A multi-embedding neural model for incident video retrieval. (October 2022)

• Record Type: Journal Article
• Authors: Chiang, Ting-Hui; Tseng, Yi-Chun; Tseng, Yu-Chee
• Is Part Of: Pattern recognition. Volume 130(2022)
• Publication Date: 2022-10
• Subjects: Artificial intelligence -- Computer vision -- Deep metric learning -- Incident video retrieval; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.108807
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A state-of-the-art approach for video retrieval on several datasets. An encoder-decoder for learning the spatial and temporal characteristics of videos. Multi-resolution embedding of incident videos for similarity comparison. Abstract: Many internet search engines have been developed, however, the retrieval of video clips remains a challenge. This paper considers the retrieval of incident videos, which may contain more spatial and temporal semantics. We propose an encoder-decoder ConvLSTM model that explores multiple embeddings of a video to facilitate comparison of similarity between a pair of videos. The model is able to encode a video into an embedding that integrates both its spatial information and temporal semantics. Multiple video embeddings are then generated from coarse- and fine-grained features of a video to capture high- and low-level meanings. Subsequently, a learning-based comparative model is proposed to compare the similarity of two videos based on their embeddings. Extensive evaluations are presented and show that our model outperforms state-of-the-art methods for several video retrieval tasks on the FIVR-200K, CC_WEB_VIDEO, and EVVE datasets.