Temporal action localization is an important yet challenging task in video understanding. Typically, such a task aims at inferring both the action category and localization of the start and end frame ...for each action instance in a long, untrimmed video. While most current models achieve good results by using pre-defined anchors and numerous actionness, such methods could be bothered with both large number of outputs and heavy tuning of locations and sizes corresponding to different anchors. Instead, anchor-free methods is lighter, getting rid of redundant hyper-parameters, but gains few attention. In this paper, we propose the first purely anchor-free temporal localization method, which is both efficient and effective. Our model includes (i) an end-to-end trainable basic predictor, (ii) a saliency-based refinement module to gather more valuable boundary features for each proposal with a novel boundary pooling, and (iii) several consistency constraints to make sure our model can find the accurate boundary given arbitrary proposals. Extensive experiments show that our method beats all anchor-based and actionness-guided methods with a remarkable margin on THUMOS14, achieving state-of-the-art results, and comparable ones on ActivityNet v1.3. Code is available at https://github.com/TencentYoutuResearch/ActionDetection-AFSD.
RNA localization mechanisms have been intensively studied and include localized protection of mRNA from degradation, diffusion-coupled local entrapment of mRNA, and directed transport of mRNAs along ...the cytoskeleton. While it is well understood how cells utilize these three mechanisms to organize mRNAs within the cytoplasm, a newly appreciated mechanism of RNA localization has emerged in recent years in which mRNAs phase-separate and form liquid-like droplets. mRNAs both contribute to condensation of proteins into liquid-like structures and are themselves regulated by being incorporated into membraneless organelles. This ability to condense into droplets is in many instances contributing to previously appreciated mRNA localization phenomena. Here we review how phase separation enables mRNAs to selectively and efficiently colocalize and be coregulated, allowing control of gene expression in time and space.
Perceptual image hash is an emerging technology that is closely related to many applications such as image content authentication, image forging detection, image similarity detection, and image ...retrieval. In this work, we propose an image alignment based perceptual image hash method, and a hash-based image forging detection and tampering localization method. In the proposed method, we introduce an image alignment process to provide a framework for image hash method to tolerate a wide range of geometric distortions. The image hash is generated by utilizing hybrid perceptual features that are extracted from global and local Zernike moments combining with DCT-based statistical features of the image. The proposed method can detect various image forging and compromised image regions. Furthermore, it has broad-spectrum robustness, including tolerating content-preserving manipulations and geometric distortion-resilient. Compared with state-of-the-art schemes, the proposed method provides satisfactory comprehensive performances in content-based image forging detection and tampering localization.
•Proposed a perceptual image hash for content authentication.•Image tampering detection and tampering localization.•Image alignment is used to obtain the standard position of an image object.•Using Watson’s visual model to select Perceptual robust features.•Fisher criterion is used to generate system parameters.
In robotic applications of visual simultaneous localization and mapping techniques, loop-closure detection and global localization are two issues that require the capacity to recognize a previously ...visited place from current camera measurements. We present an online method that makes it possible to detect when an image comes from an already perceived scene using local shape and color information. Our approach extends the bag-of-words method used in image classification to incremental conditions and relies on Bayesian filtering to estimate loop-closure probability. We demonstrate the efficiency of our solution by real-time loop-closure detection under strong perceptual aliasing conditions in both indoor and outdoor image sequences taken with a handheld camera.
It has been shown that direct target localization in distributed multiple input multiple output (MIMO) radar can outperform indirect localization significantly, but conventional direct localization ...methods suffer from both high computational complexity and high communication cost. In this work, we address the issues by designing an efficient factor graph based message passing approach to direct localization, which greatly reduces the computational complexity and communication cost. First, a factor graph representation for the problem of direct localization is developed, which, however, involves difficult local functions. Inspired by expectation propagation (EP), we design an iterative method to solve the problem, where both EP and belief propagation (BP) are used to make message passing in the factor graph tractable, leading to a low complexity message passing iterative method. We show that the message passing based method are very suitable for decentralized processing and can be employed in distributed radars with different configurations. Extensive comparisons with state-of-the-art indirect and direct methods are provided, which show that the proposed method can achieve similar performance to the exhaustive search-based direct localization methods while with much lower computational complexity and communication cost, and it outperforms significantly indirect localization methods at low signal to noise ratios.
In today's world, automatic navigation for a robotic device (autonomous vehicle and robot) is a pre-requisite for many complex tasks, which requires a robust localization method. We focus in this ...paper on the topic of localizing such a robot into an absolute and imprecise map. We propose a multi-sensor self-localization method, which is simultaneously able to operate with an imprecise map, as well as to improve the precision of an already existing one. The method uses split covariance intersection filter as well as an a priori selection of the best informative measurements out of all possible measurement sources at each time step. This selection scheme is based on an "added Shannon information"-based criterion. We demonstrate in operation via statistical analysis the consistency of a refined map obtained from a biased map while keeping vehicle localization integrity. On top of this, we demonstrate solving of the so-called kidnapped-robot problem using the same framework.
Long‐term operation of robots creates new challenges to Simultaneous Localization and Mapping (SLAM) algorithms. Long‐term SLAM algorithms should adapt to recent changes while preserving older ...states, when dealing with appearance variations (lighting, daytime, weather, or seasonal) or environment reconfiguration. When also operating robots for long periods and trajectory lengths, the map should readjust to environment changes but not grow indefinitely. The map size should depend only on updating the map with new information of interest, not on the operation time or trajectory length. Although several studies in the literature review SLAM algorithms, none of the studies focus on the challenges associated to lifelong SLAM. Thus, this paper presents a systematic literature review on long‐term localization and mapping following the Preferred Reporting Items for Systematic reviews and Meta‐Analysis guidelines. The review analyzes 142 works covering appearance invariance, modeling the environment dynamics, map size management, multisession, and computational topics such as parallel computing and timing efficiency. The analysis also focus on the experimental data and evaluation metrics commonly used to assess long‐term autonomy. Moreover, an overview over the bibliographic data of the 142 records provides analysis in terms of keywords and authorship co‐occurrence to identify the terms more used in long‐term SLAM and research networks between authors, respectively. Future studies can update this paper thanks to the systematic methodology presented in the review and the public GitHub repository with all the documentation and scripts used during the review process.
Millimeter-wave (mmWave) cloud radio access networks (CRANs) provide new opportunities for accurate cooperative localization, in which large bandwidths and antenna arrays and increased densities of ...base stations enhance the delay and angular resolution. This study considers the joint location and velocity estimation of user equipment (UE) and scatterers in a three-dimensional mmWave CRAN architecture. Several existing works have achieved satisfactory results by using neural networks (NNs) for localization. However, the black box NN localization method has limited robustness and accuracy and relies on a prohibitive amount of training data to increase localization accuracy. Thus, we propose a model-based learning network for localization to address these problems. In comparison with the black box NN, we combine NNs with geometric models. Specifically, we first develop an unbiased weighted least squares (WLS) estimator by utilizing hybrid delay and angular measurements, which determine the location and velocity of the UE in only one estimator, and can obtain the location and velocity of scatterers further. The proposed estimator can achieve the Cramér-Rao lower bound under small measurement noise and outperforms other state-of-the-art methods. Second, we establish a NN-assisted localization method called NN-WLS by replacing the linear approximations in the proposed WLS localization model with NNs to learn the higher-order error components, thereby enhancing the performance of the estimator, especially in a large noise environment. The solution possesses the powerful learning ability of the NN and the robustness of the proposed geometric model. Moreover, the ensemble learning is applied to improve the localization accuracy further. Comprehensive simulations show that the proposed NN-WLS is superior to the benchmark methods in terms of localization accuracy, robustness, and required time resources.
Mechanisms of Long Noncoding RNA Nuclear Retention Guo, Chun-Jie; Xu, Guang; Chen, Ling-Ling
Trends in biochemical sciences (Amsterdam. Regular ed.),
November 2020, 2020-11-00, 20201101, Letnik:
45, Številka:
11
Journal Article
Recenzirano
Long noncoding RNAs (lncRNAs) are crucial regulators in diverse cellular contexts and biological processes. The subcellular localization of lncRNAs determines their modes of action. Compared to ...mRNAs, however, many mRNA-like lncRNAs are preferentially localized to the nucleus where they regulate chromatin organization, transcription, and different nuclear condensates. Recent studies have revealed the complex mechanisms that govern lncRNA nuclear retention. We review current understanding of how the transcription and processing of lncRNAs, motifs within lncRNAs, and trans-factors coordinately contribute to their nuclear retention in mammalian cells.
Many lncRNAs are transcribed by dysregulated RNA polymerase II and are inefficiently spliced, leading to preferred nuclear localization patterns.Exonic repeats, C-rich motifs, and U1 motifs in lncRNAs promote their specific nuclear localization and function.Trans-factors such as hnRNPs, RNA helicases, and splicing factors facilitate lncRNA nuclear localization by interacting with different cis-acting motifs.The subcellular localization of lncRNA orthologs is regulated during evolution.
Cross-view geo-localization is a task of matching the same geographic image from different views, e.g., unmanned aerial vehicle (UAV) and satellite. The most difficult challenges are the position ...shift and the uncertainty of distance and scale. Existing methods are mainly aimed at digging for more comprehensive fine-grained information. However, it underestimates the importance of extracting robust feature representation and the impact of feature alignment. The CNN-based methods have achieved great success in cross-view geo-localization. However it still has some limitations, e.g., it can only extract part of the information in the neighborhood and some scale reduction operations will make some fine-grained information lost. In particular, we introduce a simple and efficient transformer-based structure called Feature Segmentation and Region Alignment (FSRA) to enhance the model's ability to understand contextual information as well as to understand the distribution of instances. Without using additional supervisory information, FSRA divides regions based on the heat distribution of the transformer's feature map, and then aligns multiple specific regions in different views one on one. Finally, FSRA integrates each region into a set of feature representations. The difference is that FSRA does not divide regions manually, but automatically based on the heat distribution of the feature map. So that specific instances can still be divided and aligned when there are significant shifts and scale changes in the image. In addition, a multiple sampling strategy is proposed to overcome the disparity in the number of satellite images and that of images from other sources. Experiments show that the proposed method has superior performance and achieves the state-of-the-art in both tasks of drone view target localization and drone navigation.