Existing portrait matting methods either require auxiliary inputs that are costly to obtain or involve multiple stages that are computationally expensive, making them less suitable for real-time applications. In this work, we present a light-weight matting objective decomposition network (MODNet) for portrait matting in real-time with a single input image. The key idea behind our efficient design is by optimizing a series of sub-objectives simultaneously via explicit constraints. In addition, MODNet includes two novel techniques for improving model efficiency and robustness. First, an Efficient Atrous Spatial Pyramid Pooling (e-ASPP) module is introduced to fuse multi-scale features for semantic estimation. Second, a self-supervised sub-objectives consistency (SOC) strategy is proposed to adapt MODNet to real-world data to address the domain shift problem common to trimap-free methods. MODNet is easy to be trained in an end-to-end manner. It is much faster than contemporaneous methods and runs at 67 frames per second on a 1080Ti GPU. Experiments show that MODNet outperforms prior trimap-free methods by a large margin on both Adobe Matting Dataset and a carefully designed photographic portrait matting (PPM-100) benchmark proposed by us. Further, MODNet achieves remarkable results on daily photos and videos.
Human foamy virus encodes a 300-amino-acid nuclear regulatory protein termed Bel-1 that is required for human foamy virus replication in culture. Bel-1 is a potent trans-activator of gene expression directed by the homologous HFV long terminal repeat as well as the long terminal repeat of human immunodeficiency virus type 1. We have used mutational analysis to define several discrete functional domains within Bel-1. The C-terminal-50 amino acids of Bel-1 are shown to be essential for Bel-1 activity but can be effectively 1896
Nucleoporin proteins (Nups) have been proposed to mediate spatial and temporal chromatin organization during gene regulation. Nevertheless, the molecular mechanisms in mammalian cells are not well understood. Here, we report that Nucleoporin 153 (NUP153) interacts with the chromatin architectural proteins, CTCF and cohesin, and mediates their binding across cis-regulatory elements and TAD boundaries in mouse embryonic stem (ES) cells. NUP153 depletion results in altered CTCF and cohesin binding and differential gene expressionspecifically at the bivalent developmental genes. To investigate the molecular mechanism, we utilize epidermal growth factor (EGF)-inducible immediate early genes (IEGs). We find that NUP153 controls CTCF and cohesin binding at the cis-regulatory elements and POL II pausing during the basal state. Furthermore, efficient IEG transcription relies on NUP153. We propose that NUP153 links the nuclear pore complex (NPC) to chromatin architecture allowing genes that are poised to respond rapidly to developmental cues to be properly modulated.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.