Template Region Research Articles

Phage-triggered reverse transcription assembles a toxic repetitive gene from a noncoding RNA.

Reverse transcription has frequently been co-opted for cellular functions and in prokaryotes is associated with protection against viral infection, but the underlying mechanisms of defense are generally unknown. Here, we show that in the DRT2 defense system, the reverse transcriptase binds a neighboring pseudoknotted noncoding RNA. Upon bacteriophage infection, a template region of this RNA is reverse transcribed into an array of tandem repeats that reconstitute a promoter and open reading frame, allowing expression of a toxic repetitive protein and an abortive infection response. Biochemical reconstitution of this activity and cryo-electron microscopy provide a molecular basis for repeat synthesis. Gene synthesis from a noncoding RNA is a previously unknown mode of genetic regulation in prokaryotes.

Selective Information Flow for Transformer Tracking

Fully transformer-based one-stream trackers have demonstrated outstanding performance on challenging benchmark datasets over the past three years. These trackers enable bidirectional information flow between all target template and search region tokens to compute attention features without assessing its impact on the tracker’s discriminative capability. Our study found that the information flow from a large portion of background tokens in the search region diminishes the importance of the target-specific features of the template. Moreover, previous transformer-based trackers fail to consider cues from the dynamic background region, even though it contains information about distracting similar objects. To address the identified limitations in transformer tracking, we propose a novel Selective Information Flow Tracking (SIFTrack) framework to enhance the tracker’s discriminative capability by selectively allowing information flow between different types of token groups. In the early encoder layers of the proposed SIFTrack, interactions from all search tokens to target template tokens are blocked to enrich target-specific feature extraction. In the deeper encoder layers, search tokens are partitioned into target and non-target tokens based on their attention scores. Then, bidirectional flow from target search tokens to template tokens is allowed to capture the appearance changes of the target. In addition, by including tokens from the dynamic background, SIFTrack effectively avoids distractor objects by capturing cues from the area surrounding the target. The proposed SIFTrack demonstrated outstanding performance in challenging benchmarks, particularly excelling in the one-shot tracking benchmark GOT-10k, achieving an average overlap of 74.6%. The code, models, and results of this work are available at https://github.com/JananiKugaa/SIFTrack.

Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking With Transformer.

With the prevalent use of LiDAR sensors in autonomous driving, 3D point cloud object tracking has received increasing attention. In a point cloud sequence, 3D object tracking aims to predict the location and orientation of an object in consecutive frames. Motivated by the success of transformers, we propose Point Tracking TRansformer (PTTR), which efficiently predicts high-quality 3D tracking results in a coarse-to-fine manner with the help of transformer operations. PTTR consists of three novel designs. 1) Instead of random sampling, we design Relation-Aware Sampling to preserve relevant points to the given template during subsampling. 2) We propose a Point Relation Transformer for effective feature aggregation and feature matching between the template and search region. 3) Based on the coarse tracking results, we employ a novel Prediction Refinement Module to obtain the final refined prediction through local feature pooling. In addition, motivated by the favorable properties of the Bird's-Eye View (BEV) of point clouds in capturing object motion, we further design a more advanced framework named PTTR++, which incorporates both the point-wise view and BEV representation to exploit their complementary effect in generating high-quality tracking results. PTTR++ substantially boosts the tracking performance on top of PTTR with low computational overhead. Extensive experiments over multiple datasets show that our proposed approaches achieve superior 3D tracking accuracy and efficiency.

Siamese Tracking Network with Multi-attention Mechanism

Object trackers based on Siamese networks view tracking as a similarity-matching process. However, the correlation operation operates as a local linear matching process, limiting the tracker’s ability to capture the intricate nonlinear relationship between the template and search region branches. Moreover, most trackers don’t update the template and often use the first frame of an image as the initial template, which will easily lead to poor tracking performance of the algorithm when facing instances of deformation, scale variation, and occlusion of the tracking target. To this end, we propose a Simases tracking network with a multi-attention mechanism, including a template branch and a search branch. To adapt to changes in target appearance, we integrate dynamic templates and multi-attention mechanisms in the template branch to obtain more effective feature representation by fusing the features of initial templates and dynamic templates. To enhance the robustness of the tracking model, we utilize a multi-attention mechanism in the search branch that shares weights with the template branch to obtain multi-scale feature representation by fusing search region features at different scales. In addition, we design a lightweight and simple feature fusion mechanism, in which the Transformer encoder structure is utilized to fuse the information of the template area and search area, and the dynamic template is updated online based on confidence. Experimental results on publicly tracking datasets show that the proposed method achieves competitive results compared to several state-of-the-art trackers.

Highly compact adaptive network based on transformer for RGBT tracking

RGBT tracking is a challenging task that requires robust fusion of visible images (RGB) and thermal infrared images (TIR) to handle various scenarios, such as illumination changes, occlusions, and camouflage. The current popular RGBT trackers mostly based on two stream Siamese trackers. They tend to separately extracts template and search images region features, which neglects relationship between target and background. Moreover, they do not fuse RGB and TIR features properly, limiting their ability to utilize complementary features. To address these issues, we introduce a highly compact adaptive transformer-based network that unifies the process of feature extracting and correlation between template and search images. In this way, the compact network has dual-branches. They can combine feature extraction and correlation for different modalities of template images and search images. Meanwhile, we introduce a cross-modal weight redistribution module (CMWR) for multi-modal fusion. This adaptive fusion scheme learns discriminative features of RGB and TIR data and assigns weights to them, enabling them to complement each other. Furthermore, to address the issue of tracking targets of different scales, we design scale-adaptive optimization pyramid module (SAOP) that adapt to objects of different sizes. Our method achieves exceptional performance on the GTOT, RGBT234 and LasHeR datasets, surpassing most of the existing methods. The results are consistent across multiple datasets, demonstrating the effectiveness and superiority of our approach. And our code is released at: https://github.com/ELOESZHANG/HCANet.

Near-infrared fluorescence lymph node template region dissection plus backup lymphadenectomy in open radical cystectomy for bladder cancer using an innovative handheld device: A single center experience.

The extent of pelvic lymphadenectomy (PLND) as part of radical cystectomy (RC) for bladder cancer (BC) remains unclear. Sentinel-based and lymphangiographic approaches could lead to reduced morbidity without sacrificing oncologic safety. To evaluate the feasibility and diagnostic value of fluorescence-guided template sentinel region dissection (FTD) using a handheld near-infrared fluorescence (NIRF) camera in open radical cystectomy. After peritumoral cystoscopic injection of indocyanine green (ICG) 21 patients underwent open RC with FTD due to BC between June 2019 and June 2021. Intraoperatively, the FIS-00 Hamamatsu Photonics® NIRF camera was used to identify and resect fluorescent template sentinel regions (FTRs) followed by extended pelvic lymphadenectomy (ePLND) as oncological back-up. Descriptive analysis of positive and negative results per template region. FTRs were identified in all 21 cases. Median time (range) from ICG injection to fluorescence detection was 75 (55-125) minutes. On average (SD), 33.4 (9.6) lymph nodes were dissected per patient. Considering template regions as the basis of analysis, 67 (38.3%) of 175 resected regions were NIRF-positive, with 13 (7.4%) regions harboring lymph node metastases. We found no metastatic lymph nodes in NIRF-negative template regions. Outside the standard template, two NIRF-positive benign nodes were identified. The concept of NIRF-guided FTD proved for this group all lymph node metastases to be found in NIRF-positive template regions. Pending validation in a larger collective, resection of approximately 40% of standard regions may be sufficient and may result in less morbidity.

CorrFormer: Context-aware tracking with cross-correlation and transformer

The fusion of the template and search region features plays a significant role in deep learning-based trackers. In Siamese-based trackers, different cross-correlation operations are commonly used to fuse features, which cannot obtain global connections. On the other hand, transformer-based trackers use attention mechanism to fuse features, which cannot suppress the interference of distractors in the background. Furthermore, existing trackers use regression and classification heads with the same structure, which leads to lack a deeper understanding of these two different tasks. To address these problems, we firstly propose a feature enhancement-fusion network (FEFN) based on cross-correlation and transformer, with two Encoders that employ self-attention and a Decoder that removes cross-attention to adapt to the tracking task. Using the FEFN to combine the advantages of Siamese-based and transformer-based trackers, our tracker establishes global connections while effectively suppressing the distractors. We also propose a novel decoupled head, designing a spatial sensitive classification head and a global information sensitive regression head, which helps the context-aware tracker locate the target more accurately. Our proposed tracker obtains 0.710 of AO, 0.814 of SR0.5 and 0.657 of SR0.75 on the GOT-10k test set, and achieves real-time requirement at 36.99FPS.

Spatial-Arrangement-Assisted Emission Energy Fine Tuning of CdSe Quantum Dots (QDs) in QD–Block Copolymer Complexes

Quantum dots (QDs) exhibit size-dependent optical properties, where both the absorption and fluorescence energy levels vary with QD size. However, this dependence results in a discontinuity of intrinsically accessible energy levels for the bandgap, posing challenges in achieving precise energy tuning within a specific range. Herein, we demonstrate emission energy control of QDs with identical absorption energy levels by manipulating the spatial arrangement of QDs within QD–polymer complexes through hydrophobic interactions. The phase behavior of the QD–polymer complexes was modulated by adjusting the mass fraction of hydrophilic and hydrophobic blocks in the block copolymer, utilizing two types of amphiphilic block copolymers and varying temperatures. The QDs were spontaneously trapped within the hydrophobic region of the polymer template in water, resulting in spherical, cylindrical, and vesicle structures of QD–polymer complexes, corresponding to spherical, cylindrical, and layered assemblies of QDs, respectively. Depending on the QDs’ location within the QD–polymer complex, the surface area in contact with water varied, leading to different degrees of oxidation and, consequently, a change in the fluorescence energy level of QDs. This study introduces a novel method to fine tune the emission energy (<15 eV) of QDs by adjusting the polymer form factor without complicated procedures.

CVTrack: Combined Convolutional Neural Network and Vision Transformer Fusion Model for Visual Tracking.

Most single-object trackers currently employ either a convolutional neural network (CNN) or a vision transformer as the backbone for object tracking. In CNNs, convolutional operations excel at extracting local features but struggle to capture global representations. On the other hand, vision transformers utilize cascaded self-attention modules to capture long-range feature dependencies but may overlook local feature details. To address these limitations, we propose a target-tracking algorithm called CVTrack, which leverages a parallel dual-branch backbone network combining CNN and Transformer for feature extraction and fusion. Firstly, CVTrack utilizes a parallel dual-branch feature extraction network with CNN and transformer branches to extract local and global features from the input image. Through bidirectional information interaction channels, the local features from the CNN branch and the global features from the transformer branch are able to interact and fuse information effectively. Secondly, deep cross-correlation operations and transformer-based methods are employed to fuse the template and search region features, enabling comprehensive interaction between them. Subsequently, the fused features are fed into the prediction module to accomplish the object-tracking task. Our tracker achieves state-of-the-art performance on five benchmark datasets while maintaining real-time execution speed. Finally, we conduct ablation studies to demonstrate the efficacy of each module in the parallel dual-branch feature extraction backbone network.

Measuring telomerase activity using TRAP assays.

Telomerase is a reverse transcriptase that consists of the telomerase reverse transcriptase (TERT) protein and the telomerase RNA component TERC which also harbors the template region for telomere synthesis. In its canonical function the enzyme adds single-stranded telomeric hexanucleotides de novo to the ends of linear chromosomes, telomeres, in telomerase-positive cells such as germline, stem- and cancer cells. This potential biochemical activity of telomerase can be measured with the help of a telomerase repeat amplification protocol (TRAP) which often includes a PCR amplification due to the low abundance of telomerase in most cells and tissues. The current chapter describes various TRAP methods to detect telomerase activity (TA) using gel-based methods, its advantages and deficits, how to perform an ELISA-based TRAP assay and how best to interpret its results. Since development of the TRAP assay in 1994, there have been numerous modifications and adaptations of the method from real-time PCR analysis, isothermal amplification and nanotechnology to CRISPR/Cas-based methods which will be briefly mentioned. However, it is not possible to cover all different TRAP methods and thus there is no comprehensiveness claimed by this chapter. Instead, the author describes various aspects of using TRAP assays including required controls, sample preparation, etc. in order to avoid pitfalls and set-backs in applying this rather complex and demanding technique. The TRAP assay is particularly important to support clinical diagnosis of cancer, analyze tumor therapy as well as to evaluate various approaches to inhibit TA as a form of anti-cancer therapy.

Analysis of Telomerase RNA Structure in Physcomitrium patens Indicates Functionally Relevant Transitions Between OPEN and CLOSED Conformations

Telomerase RNA (TR) conformation determines its function as a template for telomere synthesis and as a scaffold for the assembly of the telomerase nucleoprotein complex. Experimental analyses of TR secondary structure using DMS-Map Seq and SHAPE-Map Seq techniques show its CLOSED conformation as the consensus structure where the template region cannot perform its function. Our data show that the apparent discrepancy between experimental results and predicted TR functional conformation, mostly ignored in published studies, can be explained using data analysis based on single-molecule structure prediction from individual sequencing reads by the recently established DaVinci method. This method results in several clusters of secondary structures reflecting the structural dynamics of TR, possibly related to its multiple functional states. Interestingly, the presumed active (OPEN) conformation of TR corresponds to a minor fraction of TR under in vivo conditions. Therefore, structural polymorphism and dynamic TR transitions between CLOSED and OPEN conformations may be involved in telomerase activity regulation as a switch that functions independently of total TR transcript levels.

In situ nanofibers patterned deposition based on electrostatic attraction–repulsion induction

The in situ nanofibers patterned deposition technique, enabling polymer nanofibers to be deposited into pre-designed patterns with high accuracy, have an extensive application prospects in many fields. Currently, the solutions of realizing the highly accurate patterning deposition all have shortcomings, such as simple pattern structure, inaccurate nanofibers deposition, fewer available material types, complex and expensive manufacturing processes, chemical pollution, etc. Here, in order to enable polymer nanofibers to be deposited into pre-designed patterns with comprehensive advantages including highly accurate deposition of multiple pattern structures, more available materials, economically efficient and environmentally friendly, an in-situ nanofibers patterned deposition technique(in-situ NFs-PDT) is proposed, based on the induction of attractive and repulsive forces of static electricity. This in-situ NFs-PDT is achieved by improving the collection terminal of electrospinning, which includes a pre-designed target pattern electrode, an insulating layer and a repulsive positive bottom electrode. By controlling the repulsion voltage and thickness of target pattern electrode, the amount of nanofibers deposited in the unpatterned template region can reach 0. In addition, in order to validate and demonstrate high-accuracy in-situ NFs-PDT, a sensor array that can sense the tensile deformation of the epidermal layer of human skin is successfully designed and fabricated.

Consistent Weighted Correlation-Based Attention for Transformer Tracking

Attention mechanism takes a crucial role among the key technologies in transformer-based visual tracking. However, the current methods for attention computing neglect the correlation between the query and the key, which results in erroneous correlations. To address this issue, a CWCTrack framework is proposed in this study for transformer visual tracking. To balance the weights of the attention module and enhance the feature extraction of the search region and template region, a consistent weighted correlation (CWC) module is introduced into the cross-attention block. The CWC module computes the correlation score between each query and all keys. Then, the correlation multiplies the consistent weights of the other query–key pairs to acquire the final attention weights. The weights of consistency are computed by the relevance of the query–key pairs. The correlation is enhanced for the relevant query–key pair and suppressed for the irrelevant query–key pair. Experimental results conducted on four prevalent benchmarks demonstrate that the proposed CWCTrack yields preferable performances.

IoUformer: Pseudo-IoU prediction with transformer for visual tracking

Siamese tracking has witnessed tremendous progress in tracking paradigm. However, its default box estimation pipeline still faces a crucial inconsistency issue, namely, the bounding box decided by its classification score is not always best overlapped with the ground truth, thus harming performance. To this end, we explore a novel simple tracking paradigm based on the intersection over union (IoU) value prediction. To first bypass this inconsistency issue, we propose a concise target state predictor termed IoUformer, which instead of default box estimation pipeline directly predicts the IoU values related to tracking performance metrics. In detail, it extends the long-range dependency modeling ability of transformer to jointly grasp target-aware interactions between target template and search region, and search sub-region interactions, thus neatly unifying global semantic interaction and target state prediction. Thanks to this joint strength, IoUformer can predict reliable IoU values near-linear with the ground truth, which paves a safe way for our new IoU-based siamese tracking paradigm. Since it is non-trivial to explore this paradigm with pleased efficacy and portability, we offer the respective network components and two alternative localization ways. Experimental results show that our IoUformer-based tracker achieves promising results with less training data. For its applicability, it still serves as a refinement module to consistently boost existing advanced trackers.

Visible-infrared image matching based on parameter-free attention mechanism and target-aware graph attention mechanism

Image matching involves identifying the template region in the search image after selecting it in the template image. Image matching, as a basic task, is a pre-order step of many image processing. Because of the different imaging principles of visible and infrared images, the difference between visible and infrared images is large. Compared with the matching of visible images, it is more difficult to match visible and infrared images. Due to the characteristics of infrared images, many targets in infrared images do not have clear outlines, which makes it difficult to distinguish targets and backgrounds in infrared images during the matching process. Regarding the issue above, we propose a network named VINet for visible infrared image matching, and design a feature extraction network AM-Net based on Inception-v3. In order to improve the feature expression ability of the network, we added a parameter-free attention mechanism to the AM-Net network, which improved the network expression ability without introducing new parameters. In addition, we added DropBlock to the AM-Net network, which can achieve better regularization through the DropBlock. To accurately differentiate the background from the target and obtain the target position, we integrate target-aware graph attention in VINet and employ the CIoU loss during training. To address the limited number of visible and infrared image matching datasets, we repurpose existing datasets by relabeling them to obtain new training and testing sets. The experimental results indicate that our method can achieve better matching results compared with other state-of-the-art methods.

First Report of Root Rot Caused by Phytophthora lacustris on alder (Alnus lusitanica) in Spain.

Alder decline caused by Phytophthora species is considered one of Europe´s most important diseases of natural ecosystems. In Spain, P. x alni, P. uniformis, P. x multiformis and P. plurivora have been detected in association with root and collar rot in riparian alder populations (Pintos et al. 2010, 2012, 2017; Haque et al. 2014). During the active growth periods 2020-2021, a field survey of the newly designed species Alnus lusitanica (Vít et al. 2017) was carried out at the most symptomatic areas along the Miño-Sil river basin in Galicia and León (NW-Spain). Samples of bark, root, rizosphere soil of declining trees, and river water were collected. Symptoms, similar to those caused by other Phytophthora species, included low leaf density of the canopy, generally with smaller and chlorotic leaves, and branches with dry tips. In some cases, the presence of cankers on the trunk were observed (Figure 1). Necrotic lesions were transferred onto V8-PARPH, a Phytophthora selective medium. Soil and water were baited with carnation petals. Three isolates of one Phytophthora species was recovered: two from the roots of trees, and one from river water at three different sites. The isolates were transferred to V8 agar and incubated a 22ºC in the dark. Colonies had petaloid patterns, and their optimum growth temperature ranged from 25 to 30 °C. In soil extract, non-caducous, non-papillate and ovoid sporangia were produced. Sporangia averaged 41.0×29.4 μm with a length/breadth ratio of 1.39. Internal proliferation occurred (Figure 2). No sexual structures were observed . Genomic DNA was extracted from mycelium obtained from pure cultures of three Phytophthora isolates. The ITS region of the ribosomal DNA template was performed by nested PCR using DC6 (Cooke et al. 2000) and ITS4 (White et al. 1990) in the first round, and ITS6 (Cooke et al. 2000) and ITS4 in the second. The mitochondrial gene cox1 was amplified with primers CoxF4N and CoxR4N (Kroon et al. 2004). BLASTn analyses showed 100% identity to the type of P. lacustris (AF266793, 156 matching bp) for ITS, and 100% identity to the ex-type of P. lacustris (MH136916, 596 matching bp) for the cox1 sequence. Phylogenetic analysis indicated that our isolates were localized in the same evolutionary branch as P. lacustris based on consense sequences of ITS and cox1 sequences. The ITS and cox1 sequences generated in this study were deposited in GenBank with accession number OP588369 and OP548051, and one isolate isolated from root (CECT 21212) was submitted to the Spanish Type Culture Collection (Paterna, Valencia). Pathogenicity tests with isolate CECT 21212 were conducted on ten 3-year-old alders (A. lusitanica) growing in free draining 5 L pots. One shallow cut was made into the cambium at the root collar level. A colonized 5-mm mycelial agar plug, from a 7-day-old culture was inserted into every wound (mycelial surface face-down) and sealed with Parafilm®. Five control plants were inoculated with a sterile agar plug. Plants were kept in a controlled chamber at 25 ºC and 80% humidity. After a 3-week incubation period, inoculated plants showed dieback symptoms and necrosis of the inner bark tissue (Figure 3). Lesion lengths ranged from 2 to 8 cm. Control plants remained symptomless. P. lacustris was recovered from all inoculated plants, but not from the control ones. To our knowledge, this is the first report of P. lacustris causing root rot on alders in Spain. This new detection represents an increased threat to riparian alders by the presence of an additional Phytophthora species associated with alder decline, since P. lacustris can readily adapt to a wide variety of climatic conditions with the ability to infect different hosts (Nechwatal et al. 2013).

Spatio-temporal hierarchical feature transformer for UAV object tracking

Most existing Siamese network based trackers calculate the similarity between template and search region through a simple correlation operation, and these trackers classify and regress the target object based on the similarity maps obtained by the correlation operation. However, the correlation operation itself is a local linear matching process, if these Siamese network based trackers decide only on feature maps obtained by the correlation operation, using only a single similarity feature map will reduce position accuracy in challenging environments, using multiple similarity feature maps separately will introduce complicated computations. Thus, we propose an efficient spatio-temporal hierarchical feature transformer (STHFT) for UAV tracking. The spatio-temporal hierarchical similarity maps generated by the multi-level convolutional layers are sent to the transformer to achieve the interactive fusion of shallow spatio-temporal and deep semantic information. Therefore, our STHFT not only enhances the learning ability for global contextual information, but also effectively learns the interdependencies among multi-level features. Moreover, STHFT treats object tracking as a straightforward bounding box prediction task, only using a simple fully convolutional neural network to directly estimate the corners of the target and localize it. We have conducted extensive experiments on the UAV123 and UAV20L benchmarks, STHFT outperforms other traditional trackers. Specifically, compared to the conventional tracker DaSiamRPN the success and accuracy scores of STHFT improved by 7.3% and 6.5% on the UAV123 dataset and 10.9% and 10.4% on UAV20L, which show that STHFT is robust to tracking challenges.

Multiple templates transformer for visual object tracking

Matching the similarity between a template and search region is crucial in Siamese trackers. However, due to the limited information provided by a fixed template, existing trackers are not robust enough in complex scenarios, such as severe deformation, background clutters, out-of-view, illumination variation, low resolution, scale variation, fast motion, and full occlusion. Therefore, it is essential to use an informative template. Additionally, since the Transformer has superior model capability compared to traditional cross-correlation in tracking, some Siamese trackers have integrated Transformers and achieved exceptional performance. In this paper, we present a novel tracking architecture with Multiple Templates Transformer (MTT) to address the above issues. By utilizing multiple templates, the proposed method can grasp more contextual information and historical changes about the target, which can be leveraged to enhance the response in the search region using an encoder-decoder framework. We also explore different mechanisms to fuse templates effectively to achieve higher accuracy. We evaluate MTT in several famous benchmarks such as GOT-10k, TrackingNet, UAV123, OTB2015, VOT2018, and LaSOT. Extensive experimental results indicate that our tracker is capable of achieving better robustness in the face of different challenges while maintaining a considerable real-time speed.

Single Object Tracking in Satellite Videos Based on Feature Enhancement and Multi-Level Matching Strategy

Despite significant advancements in remote sensing object tracking (RSOT) in recent years, achieving accurate and continuous tracking of tiny-sized targets remains a challenging task due to similar object interference and other related issues. In this paper, from the perspective of feature enhancement and a better feature matching strategy, we present a tracker SiamTM specifically designed for RSOT, which is mainly based on a new target information enhancement (TIE) module and a multi-level matching strategy. First, we propose a TIE module to address the challenge of tiny object sizes in satellite videos. The proposed TIE module goes along two spatial directions to capture orientation and position-aware information, respectively, while capturing inter-channel information at the global 2D image level. The TIE module enables the network to extract discriminative features of the targets more effectively from satellite images. Furthermore, we introduce a multi-level matching (MM) module that is better suited for satellite video targets. The MM module firstly embeds the target feature map after ROI Align into each position of the search region feature map to obtain a preliminary response map. Subsequently, the preliminary response map and the template region feature map are subjected to the Depth-wise Cross Correlation operation to get a more refined response map. Through this coarse-to-fine approach, the tracker obtains a response map with a more accurate position, which lays a good foundation for the prediction operation of the subsequent sub-networks. We conducted extensive experiments on two large satellite video single-object tracking datasets: SatSOT and SV248S. Without bells and whistles, the proposed tracker SiamTM achieved competitive results on both datasets while running at real-time speed.

PRAT: Accurate object tracking based on progressive attention

Object tracking aims to estimate the position of a given object in subsequent video sequences. One of the research focuses in tracking is feature fusion as the similar response maps generated by feature fusion can significantly affect tracking accuracy. However, traditional naive correlation and depthwise correlation blur the spatial information and do not perform well in low resolution, similar objects, partial occlusion and other scenes. In this paper, we propose a progressive attention tracker called PRAT. It performs sufficient similarity learning between the template and search region to achieve more accurate object tracking. Specifically, PRAT performs self-enhancement on template features, and uses unidirectional cross enhancement and progressive enhancement to fuse template features into search features. Therefore, the search region features have the ability of target perception. In addition, we also design a convolution-based network to replace the FFN in the original Transformer to enhance local semantics. Experiments on six challenging benchmarks show that our PRAT achieves state-of-the-art performance. Particularly, on the challenging UAV123, PRAT sets a new record with 0.703 SUC score. PRAT runs at 63 fps on GPU.