Attention Transfer from Web Images for Video Recognition
Authors:
Open Access
- 19 October 2017
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Abstract
The Human Interaction Image (HII) dataset is a new dataset containing Web images from Commercial Search Engines (Google, Bing and Flickr). We use keyword search to collect images corresponding to four types of interactions: handshake, highfive, hug, kiss. Then we manually filter the irrelevant images. The dataset contains 2410 images with at least 550 images per interaction. The dataset can be applied, but not limited to the following research areas: interaction recognition/prediction action recognition video analysis transfer learning Please cite the following paper if you use the HII dataset in your work (papers, articles, reports, books, software, etc): J. Li, Y. Wong, Q.Zhao, M. Kankanhalli Attention Transfer from Web Images for Video Recognition ACM Multimedia, 2017. http://doi.org/10.1145/3123266.312343Keywords
All Related Versions
Funding Information
- National Research Foundation Prime Minister's Office Singapore
This publication has 35 references indexed in Scilit:
- Action recognition with trajectory-pooled deep-convolutional descriptors2015
- Improving Human Action Recognition Using Score Distribution and Ranking2015
- Large-Scale Video Classification with Convolutional Neural Networks2014
- Learning Fine-Grained Image Similarity with Deep Ranking2014
- Learning Everything about Anything: Webly-Supervised Visual Concept Learning2014
- Zero-Shot Event Detection Using Multi-modal Fusion of Weakly Supervised Concepts2014
- Unsupervised Domain Adaptation by Domain Invariant Projection2013
- Action Recognition with Improved Trajectories2013
- Subspace Interpolation via Dictionary Learning for Unsupervised Domain Adaptation2013
- Adapting Visual Category Models to New Domains2010