Video Alignment Using Bi-Directional Attention Flow in a Multi-Stage Learning Model

Abstract

Recently, deep learning techniques have contributed to solving a multitude of computer vision tasks. In this paper, we propose a deep-learning approach for video alignment, which involves finding the best correspondences between two overlapping videos. We formulate the video alignment task as a variant of the well-known machine comprehension (MC) task in natural language processing. While MC answers a question about a given paragraph, our technique determines the most relevant frame sequence in the context video to the query video. This is done by representing the individual frames of the two videos by highly discriminative and compact descriptors. Next, the descriptors are fed into a multi-stage network that is able, with the help of the bidirectional attention flow mechanism, to represent the context video at various granularity levels besides estimating the query-aware context part. The proposed model was trained on 10k video-pairs collected from ''YouTube''. The obtained results show that our model outperforms all known state of the art techniques by a considerable margin, confirming its efficacy. INDEX TERMS Bi-directional attention, temporal alignment, video retrieval, video synchronization, video alignment. REHAM ABOBEAH received the B.Sc. and M.Sc. degrees from the Computers and Systems Engineering Department, Faculty of Engineering, Al-Azhar University. She is currently pursuing the Ph.D. degree with the

Bridge inspection component registration for damage evolution

“…Building on the LAMV algorithm, the bi-directional attention flow (BDAF) algorithm very accurately aligned video frames. 15 This BDAF algorithm demonstrated a 10% and 14% increase in accuracy on the Climbing 16 and Madonna 16 datasets, respectively.…”