Target Template Research Articles

SiamSTC: Updatable Siamese tracking network via Spatio-Temporal Context

To adapt to the target appearance, some trackers focus only on learning the target model online with the spatial context or only on learning an adaptive template with the temporal context. However, these trackers do not fully utilize spatial and temporal contexts and therefore cannot robustly adapt to sharp appearance variations in challenging situations, such as deformation, rotation, out-of-view, and background clutter. To address the above problem, we propose a novel online updatable Siamese tracker (SiamSTC) that takes advantage of the spatiotemporal context to be aware of the appearance variations in the target to improve the accuracy and robustness of tracking. Specifically, we build a memory bank to collect the spatial and temporal contexts of the target, and design a template update module to learn an adaptive target template using the historical knowledge in memory. We propose a novel update mechanism to ensure that high-quality samples are utilized to update the memory bank. In addition, we propose a target alignment module to explore the fine-grained relationships between the adaptive template and the search image, and locate discriminative regions for tracking based on fine-grained relationships. The proposed method achieves state-of-the-art tracking performance on seven challenging benchmarks, including OTB100, LaSOT, TC128, GOT10k, VOT2016, VOT2018, and VOT2019.

SiamMDM: An Adaptive Fusion Network With Dynamic Template for Real-Time Satellite Video Single Object Tracking

Tracking moving targets in satellite videos has attracted wide attention recently. However, the development of target tracking in satellite videos is much slower than that in general videos for the following key reasons. First, typical moving objects in satellite videos consist of few pixels and lose most of their appearance features, making it difficult for the tracker to distinguish the target from the background. Second, the appearance of satellite video objects often changes due to occlusion, illumination variation, or other factors. Classic Siamese tracking networks only use the first frame as the target template, leading to poor tracking results. Third, when the target is fully occluded, it is difficult for the tracker to recapture the target. To address the above problems, we propose a Siamese tracking network based on multiple(M) response map fusion and spatiotemporal constraints in this paper. By generating response maps at different layers of the tracking network and fusing them adaptively, small objects in the satellite videos can be tracked more accurately. Furthermore, a dynamic(D) template update strategy is proposed to cope with possible changes in the appearance of objects in satellite videos, preventing the high dependence on the initial frame. To recapture the target, a score-guided target motion(M) trajectory prediction model is proposed. We call the proposed Siamese tracking network SiamMDM for short. We conducted complete experiments on SatSOT and SV248S, two large satellite video target tracking datasets. The results show that our method achieves state-of-the-art tracking performance while running at over 110 FPS.

Tracking With Mutual Attention Network

Visual tracking is a visual task that tracks a specific target by only giving its first frame location and size. To punish the low-quality but high-scoring tracking results, researchers resorted to foreground reinforcement learning to suppress the scores of positive samples near edges. However, for training with negative samples, all backgrounds are equally labeled as false. In this way, the interdependence and difference between the foreground and the background are not considered. We interpret the underlying reason for drifts as the imbalance between the embedding of background and foreground information. Specifically, some catastrophic tracking results and common tracking errors should not be treated equally but should strengthen the implicit connection between the foreground and background. In this paper, we propose a Mutual Attention (MA) module to strengthen the interdependence between positive and negative samples. It can aggregate the rich contextual interdependence between the target template and the search area, thereby providing an implicit way to update the target template accordingly. As for the difference, we design a background training enhancement (BTE) mechanism to distinguish negative samples with varying degrees of error, that is, to down-weight outrageous and absurd tracking results to improve the robustness of the tracker. The results on a large number of benchmarks indicate the validity of our results, such as OTB-100, VOT-2018, VOT-2019, and LaSOT.

Expanding the Toolbox of Target Directed Bio-Orthogonal Synthesis: In Situ Direct Macrocyclization by DNA Templates.

Herein, we demonstrate for the first time that noncanonical DNA can direct macrocyclization-like challenging reactions to synthesize gene modulators. The planar G-quartets present in DNA G-quadruplexes (G4s) provide a size complementary reaction platform for the bio-orthogonal macrocyclization of bifunctional azide and alkyne fragments over oligo- and polymerization. G4s immobilized on gold-coated magnetic nanoparticles have been used as target templates to enable easy identification of a selective peptidomimetic macrocycle. Structurally similar macrocycles have been synthesized to understand their functional role in the modulation of gene function. The innate fluorescence of the in situ formed macrocycle has been utilized to monitor its cellular localization using a G4 antibody and its in cell formation from the corresponding azide and alkyne fragments. The successful execution of in situ macrocyclization in vitro and in cells would open up a new dimension for target-directed therapeutic applications.

Expanding the Toolbox of Target Directed Bio‐Orthogonal Synthesis: In Situ Direct Macrocyclization by DNA Templates

AbstractHerein, we demonstrate for the first time that noncanonical DNA can direct macrocyclization‐like challenging reactions to synthesize gene modulators. The planar G‐quartets present in DNA G‐quadruplexes (G4s) provide a size complementary reaction platform for the bio‐orthogonal macrocyclization of bifunctional azide and alkyne fragments over oligo‐ and polymerization. G4s immobilized on gold‐coated magnetic nanoparticles have been used as target templates to enable easy identification of a selective peptidomimetic macrocycle. Structurally similar macrocycles have been synthesized to understand their functional role in the modulation of gene function. The innate fluorescence of the in situ formed macrocycle has been utilized to monitor its cellular localization using a G4 antibody and its in cell formation from the corresponding azide and alkyne fragments. The successful execution of in situ macrocyclization in vitro and in cells would open up a new dimension for target‐directed therapeutic applications.

Two Target Templates for Attentional Guidance and Decision-Making: Relational and Optimal

Two Target Templates for Attentional Guidance and Decision-Making: Relational and Optimal

Search for a fixed target or a varying target: Does the precision of the target template influence distractor location learning?

Search for a fixed target or a varying target: Does the precision of the target template influence distractor location learning?

SGAT: Shuffle and graph attention based Siamese networks for visual tracking.

Siamese-based trackers have achieved excellent performance and attracted extensive attention, which regard the tracking task as a similarity learning between the target template and search regions. However, most Siamese-based trackers do not effectively exploit correlations of the spatial and channel-wise information to represent targets. Meanwhile, the cross-correlation is a linear matching method and neglects the structured and part-level information. In this paper, we propose a novel tracking algorithm for feature extraction of target templates and search region images. Based on convolutional neural networks and shuffle attention, the tracking algorithm computes the similarity between the template and a search region through a graph attention matching. The proposed tracking algorithm exploits the correlations between the spatial and channel-wise information to highlight the target region. Moreover, the graph matching can greatly alleviate the influences of appearance variations such as partial occlusions. Extensive experiments demonstrate that the proposed tracking algorithm achieves excellent tracking results on multiple challenging benchmarks. Compared with other state-of-the-art methods, the proposed tracking algorithm achieves excellent tracking performance.

A colorimetric hydroxy naphthol blue based loop-mediated isothermal amplification detection assay targeting the β-tubulin locus of Sarocladium oryzae infecting rice seed.

Sarocladium oryzae is a widely prevalent seed-borne pathogen of rice. The development of a rapid and on-site detection method for S. oryzae is therefore important to ensure the health of rice seeds. Loop-mediated isothermal amplification (LAMP) is ideal for field-level diagnosis since it offers quick, high-specific amplification of target template sequences at a single temperature. We designed primers based on the β-tubulin region of S. oryzae. The LAMP technique devised was extremely sensitive, detecting the presence of the S. oryzae template at concentrations as low as 10 fg in 30 minutes at 65°C. The assay specificity was confirmed by performing the experiment with genomic DNA isolated from 22 different phytopathogens. Through the addition of hydroxy naphthol blue in the reaction process prior to amplification, a colour shift from violet to deep sky blue was seen in the vicinity of the target pathogen only. Finally, the LAMP assay was validated using live infected tissues, weeds and different varieties of seeds collected from different locations in Tamil Nadu, India. If developed into a detection kit, the LAMP assay developed in this study has potential applications in seed health laboratories, plant quarantine stations, and on-site diagnosis of S. oryzae in seeds and plants.

Prime editing for precise and highly versatile genome manipulation.

Programmable gene-editing tools have transformed the life sciences and have shown potential for the treatment of genetic disease. Among the CRISPR-Cas technologies that can currently make targeted DNA changes in mammalian cells, prime editors offer an unusual combination of versatility, specificity and precision. Prime editors do not require double-strand DNA breaks and can make virtually any substitution, small insertion and small deletion within the DNA of living cells. Prime editing minimally requires a programmable nickase fused to a polymerase enzyme, and an extended guide RNA that both specifies the target site and templates the desired genome edit. In this Review, we summarize prime editing strategies to generate programmed genomic changes, highlight their limitations and recent developments that circumvent some ofthese bottlenecks, and discuss applications and future directions.

Attentional priority is determined by predicted feature distributions.

Visual attention is often characterized as being guided by precise memories for target objects. However, real-world search targets have dynamic features that vary over time, meaning that observers must predict how the target could look based on how features are expected to change. Despite its importance, little is known about how target feature predictions influence feature-based attention, or how these predictions are represented in the target template. In Experiment 1 (N = 60 university students), we show observers readily track the statistics of target features over time and adapt attentional priority to predictions about the distribution of target features. In Experiments 2a and 2b (N = 480 university students), we show that these predictions are encoded into the target template as a distribution of likelihoods over possible target features, which are independent of memory precision for the cued item. These results provide a novel demonstration of how observers represent predicted feature distributions when target features are uncertain and show that these predictions are used to set attentional priority during visual search. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Siamese visual tracking with multilayer feature fusion and corner distance IoU loss

The tracker based on the Siamese network regards tracking tasks as solving a similarity problem between the target template and search area. Using shallow networks and offline training, these trackers perform well in simple scenarios. However, due to the lack of semantic information, they have difficulty meeting the accuracy requirements of the task when faced with complex backgrounds and other challenging scenarios. In response to this problem, we propose a new model, which uses the improved ResNet-22 network to extract deep features with more semantic information. Multilayer feature fusion is used to obtain a high-quality score map to reduce the influence of interference factors in the complex background on the tracker. In addition, we propose a more powerful Corner Distance IoU (intersection over union) loss function so that the algorithm can better regression to the bounding box. In the experiments, the tracker was extensively evaluated on the object tracking benchmark data sets, OTB2013 and OTB2015, and the visual object tracking data sets, VOT2016 and VOT2017, and achieved competitive performance, proving the effectiveness of this method.

Visual tracking with dumbbell selection network

The Siamese network-based trackers aim to train the convolutional neural network offline to match target templates and search regions. Recent researches have managed to adopt deep neural networks to extract sufficient semantic information for the Siamese trackers. However, most of the current methods suffer drastic target appearance variations for 1) failing to encode sufficient localization information of targets and 2) neglecting powerful cross-channel interaction information, thus reducing the learned features’ discriminative and representative ability the tracking accuracy. To remedy these issues, in this article, we propose a Dumbbell Selection Network (DuStNet) by exploring the correlation of the hierarchies of convolutional layers. In concrete, an adaptively Dumbbell Selection mechanism is presented to deal with the targets’ appearance deformation by providing rich semantic and localization information. Furthermore, a CSResNet is developed to improve the residual unit in backbones by strengthening the interdependence between the convolution feature channels. We ingeniously employ the Generalized Intersection over Union (GIoU) to supervise the cross-layer feature-map selection, improving tracking accuracy when utilized as a regression loss simultaneously. Our results suggest that the proposed method is robust to significant appearance variations and can generate more accurate bounding boxes in complicated scenarios. Extensive experimental results on large-scale benchmark datasets prove our method’s effectiveness, which achieves excellent performance on OTB2015, VOT2017, LaSOT, and VOT2019.

A Dynamic Adjust‐Head Siamese network for object tracking

AbstractSiamese network based trackers formulate tracking as a similarity matching problem between a target template and a search region. Virtually all popular Siamese trackers use cross‐correlation to measure the similarity between the deep feature of template and search image. However, the emphasis for feature extraction in different parts of the image are the same. Besides, the global matching between the template and search region also seriously neglects the part‐level information and the deformation of targets during tracking. In this study, to tackle the above issues, a simple but effective Dynamic Adjust‐Head (SiamDAH) model is proposed to extract features from different parts of an object. In addition, an improved pixelwise cross‐correlation model (PWCC) is designed to enhance the naive cross‐correlation operation to produce multiple similarity maps associated with different parts of the target. Experiments on serval challenging benchmarks including OTB‐100, GOT‐10k, LaSOT, and TrackingNet demonstrate that the proposed SiamDAH outperforms many state‐of‐the‐art trackers and achieves leading performance.

Top-down and bottom-up sources of eye-movement guidance during realistic scene search in Alzheimer's disease.

Visual search is a crucial task in daily life, but in Alzheimer's disease (AD) it has usually been investigated using simple arrays. Here, we used scenes depicting real environments and studied the time course of attentional guidance. We analyzed eye-movement differences between mild AD patients and age-matched healthy controls during search. We examined top-down guidance, manipulating the target template (precise picture vs. word cue) and the target-scene semantic consistency (consistent vs. inconsistent), and bottom-up guidance, manipulating the perceptual salience (high vs. low) of targets and distractors. During scene scanning, AD patients had longer search times, made more fixations before the first target fixation, and showed a greater probability of distractor selection, with longer distractor fixation. AD also led to longer target fixation. In patients and controls, picture cues and highly salient targets improved all search phases, whereas consistent targets only improved search initiation (first saccade). Moreover, top-down and bottom-up guidance interacted in initiation and scanning, and this did not differ between the two groups of participants. However, AD led to a smaller picture cue benefit in shortening distractor fixation and greater bottom-up search facilitation during scanning, where a high-salience target reduced the performance gap between patients and controls. Our study shows the importance of top-down and bottom-up guidance, and their integration, in improving search in AD patients. It suggests that precise target cues and, even more, highly salient targets may act as environmental supports that enhance attentional processing and search performance. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Research on Athlete Detection Method Based on Visual Image and Artificial Intelligence System.

Pedestrian detection and tracking based on computer vision has gradually become an international pattern recognition, which is one of the most active research topics in the field of computer vision and artificial intelligence. Using the theoretical results in the field of pattern recognition and computer vision technology, we are committed to detect and track pedestrians from video sequences. In addition to computer vision-based passer-by detection and tracking technology as the key, in the advanced computer vision action and analysis, it has a direct impact on the accuracy and robustness of its understanding. We analyzed various targets, such as subsequent recognition motion and pedestrian motion, and described them as high-level application processing, such as action understanding. In addition, because of the unique texture of human clothes compared with the surrounding natural landscape, they are highly “prominent” from the perspective of human visual system, and they are particularly prominent in the peripheral part of human contact with the background. In this paper, a binary function based on importance is proposed. As the space representation of image itself is not sensitive to noise and local signal, space representation is used. In addition, as an observation model, it can reduce the adverse effects of background noise and local noise on the tracking algorithm. Through the function block tracking, the pedestrian's body can be tracked in detail. At the same time, the color band learning method is used to update the target template online to deal with the changes of target appearance caused by sunshine, pedestrian posture, and other factors. According to the experimental results, even if the appearance and posture of pedestrians change greatly, it has a stable tracking effect.

SiamAGN: Siamese attention-guided network for visual tracking

Most Siamese-based trackers utilize cross-correlation to calculate the similarity scores between the target template and the search image, which may cause the loss of spatial information and lead to inaccurate target estimation. To address this issue, we propose an attention-guided model under the Siamese framework for object tracking, named SiamAGN. Specifically, we combine the template and search image through the proposed feature fusion module. It contains a self-context interaction (SCI) module, cross-context interaction (CCI) module, and target location module (TLM). SCI based on self-attention learns global context by emphasizing channel-wise complementary features. CCI based on cross-attention explores rich dynamic context via the channel interaction between the template and the search image. TLM based on cross-attention reformulates the template according to the pixel-level similarity scores between the template and the search image, which can keep as much spatial information as possible and enable our model to predict more precise bounding boxes. Extensive experimental results on the GOT10k, OTB100, VOT2016, VOT2018, UAV123, and LaSOT benchmarks indicate that the proposed tracker SiamAGN achieves competitive performance compared with state-of-the-art trackers.

Learned distractor rejection persists across target search in a different dimension.

Attention is guided by several factors, including task-relevant target features, which attract attention, but also statistical regularities associated distractors, which repel attention away from themselves. However, whether feature-based distractor regularities (e.g., color) are extracted automatically from a feature dimension orthogonal to the target-guiding dimension (e.g., shape) remains to be tested. In two experiments, we tested if learned distractor rejection by color operated when color was not part of the attentional control settings, specifically, while attention was guided by a shape-based target template. Participants performed a visual search task for a task-relevant shape in displays containing two unsegregated colors. These displays allowed us to manipulate target guidance (based on shape) independently from distractor-based regularities (based on color). In both experiments we found clear evidence for learned distractor rejection: faster mean response times to locate the target when a consistent distractor color was present than when it was absent. Critically, these task-irrelevant learned distractor rejection effects were robust despite strong target guidance by an orthogonal search dimension. These findings corroborate recent demonstrations of learned distractor rejection during strong target guidance, indicating that learned distractor rejection and target guidance can operate on separate feature dimensions.

Antiocclusion Visual Tracking Algorithm Combining Fully Convolutional Siamese Network and Correlation Filtering.

Machine learning only uses single-channel grayscale features to model the target, and the filter solution process is relatively simple. When the target has a large change relative to the initial frame, the tracking effect is poor. When there is the same kind of target interference in the target search area, the tracking results will be poor. The tracking algorithm based on the fully convolutional Siamese network can solve these problems. By learning the similarity measurement function, the similarity between the template and the target search area is evaluated, and the target area is found according to the similarity. It adopts offline pre-training and does not update online for tracking, which has a faster tracking speed. According to this study, (1) considering the accuracy and speed, the target tracking algorithm based on correlation filtering performs well. A sample adaptive update model is introduced to eliminate unreliable samples, which effectively enhances the reliability of training samples. With simultaneous changes in illumination and scale, fast motion and in-plane rotation IPR can still be maintained. (2) Determined by calculating the Hessian matrix, in the Struck function, Bike3 parameter adjustment can achieve fast tracking, and Boat5 ensures that the system stability is maintained in the presence of interference factors. The position of the highest scoring point in the fine similarity score map of the same size as the search image is obtained by bicubic interpolation as the target position. (3) The parallax discontinuity caused by the object boundary cannot be directly processed as a smooth continuous parallax. The MeanShift vector obtained by calculating the target template feature and the feature to be searched can increase the accuracy by 53.1%, reduce the robustness by 31.8%, and reduce the error by 28.6% in the SiamVGG algorithm.

Graph-based Automated Macro-Molecule Assembly.

We present a general molecular framework assembly algorithm that takes a largely arbitrary molecular fragment database and a user-supplied target template graph as input. Automatic assembly of molecular fragments from the database, following a prescribed, user-supplied set of connection rules, then turns the template graph into an actual, chemically reasonable molecular framework. Assembly capabilities of our algorithm are tested by producing several abstract, closed-loop shapes. To indicate a few of many possible application areas we demonstrate a host-guest complex and a road toward catalysis. Postassembly substituent exchange can be used to produce electric fields of desired values at desired points inside the framework or at its surface as a stepping stone toward rationally designed, artificial heterogeneous catalysts.