Near-duplicate detection and alignment for multi-view videos

Melloni, Andrea; Lameri, Silvia; Bestagini, Paolo; Tagliasacchi, Marco; Tubaro, Stefano

doi:10.1109/icip.2015.7351241

Cited by 8 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Techniques similar to VSS's joint compression optimization have been explored in the image and signal processing communities. For example, Melloni et al develop a pipeline that identifies and aligns near-duplicate videos [37], and Pinheiro et al introduce a fingerprinting method to identify correlations among near-duplicate videos [41]. However, unlike VSS, these techniques assume that sets of near-duplicate videos are known a priori and they do not exploit redundancies to improve compression or read/write performance.…”

Section: Related Workmentioning

confidence: 99%

VSS: A Storage System for Video Analytics [Technical Report]

Haynes,

Daum,

et al. 2021

Preprint

View full text Add to dashboard Cite

We present a new video storage system (VSS) designed to decouple high-level video operations from the low-level details required to store and efficiently retrieve video data. VSS is designed to be the storage subsystem of a video data management system (VDBMS) and is responsible for:(1) transparently and automatically arranging the data on disk in an efficient, granular format; (2) caching frequentlyretrieved regions in the most useful formats; and (3) eliminating redundancies found in videos captured from multiple cameras with overlapping fields of view. Our results suggest that VSS can improve VDBMS read performance by up to 54%, reduce storage costs by up to 45%, and enable developers to focus on application logic rather than video storage and retrieval.

show abstract

Section: Related Workmentioning

confidence: 99%