identification

Sketch-BERT: Learning Sketch Bidirectional Encoder Representation from Transformers by Self-supervised Learning of Sketch Gestalt

1 code implementation CVPR 2020 Hangyu Lin, Yanwei Fu, Yu-Gang Jiang, xiangyang xue

Unfortunately, the representation learned by SketchRNN is primarily for the generation tasks, rather than the other tasks of recognition and retrieval of sketches.

Self-Supervised Learning Sketch Recognition

MOTS: Multiple Object Tracking for General Categories Based On Few-Shot Method

no code implementations19 May 2020 Xixi Xu, Chao Lu, Liang Zhu, xiangyang xue, Guanxian Chen, Qi Guo, Yining Lin, Zhijian Zhao

Most modern Multi-Object Tracking (MOT) systems typically apply REID-based paradigm to hold a balance between computational efficiency and performance.

Multi-Object Tracking Multiple Object Tracking

BERT-ATTACK: Adversarial Attack Against BERT Using BERT

3 code implementations EMNLP 2020 Linyang Li, Ruotian Ma, Qipeng Guo, xiangyang xue, Xipeng Qiu

Adversarial attacks for discrete data (such as texts) have been proved significantly more challenging than continuous data (such as images) since it is difficult to generate adversarial samples with gradient-based methods.

Adversarial Attack

3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection

no code implementations1 Mar 2020 Liang Du, Jingang Tan, xiangyang xue, Lili Chen, Hongkai Wen, Jianfeng Feng, Jiamao Li, Xiaolin Zhang

We propose a novel fast and robust 3D point clouds segmentation framework via coupled feature selection, named 3DCFS, that jointly performs semantic and instance segmentation.

3D Semantic Instance Segmentation feature selection +1

Learning to Augment Expressions for Few-shot Fine-grained Facial Expression Recognition

no code implementations17 Jan 2020 Wenxuan Wang, Yanwei Fu, Qiang Sun, Tao Chen, Chenjie Cao, Ziqi Zheng, Guoqiang Xu, Han Qiu, Yu-Gang Jiang, xiangyang xue

Considering the phenomenon of uneven data distribution and lack of samples is common in real-world scenarios, we further evaluate several tasks of few-shot expression learning by virtue of our F2ED, which are to recognize the facial expressions given only few training instances.

Facial Expression Recognition

DeepSFM: Structure From Motion Via Deep Bundle Adjustment

1 code implementation ECCV 2020 Xingkui Wei, yinda zhang, Zhuwen Li, Yanwei Fu, xiangyang xue

The explicit constraints on both depth (structure) and pose (motion), when combined with the learning components, bring the merit from both traditional BA and emerging deep learning technology.

Pose Estimation

Multi-Scale Self-Attention for Text Classification

no code implementations2 Dec 2019 Qipeng Guo, Xipeng Qiu, PengFei Liu, xiangyang xue, Zheng Zhang

In this paper, we introduce the prior knowledge, multi-scale structure, into self-attention modules.

Classification General Classification +1

Fast Color Constancy with Patch-wise Bright Pixels

no code implementations17 Nov 2019 Yiyao Shi, Jian Wang, xiangyang xue

In this paper, a learning-free color constancy algorithm called the Patch-wise Bright Pixels (PBP) is proposed.

Color Constancy

Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models

no code implementations ICLR 2020 Xisen Jin, Zhongyu Wei, Junyi Du, xiangyang xue, Xiang Ren

Human and metrics evaluation on both LSTM models and BERT Transformer models on multiple datasets show that our algorithms outperform prior hierarchical explanation algorithms.

Natural Language Processing Semantic Composition

DeepEnFM: Deep neural networks with Encoder enhanced Factorization Machine

no code implementations25 Sep 2019 Qiang Sun, Zhinan Cheng, Yanwei Fu, Wenxuan Wang, Yu-Gang Jiang, xiangyang xue

Instead of learning the cross features directly, DeepEnFM adopts the Transformer encoder as a backbone to align the feature embeddings with the clues of other fields.

Click-Through Rate Prediction

Dynamic Graph Message Passing Networks

1 code implementation CVPR 2020 Li Zhang, Mohan Chen, Anurag Arnab, xiangyang xue, Philip H. S. Torr

A fully-connected graph, such as the self-attention operation in Transformers, is beneficial for such modelling, however, its computational overhead is prohibitive.

Image Classification object-detection +3

Towards Instance-level Image-to-Image Translation

no code implementations CVPR 2019 Zhiqiang Shen, Mingyang Huang, Jianping Shi, xiangyang xue, Thomas Huang

The proposed INIT exhibits three import advantages: (1) the instance-level objective loss can help learn a more accurate reconstruction and incorporate diverse attributes of objects; (2) the styles used for target domain of local/global areas are from corresponding spatial regions in source domain, which intuitively is a more reasonable mapping; (3) the joint training process can benefit both fine and coarse granularity and incorporates instance information to improve the quality of global translation.

Image-to-Image Translation object-detection +2

CODA: Counting Objects via Scale-aware Adversarial Density Adaption

1 code implementation25 Mar 2019 Li Wang, Yongbo Li, xiangyang xue

Extensive experiments demonstrate that our network produces much better results on unseen datasets compared with existing counting adaption models.

Crowd Counting

Star-Transformer

2 code implementations NAACL 2019 Qipeng Guo, Xipeng Qiu, PengFei Liu, Yunfan Shao, xiangyang xue, Zheng Zhang

Although Transformer has achieved great successes on many NLP tasks, its heavy structure with fully-connected attention connections leads to dependencies on large training data.

Named Entity Recognition Natural Language Inference +2

Spatial Mixture Models with Learnable Deep Priors for Perceptual Grouping

1 code implementation7 Feb 2019 Jinyang Yuan, Bin Li, xiangyang xue

Different from existing methods, the proposed method disentangles the attributes of an object into ``shape'' and ``appearance'' which are modeled separately by the mixture weights and the mixture components.

MEAL: Multi-Model Ensemble via Adversarial Learning

1 code implementation6 Dec 2018 Zhiqiang Shen, Zhankui He, xiangyang xue

In this paper, we present a method for compressing large, complex trained ensembles into a single network, where knowledge from a variety of trained deep neural networks (DNNs) is distilled and transferred to a single DNN.

Instance-level Sketch-based Retrieval by Deep Triplet Classification Siamese Network

no code implementations28 Nov 2018 Peng Lu, Hangyu Lin, Yanwei Fu, Shaogang Gong, Yu-Gang Jiang, xiangyang xue

Additionally, to study the tasks of sketch-based hairstyle retrieval, this paper contributes a new instance-level photo-sketch dataset - Hairstyle Photo-Sketch dataset, which is composed of 3600 sketches and photos, and 2400 sketch-photo pairs.

General Classification Sketch-Based Image Retrieval +1

Learning the Compositional Spaces for Generalized Zero-shot Learning

no code implementations ICLR 2019 Hanze Dong, Yanwei Fu, Sung Ju Hwang, Leonid Sigal, xiangyang xue

This paper studies the problem of Generalized Zero-shot Learning (G-ZSL), whose goal is to classify instances belonging to both seen and unseen classes at the test time.

Generalized Zero-Shot Learning Open Set Learning

Object Detection from Scratch with Deep Supervision

1 code implementation25 Sep 2018 Zhiqiang Shen, Zhuang Liu, Jianguo Li, Yu-Gang Jiang, Yurong Chen, xiangyang xue

Thus, a better solution to handle these critical problems is to train object detectors from scratch, which motivates our proposed method.

General Classification object-detection +1

Top-Down Tree Structured Text Generation

no code implementations14 Aug 2018 Qipeng Guo, Xipeng Qiu, xiangyang xue, Zheng Zhang

Text generation is a fundamental building block in natural language processing tasks.

Natural Language Processing Text Generation

SCSP: Spectral Clustering Filter Pruning with Soft Self-adaption Manners

no code implementations14 Jun 2018 Huiyuan Zhuo, Xuelin Qian, Yanwei Fu, Heng Yang, xiangyang xue

In this paper, we proposed a novel filter pruning for convolutional neural networks compression, namely spectral clustering filter pruning with soft self-adaption manners (SCSP).

Model Compression

Multi-level Semantic Feature Augmentation for One-shot Learning

1 code implementation15 Apr 2018 Zitian Chen, Yanwei Fu, yinda zhang, Yu-Gang Jiang, xiangyang xue, Leonid Sigal

In semantic space, we search for related concepts, which are then projected back into the image feature spaces by the decoder portion of the TriNet.

One-Shot Learning

Learning to score the figure skating sports videos

1 code implementation8 Feb 2018 Chengming Xu, Yanwei Fu, Bing Zhang, Zitian Chen, Yu-Gang Jiang, xiangyang xue

This paper targets at learning to score the figure skating sports videos.

VOCABULARY-INFORMED VISUAL FEATURE AUGMENTATION FOR ONE-SHOT LEARNING

no code implementations ICLR 2018 jianqi ma, Hangyu Lin, yinda zhang, Yanwei Fu, xiangyang xue

Besides directly augmenting image features, we transform the image features to semantic space using the encoder and perform the data augmentation.

Classification Data Augmentation +2

Pose-Normalized Image Generation for Person Re-identification

2 code implementations ECCV 2018 Xuelin Qian, Yanwei Fu, Tao Xiang, Wenxuan Wang, Jie Qiu, Yang Wu, Yu-Gang Jiang, xiangyang xue

Person Re-identification (re-id) faces two major challenges: the lack of cross-view paired training data and learning discriminative identity-sensitive and view-invariant features in the presence of large pose variations.

Image Generation Person Re-Identification +1

DeepSkeleton: Skeleton Map for 3D Human Pose Regression

no code implementations29 Nov 2017 Qingfu Wan, Wei zhang, xiangyang xue

For the first time, we show that training regression network from skeleton map alone is capable of meeting the performance of state-of-theart 3D human pose estimation works.

3D Human Pose Estimation

Dual Skipping Networks

no code implementations CVPR 2018 Changmao Cheng, Yanwei Fu, Yu-Gang Jiang, Wei Liu, Wenlian Lu, Jianfeng Feng, xiangyang xue

Inspired by the recent neuroscience studies on the left-right asymmetry of the human brain in processing low and high spatial frequency information, this paper introduces a dual skipping network which carries out coarse-to-fine object categorization.

General Classification Object Categorization

Recent Advances in Zero-shot Recognition

no code implementations13 Oct 2017 Yanwei Fu, Tao Xiang, Yu-Gang Jiang, xiangyang xue, Leonid Sigal, Shaogang Gong

With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data.

Open Set Learning Zero-Shot Learning

Multi-scale Deep Learning Architectures for Person Re-identification

no code implementations ICCV 2017 Xuelin Qian, Yanwei Fu, Yu-Gang Jiang, Tao Xiang, xiangyang xue

Our model is able to learn deep discriminative feature representations at different scales and automatically determine the most suitable scales for matching.

Person Re-Identification

DSOD: Learning Deeply Supervised Object Detectors from Scratch

4 code implementations ICCV 2017 Zhiqiang Shen, Zhuang Liu, Jianguo Li, Yu-Gang Jiang, Yurong Chen, xiangyang xue

State-of-the-art object objectors rely heavily on the off-the-shelf networks pre-trained on large-scale classification datasets like ImageNet, which incurs learning bias due to the difference on both the loss functions and the category distributions between classification and detection tasks.

General Classification object-detection +1

A Jointly Learned Deep Architecture for Facial Attribute Analysis and Face Detection in the Wild

no code implementations27 Jul 2017 Keke He, Yanwei Fu, xiangyang xue

Facial attribute analysis in the real world scenario is very challenging mainly because of complex face variations.

Face Detection

Modeling Multimodal Clues in a Hybrid Deep Learning Framework for Video Classification

no code implementations14 Jun 2017 Yu-Gang Jiang, Zuxuan Wu, Jinhui Tang, Zechao Li, xiangyang xue, Shih-Fu Chang

More specifically, we utilize three Convolutional Neural Networks (CNNs) operating on appearance, motion and audio signals to extract their corresponding features.

General Classification Video Classification

Vocabulary-informed Extreme Value Learning

no code implementations28 May 2017 Yanwei Fu, Hanze Dong, Yu-feng Ma, Zhengjun Zhang, xiangyang xue

To solve this problem, we propose the Extreme Value Learning (EVL) formulation to learn the mapping from visual feature to semantic space.

Open Set Learning

Semi-Latent GAN: Learning to generate and modify facial images from attributes

no code implementations7 Apr 2017 Weidong Yin, Yanwei Fu, Leonid Sigal, xiangyang xue

Generating and manipulating human facial images using high-level attributal controls are important and interesting problems.

Weakly Supervised Dense Video Captioning

no code implementations CVPR 2017 Zhiqiang Shen, Jianguo Li, Zhou Su, Minjun Li, Yurong Chen, Yu-Gang Jiang, xiangyang xue

This paper focuses on a novel and challenging vision task, dense video captioning, which aims to automatically describe a video clip with multiple informative and diverse caption sentences.

Dense Video Captioning Language Modelling +1

Iterative Object and Part Transfer for Fine-Grained Recognition

no code implementations29 Mar 2017 Zhiqiang Shen, Yu-Gang Jiang, Dequan Wang, xiangyang xue

On both datasets, we achieve better results than many state-of-the-art approaches, including a few using oracle (manually annotated) bounding boxes in the test images.

Arbitrary-Oriented Scene Text Detection via Rotation Proposals

4 code implementations3 Mar 2017 Jianqi Ma, Weiyuan Shao, Hao Ye, Li Wang, Hong Wang, Yingbin Zheng, xiangyang xue

This paper introduces a novel rotation-based framework for arbitrary-oriented text detection in natural scene images.

Region Proposal Scene Text Detection

Model-based Deep Hand Pose Estimation

1 code implementation22 Jun 2016 Xingyi Zhou, Qingfu Wan, Wei zhang, xiangyang xue, Yichen Wei

For the first time, we show that embedding such a non-linear generative process in deep learning is feasible for hand pose estimation.

Hand Pose Estimation

Learning to Point and Count

no code implementations8 Dec 2015 Jie Shao, Dequan Wang, xiangyang xue, Zheng Zhang

This paper proposes the problem of point-and-count as a test case to break the what-and-where deadlock.

General Classification

Multiple Granularity Descriptors for Fine-Grained Categorization

no code implementations ICCV 2015 Dequan Wang, Zhiqiang Shen, Jie Shao, Wei zhang, xiangyang xue, Zheng Zhang

Fine-grained categorization, which aims to distinguish subordinate-level categories such as bird species or dog breeds, is an extremely challenging task.

Weakly Supervised Semantic Segmentation for Social Images

no code implementations CVPR 2015 Wei Zhang, Sheng Zeng, Dequan Wang, xiangyang xue

Image semantic segmentation is the task of partitioning image into several regions based on semantic concepts.

Weakly-Supervised Semantic Segmentation

Evaluating Two-Stream CNN for Video Classification

no code implementations8 Apr 2015 Hao Ye, Zuxuan Wu, Rui-Wei Zhao, Xi Wang, Yu-Gang Jiang, xiangyang xue

In this paper, we conduct an in-depth study to investigate important implementation options that may affect the performance of deep nets on video classification.

Classification General Classification +1

Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification

1 code implementation7 Apr 2015 Zuxuan Wu, Xi Wang, Yu-Gang Jiang, Hao Ye, xiangyang xue

In this paper, we propose a hybrid deep learning framework for video classification, which is able to model static spatial information, short-term motion, as well as long-term temporal clues in the videos.

Classification General Classification +1

Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks

no code implementations25 Feb 2015 Yu-Gang Jiang, Zuxuan Wu, Jun Wang, xiangyang xue, Shih-Fu Chang

In this paper, we study the challenging problem of categorizing videos according to high-level semantics such as the existence of a particular human action or a complex event.

Do More Dropouts in Pool5 Feature Maps for Better Object Detection

no code implementations24 Sep 2014 Zhiqiang Shen, xiangyang xue

In these fields, the outputs of all layers of CNNs are usually considered as a high dimensional feature vector extracted from an input image and the correspondence between finer level feature vectors and concepts that the input image contains is all-important.

General Classification Image Classification +2

Correlative Multi-Label Multi-Instance Image Annotation

no code implementations IEEE International Conference on Computer Vision 2011 Xiangyang Xue, Wei zhang, Jie Zhang, Bin Wu, Jianping Fan, Yao Lu

The cross-level label coherence en-codes the consistency between the labels at the image leveland the labels at the region level.

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