QQ客服 官方微博 反馈留言

	Compact Deep Invariant Descriptors for Video Retrieval
	Lou, Yihang ; Bai, Yan ; Lin, Jie ; Wang, Shiqi ; Chen, Jie ; Chandrasekhar, Vijay ; Duan, Ling-Yu ; Huang, Tiejun ; Kot, Alex Chichung ; Gao, Wen
	2017
英文摘要	With emerging demand for large-scale video analysis, the Motion Picture Experts Group (MPEG) initiated the Compact Descriptor for Video Analysis (CDVA) standardization in 2014. In this work, we develop novel deep-learning features and incorporate them into the well-established CDVA evaluation framework to study its effectiveness in video analysis. In particular, we propose a Nested Invariance Pooling (NIP) method to obtain compact and robust Convolutional Neural Network (CNNs) descriptors. The CNNs descriptors are generated by applying three different pooling operations to the feature maps of CNNs in a nested way towards rotation and scale invariant feature representation. In particular, the rational, advantages and performance on the combination of CNNs and handcrafted descriptors are provided to better investigate the complementary effects of deep learnt and handcrafted features. Extensive experimental results show that the proposed CNNs descriptors outperform both state-of-the-art CNNs descriptors and canonical handcrafted descriptors adopted in CDVA Experimental Model (CXM) with significant mAP gains of 11.3% and 4.7%, respectively. Moreover, the combination of NIP derived deep invariant descriptors and handcrafted descriptors not only fulfills the lowest bitrate budget of CDVA, but also significantly advances the performance of CDVA core techniques.; National Natural Science Foundation of China [U1611461, 61661146005, 61390515]; National High-tech R&D Program of China [2015AA016302]; NTU-PKU Joint Research Institute; Ng Teng Fong Charitable Foundation; CPCI-S(ISTP); 420-429
语种	英语
出处	Data Compression Conference (DCC)
DOI标识	10.1109/DCC.2017.31
内容类型	其他
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/469876]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Lou, Yihang,Bai, Yan,Lin, Jie,et al. Compact Deep Invariant Descriptors for Video Retrieval. 2017-01-01.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。