283 citations · 703 across the 15 of their papers we have counts for
15 papers
SBAT: Video Captioning with Sparse Boundary-Aware Transformer
Tao Jin, Siyu Huang, Ming Chen +2
In this paper, we focus on the problem of applying the transformer structure to video captioning effectively. The vanilla transformer is proposed for uni-modal language generation…
Multitask Non-Autoregressive Model for Human Motion Prediction
Bin Li, Jian Tian, Zhongfei Zhang +2
Human motion prediction, which aims at predicting future human skeletons given the past ones, is a typical sequence-to-sequence problem. Therefore, extensive efforts have been cont…
Perceiving Physical Equation by Observing Visual Scenarios
Siyu Huang, Zhi-Qi Cheng, Xi Li +3
Inferring universal laws of the environment is an important ability of human intelligence as well as a symbol of general AI. In this paper, we take a step toward this goal such tha…
Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariance
Siyu Huang, Xi Li, Zhi-Qi Cheng +2
In this work, we explore the cross-scale similarity in crowd counting scenario, in which the regions of different scales often exhibit high visual similarity. This feature is unive…
Multi-Channel Pyramid Person Matching Network for Person Re-Identification
Chaojie Mao, Yingming Li, Yaqing Zhang +2
In this work, we present a Multi-Channel deep convolutional Pyramid Person Matching Network (MC-PPMN) based on the combination of the semantic-components and the color-texture dist…
Deep Air Learning: Interpolation, Prediction, and Feature Analysis of Fine-grained Air Quality
Zhongang Qi, Tianchun Wang, Guojie Song +4
The interpolation, prediction, and feature analysis of fine-gained air quality are three important topics in the area of urban air computing. The solutions to these topics can prov…
Boosted Zero-Shot Learning with Semantic Correlation Regularization
Te Pi, Xi Li, Zhongfei +1
We study zero-shot learning (ZSL) as a transfer learning problem, and focus on the two key aspects of ZSL, model effectiveness and model adaptation. For effective modeling, we adop…
S3Pool: Pooling with Stochastic Spatial Sampling
Shuangfei Zhai, Hui Wu, Abhishek Kumar +4
Feature pooling layers (e.g., max pooling) in convolutional neural networks (CNNs) serve the dual purpose of providing increasingly abstract representations as well as yielding com…
Doubly Convolutional Neural Networks
Shuangfei Zhai, Yu Cheng, Weining Lu +1
Building large models with parameter sharing accounts for most of the success of deep convolutional neural networks (CNNs). In this paper, we propose doubly convolutional neural ne…
Zero-Shot Learning with Multi-Battery Factor Analysis
Zhong Ji, Yuzhong Xie, Yanwei Pang +2
Zero-shot learning (ZSL) extends the conventional image classification technique to a more challenging situation where the test image categories are not seen in the training sample…
Deep Structured Energy Based Models for Anomaly Detection
Shuangfei Zhai, Yu Cheng, Weining Lu +1
In this paper, we attack the anomaly detection problem by directly modeling the data distribution with deep architectures. We propose deep structured energy based models (DSEBMs),…
Dropout Training of Matrix Factorization and Autoencoder for Link Prediction in Sparse Graphs
Shuangfei Zhai, Zhongfei Zhang
Matrix factorization (MF) and Autoencoder (AE) are among the most successful approaches of unsupervised learning. While MF based models have been extensively exploited in the graph…
Semisupervised Autoencoder for Sentiment Analysis
Shuangfei Zhai, Zhongfei Zhang
In this paper, we investigate the usage of autoencoders in modeling textual data. Traditional autoencoders suffer from at least two aspects: scalability with the high dimensionalit…
Manifold Regularized Discriminative Neural Networks
Shuangfei Zhai, Zhongfei Zhang
Unregularized deep neural networks (DNNs) can be easily overfit with a limited sample size. We argue that this is mostly due to the disriminative nature of DNNs which directly mode…
A Survey of Appearance Models in Visual Object Tracking
Xi Li, Weiming Hu, Chunhua Shen +3
Visual object tracking is a significant computer vision task which can be applied to many domains such as visual surveillance, human computer interaction, and video compression. In…