TransNet: A deep network for fast detection of common shot transitions

Abstract

Shot boundary detection (SBD) is an important first step in many video processing applications. This paper presents a simple modular convolutional neural network architecture that achieves state-of-the-art results on the RAI dataset with well above real-time inference speed even on a single mediocre GPU. The network employs dilated convolutions and operates just on small resized frames. The training process employed randomly generated transitions using selected shots from the TRECVID IACC.3 dataset. The code and a selected trained network will be available at https://github.com/soCzech/TransNet.

References in corpus (3)

• Large-scale, Fast and Accurate Shot Boundary Detection through Spatio-temporal Convolutional Neural Networks
• Video shot boundary detection using motion activity descriptor
• Fast Video Shot Transition Localization with Deep Structured Models

Cited by in corpus (5)

• Video-to-Music Recommendation using Temporal Alignment of Segments
• Is there a "language of music-video clips" ? A qualitative and quantitative study
• Automated Anonymisation of Visual and Audio Data in Classroom Studies
• Overview of Tencent Multi-modal Ads Video Understanding Challenge
• Horizontal-to-Vertical Video Conversion