1.5k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Nankai UniversityCN185 papers
- Chinese Academy of SciencesCN114 papers
- National University of SingaporeSG63 papers
- Tsinghua UniversityCN53 papers
- University of Chinese Academy of SciencesCN50 papers
- Peking UniversityCN48 papers
- Nanyang Technological UniversitySG43 papers
- Centre National de la Recherche ScientifiqueFR39 papers
- University of Science and Technology of ChinaCN37 papers
- Peng Huanwu Center for Fundamental TheoryCN31 papers
- Beijing Normal UniversityCN29 papers
- Lanzhou UniversityCN29 papers
9 papers · 2 filters
Automatic Generation of Grounded Visual Questions
Shijie Zhang, Lizhen Qu, Shaodi You +2
In this paper, we propose the first model to be able to generate visually grounded questions with diverse types for a single image. Visual question generation is an emerging topic…
Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks
Pichao Wang, Zhaoyang Li, Yonghong Hou +1
Recently, Convolutional Neural Networks (ConvNets) have shown promising performances in many computer vision tasks, especially image-based recognition. How to effectively use ConvN…
Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking
Wenhui Li, Yongkang Wong, An-An Liu +3
Action recognition has received increasing attention from the computer vision and machine learning communities in the last decade. To enable the study of this problem, there exist…
Convolution in Convolution for Network in Network
Yanwei Pang, Manli Sun, Xiaoheng Jiang +1
Network in Netwrok (NiN) is an effective instance and an important extension of Convolutional Neural Network (CNN) consisting of alternating convolutional layers and pooling layers…
Cascaded Subpatch Networks for Effective CNNs
Xiaoheng Jiang, Yanwei Pang, Manli Sun +1
Conventional Convolutional Neural Networks (CNNs) use either a linear or non-linear filter to extract features from an image patch (region) of spatial size (Typically…
Learning Multilayer Channel Features for Pedestrian Detection
Jiale Cao, Yanwei Pang, Xuelong Li
Pedestrian detection based on the combination of Convolutional Neural Network (i.e., CNN) and traditional handcrafted features (i.e., HOG+LUV) has achieved great success. Generally…
Combining ConvNets with Hand-Crafted Features for Action Recognition Based on an HMM-SVM Classifier
Pichao Wang, Zhaoyang Li, Yonghong Hou +1
This paper proposes a new framework for RGB-D-based action recognition that takes advantages of hand-designed features from skeleton data and deeply learned features from depth map…
B-spline Shape from Motion & Shading: An Automatic Free-form Surface Modeling for Face Reconstruction
Weilong Peng, Zhiyong Feng, Chao Xu
Recently, many methods have been proposed for face reconstruction from multiple images, most of which involve fundamental principles of Shape from Shading and Structure from motion…
RGB-D-based Action Recognition Datasets: A Survey
Jing Zhang, Wanqing Li, Philip O. Ogunbona +2
Human action recognition from RGB-D (Red, Green, Blue and Depth) data has attracted increasing attention since the first work reported in 2010. Over this period, many benchmark dat…