195 citations · 673 across the 20 of their papers we have counts for
20 papers
InfoBehavior: Self-supervised Representation Learning for Ultra-long Behavior Sequence via Hierarchical Grouping
Runshi Liu, Pengda Qin, Yuhong Li +4
E-commerce companies have to face abnormal sellers who sell potentially-risky products. Typically, the risk can be identified by jointly considering product content (e.g., title an…
TVDIM: Enhancing Image Self-Supervised Pretraining via Noisy Text Data
Pengda Qin, Yuhong Li, Kefeng Deng +1
Among ubiquitous multimodal data in the real world, text is the modality generated by human, while image reflects the physical world honestly. In a visual understanding application…
PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning
Huaxi Huang, Junjie Zhang, Jian Zhang +2
The predicament in semi-supervised few-shot learning (SSFSL) is to maximize the value of the extra unlabeled data to boost the few-shot learner. In this paper, we propose a Poisson…
Field-wise Learning for Multi-field Categorical Data
Zhibin Li, Jian Zhang, Yongshun Gong +2
We propose a new method for learning with multi-field categorical data. Multi-field categorical data are usually collected over many heterogeneous groups. These groups can reflect…
Multi-layer Feature Aggregation for Deep Scene Parsing Models
Litao Yu, Yongsheng Gao, Jun Zhou +2
Scene parsing from images is a fundamental yet challenging problem in visual content understanding. In this dense prediction task, the parsing model assigns every pixel to a catego…
Dual Attention on Pyramid Feature Maps for Image Captioning
Litao Yu, Jian Zhang, Qiang Wu
Generating natural sentences from images is a fundamental learning task for visual-semantic understanding in multimedia. In this paper, we propose to apply dual attention on pyrami…
TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples
Huaxi Huang, Junjie Zhang, Jian Zhang +2
The challenges of high intra-class variance yet low inter-class fluctuations in fine-grained visual categorization are more severe with few labeled samples, \textit{i.e.,} Fine-Gra…
ShadowSync: Performing Synchronization in the Background for Highly Scalable Distributed Training
Qinqing Zheng, Bor-Yiing Su, Jiyan Yang +7
Recommendation systems are often trained with a tremendous amount of data, and distributed training is the workhorse to shorten the training time. While the training throughput can…
SBSGAN: Suppression of Inter-Domain Background Shift for Person Re-Identification
Yan Huang, Qiang Wu, JingSong Xu +1
Cross-domain person re-identification (re-ID) is challenging due to the bias between training and testing domains. We observe that if backgrounds in the training and testing datase…
Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification
Huaxi Huang, Junjie Zhang, Jian Zhang +2
Deep neural networks have demonstrated advanced abilities on various visual classification tasks, which heavily rely on the large-scale training samples with annotated ground-truth…
Sample Adaptive Multiple Kernel Learning for Failure Prediction of Railway Points
Zhibin Li, Jian Zhang, Qiang Wu +3
Railway points are among the key components of railway infrastructure. As a part of signal equipment, points control the routes of trains at railway junctions, having a significant…
Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning
Huaxi Huang, Junjie Zhang, Jian Zhang +2
The recognition ability of human beings is developed in a progressive way. Usually, children learn to discriminate various objects from coarse to fine-grained with limited supervis…
Fast Registration for cross-source point clouds by using weak regional affinity and pixel-wise refinement
Xiaoshui Huang, Lixin Fan, Qiang Wu +2
Many types of 3D acquisition sensors have emerged in recent years and point cloud has been widely used in many areas. Accurate and fast registration of cross-source 3D point clouds…
Multi-pseudo Regularized Label for Generated Data in Person Re-Identification
Yan Huang, Jinsong Xu, Qiang Wu +3
Sufficient training data normally is required to train deeply learned models. However, due to the expensive manual process for labelling large number of images, the amount of avail…
Robust Guided Image Filtering
Wei Liu, Xiaogang Chen, Chunhua Shen +3
The process of using one image to guide the filtering process of another one is called Guided Image Filtering (GIF). The main challenge of GIF is the structure inconsistency betwee…
A coarse-to-fine algorithm for registration in 3D street-view cross-source point clouds
Xiaoshui Huang, Jian Zhang, Qiang Wu +2
With the development of numerous 3D sensing technologies, object registration on cross-source point cloud has aroused researchers' interests. When the point clouds are captured fro…
A Systematic Approach for Cross-source Point Cloud Registration by Preserving Macro and Micro Structures
Xiaoshui Huang, Jian Zhang, Lixin Fan +2
We propose a systematic approach for registering cross-source point clouds. The compelling need for cross-source point cloud registration is motivated by the rapid development of a…
Data Driven Robust Image Guided Depth Map Restoration
Wei Liu, Yun Gu, Chunhua Shen +3
Depth maps captured by modern depth cameras such as Kinect and Time-of-Flight (ToF) are usually contaminated by missing data, noises and suffer from being of low resolution. In thi…
LOGO-Net: Large-scale Deep Logo Detection and Brand Recognition with Deep Region-based Convolutional Networks
Steven C. H. Hoi, Xiongwei Wu, Hantang Liu +4
Logo detection from images has many applications, particularly for brand recognition and intellectual property protection. Most existing studies for logo recognition and detection…
Robust High Quality Image Guided Depth Upsampling
Wei Liu, Yijun Li, Xiaogang Chen +3
Time-of-Flight (ToF) depth sensing camera is able to obtain depth maps at a high frame rate. However, its low resolution and sensitivity to the noise are always a concern. A popula…