Unsupervised Action Localization Crop in Video Retargeting for 3D ConvNets

• Published in: TENCON ... IEEE Region Ten Conference pp. 670 - 675
• Main Authors: Jana, Prithwish, Bhaumik, Swarnabja, Mohanta, Partha Pratim
• Format: Conference Proceeding
• Language: English
• Published: IEEE 07.12.2021
• Subjects: 3D ConvNet; Action Localization; Event and Activity Recognition; Jitter; Location awareness; Robot vision systems; Shape; Social networking (online); Surveillance; Three-dimensional displays; Video Classification; Video Retargeting

Untrimmed videos on social media or those captured by robots and surveillance cameras are of varied aspect ratios. However, 3D CNNs usually require as input a square-shaped video, whose spatial dimension is smaller than the original. Random- or center-cropping may leave out the video's subject...