Pose-Guided Spatial Alignment and Key Frame Selection for One-Shot Video-Based Person Re-Identification

Abstract

One-shot video-based person re-identification exploits the unlabeled data by using a singlelabeled sample for each individual to train a model and to reduce the need for laborious labeling. Although recent works focusing on this task have made some achievements, most state-of-the-art models are vulnerable to misalignment, pose variation and corrupted frames. To address these challenges, we propose a one-shot video-based person re-identification model based on pose-guided spatial alignment and KFS. First, a spatial transformer sub-network trained using pose-guided regression is employed to perform the spatial alignment. Second, we propose a novel training strategy based on KFS. Key frames with abruptly changing poses are deliberately identified and selected to make the network adaptive to pose variation. Finally, we propose a frame feature pooling method by incorporating long short-term memory with an attention mechanism to reduce the influence of corrupted frames. Comprehensive experiments are presented based on the MARS and DukeMTMC-VideoReID datasets. The mAP values for these datasets reach 46.5% and 68.4%, respectively, demonstrating that the proposed model achieves significant improvements over state-of-the-art one-shot person re-identification methods.INDEX TERMS Person re-identification, one-shot learning, spatial alignment, key frame selection, frame feature pooling.

Best Frame Selection to Enhance Training Step Efficiency in Video-Based Human Action Recognition

“…Rajpal et al [13] used a fuzzy method based on single-frame information, such as contrast, edges and luminescence, in order to select the best frames for watermarking. Chen et al [14] suggested a frame selection scheme for video-based person re-identification. The spatial and temporal characteristics are used simultaneously to select keyframes.…”

Hardware Trojans in Chips: A Survey for Detection and Prevention

“…Neural network algorithms has driven the advancement for image recognition and detection [ 75 , 76 , 77 , 78 , 79 , 80 , 81 ]. Meanwhile, artificial intelligence (AI) chips that are based on these ML algorithms have brought a further breakthrough in the computing performance for traditional ICs.…”