Dynamic Template Research Articles

Going through the motions: Biasing of dynamic attentional templates.

Attention must coordinate with memory to actively anticipate sensory input and guide action. Memory content may be biased away from veridical when it is functionally adaptive. So far, research has considered the biasing of still features in static displays. It is unknown whether the biasing of attentional templates can functionally adapt dynamic stimuli to facilitate search when targets and distractors compete within temporally extended contexts. Biasing of dynamic templates would require learning and modulatory mechanisms capable of abstracting over space and time to guide perception. Four experiments used a novel dynamic visual search task combined with a memory probe to test whether dynamic attentional templates can be biased. In Experiments 1-3, participants searched for a moving target among distractors that systematically moved either clockwise or counterclockwise relative to the target. On memory probe trials, participants recalled the target direction as biased away from the distractors. The distortion bias was adaptively changed (Experiment 2), grew over time (Experiment 2), and occurred even when motion direction was not the target-defining feature (Experiment 3). Experiment 4 manipulated the speed of targets and distractors to test the generalizability of the findings. Participants searched for a target of a given speed among faster or slower distractors. Memory probing revealed that participants remembered the target speed as biased away from that of distractors. Across different tasks, the magnitude of the biasing correlated positively with search performance. Our findings provide compelling evidence that dynamic stimulus attributes in attentional templates can become functionally biased when adaptive. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Prey detection by a stepwise visual template matching mechanism

Predators can improve prey capture using a search image, and recent prey provide a visual template with which subsequent prey are compared. Considering trout feeding responses to mayfly prey of different sizes and phenological availability across years, we tested if changing relative abundances (ratios) of prey of the same species, but different body sizes, shifted trout feeding behaviour. For example, we hypothesized that a feeding switch from larger to smaller prey required continuous exposure to the novel smaller prey. The hypothesis that continuous exposure to novel small prey results in their acceptance was not supported. Rather, we discovered that trout identify novel prey using a dynamic stepwise visual neural template prey matching process, which involves the formation of focal prey template based on size or type, rejection of novel prey that do not match the size or type templates and modification of the existing or development of multiple prey templates that eventually enabled recognition of novel, small prey. We also discovered trout store multiple visual prey templates in memory. These results have implications for predator and prey dynamics, optimal foraging, the persistence of rare prey, prey species coexistence and predator selection on prey phenology.

Visual object tracking based on adaptive rain streak removal and fused dynamic template matching

Visual object tracking based on adaptive rain streak removal and fused dynamic template matching

Transformer object tracking algorithm based on spatiotemporal template focal attention

Existing visual object tracking methods only use the target area of the first frame as a template, which makes it easy to fail in fast-changing and complex backgrounds. To solve this problem, this paper proposes a Transformer-based object tracking algorithm that focuses on the target focus information in the template and dynamically updates the template features. In order to reduce the interference of background information on attention, this algorithm uses a sparse Transformer module to achieve the interaction of feature information; a template focus attention module is also proposed to focus on the dynamic template features and the initial template features to retain the highly reliable feature information in the initial template. Experimental results show that the success rate and accuracy of this algorithm in the 0TB100 benchmark test are and respectively 70.9%, 91.6%and the success rate and accuracy are improved by 4.11%and respectively compared with the similar template update algorithm STARK 3.27%. This algorithm effectively addresses the limitations of existing visual object tracking methods and improves the accuracy and robustness of tracking.

VLFSE: Enhancing visual tracking through visual language fusion and state update evaluator

Recently, visual tracking algorithms have achieved impressive results by combining dynamic templates. However, the instability of visual images and the incorrect timing of template updates lead to decreased tracking accuracy and stability in intricate scenarios. To address these issues, we propose a visual tracking algorithm through visual language fusion and a state update evaluator (VLFSE). Specifically, our approach introduces a multimodal attention mechanism that uses self-attention to mine and integrate information from diverse sources effectively. This mechanism ensures a richer, context-aware representation of the target, enabling more accurate tracking even in complex scenes. Moreover, we recognize the critical need for precise template updates to maintain tracking accuracy over time. To this end, we develop a state update evaluator, a component trained online to assess the necessity and timing of template updates accurately. This evaluator acts as a safeguard, preventing erroneous updates and ensuring the tracker adapts optimally to changes in the target’s appearance. The experimental results on challenging visual language tracking datasets demonstrate our tracker’s superior performance, showcasing its adaptability and accuracy in complex tracking scenarios.

In situ growth of hydrophobic 3D porous Zn@Ag electrode in achieving excellent performance for eCO2RR

Hydrophobic microenvironment is favorable to CO2 electroreduction, which can enhance CO2 transport by overcoming the low solubility limitation of CO2 in aqueous electrolytes. Up to now, hydrophobic electrode is normally prepared by coating an external hydrophobic layer or by hydrophobic in situ synthesis. Nevertheless, both methods suffer from the low current density of the reaction. To resolve this problem, a three-dimensional (3D) volumetrically electroplated PTFE (polytetrafluoroethylene) porous electrode was produced via PTFE-assisted hydrogen bubble dynamic template method, which has a heterogeneous structure with a hydrophilic surface and hydrophobic interior. The hydrophobic 3D porous Zn@Ag electrode displayed a high activity up to −45 mA cm−2 with over 92.1 % FECO in a microchannel electrolyzer with KHCO3 solution, which is 3 times higher than a bare ZnAg foam electrode without PTFE (only −15 mA cm−2 with over 92.0 % FECO). Furthermore, it achieved a FECO over 91.0 % at a current density up to −250 mA cm−2 in a flow cell with 1 M KOH electrolyte. The excellent performance was attributed to the accessibility of the active sites to CO2 in the interior of the electrode, because the pore blocking problem by liquid electrolyte was solved in the case of the hydrophobic interior.

Temporal relation transformer for robust visual tracking with dual-memory learning

Recently, transformer trackers mostly associate multiple reference images with the search area to adapt to the changing appearance of the target. However, they ignore the learned cross-relations between the target and surrounding, leading to difficulties in building coherent contextual models for specific target instances. This paper presents a Temporal Relation Transformer Tracker (TRTT) for robust visual tracking, providing a concise approach to modeling temporal relations by dual target memory learning. Specifically, a temporal relation transformer network generates paired memories based on static and dynamic templates, which are reinforced interactively. The memory contains implicit relation hints that capture the relations between the tracked object and its immediate surroundings. More importantly, to ensure consistency of target instance identities between frames, the relation hints from previous frames are transferred to the current frame for merging temporal contextual attention. Our method also incorporates mechanisms for reusing favorable cross-relations and instance-specific features, thereby overcoming background interference in complex spatio-temporal interactions through a sequential constraint. Furthermore, we design a memory token sparsification method that leverages the key points of the target to eliminate interferences and optimize attention calculations. Extensive experiments demonstrate that our method surpasses advanced trackers on 8 challenging benchmarks while maintaining real-time running speed.

Nanoporous Gold-Modified Screen-Printed Electrodes for the Simultaneous Determination of Pb2+ and Cu2+ in Water.

In this study, nanoporous gold (NPG) was deposited on a screen-printed carbon electrode (SPCE) by the dynamic hydrogen bubble template (DHBT) method to prepare an electrochemical sensor for the simultaneous determination of Pb2+ and Cu2+ by square wave anodic stripping voltammetry (SWASV). The electrodeposition potential and electrodeposition time for NPG/SPCE preparation were investigated thoroughly. Scanning electron microscopy (SEM) and energy-dispersive X-ray diffraction (EDX) analysis confirmed successful fabrication of the NPG-modified electrode. Electrochemical characterization exhibits its superior electron transfer ability compared with bare and nanogold-modified electrodes. After a comprehensive optimization, Pb2+ and Cu2+ were simultaneously determined with linear range of 1-100 μg/L for Pb2+ and 10-100 μg/L for Cu2+, respectively. The limits of detection were determined to be 0.4 μg/L and 5.4 μg/L for Pb2+ and Cu2+, respectively. This method offers a broad linear detection range, a low detection limit, and good reliability for heavy metal determination in drinking water. These results suggest that NPG/SPCE holds great promise in environmental and food applications.

Dynamic breath figure template for electrohydrodynamic lithography: Formation of multiscale micro-craters and wells

In the rapidly evolving landscape of nanofabrication, developing novel pathways that allow control over micro- and nano-lengthscales is essential for advancing different technological applications. A curable multiscale pattern, consisting of feature sizes ranging from ∼ 3 µm to ∼ 60 µm with periodicity from ∼4 µm to ∼300 µm, fabricated on a deformable elastomeric substrate is demonstrated through a soft lithographic pathway without using any expensive equipment. The modified breath figure lithography has been used in conjunction with micro-contact printing, and UV-plasma treatment to fabricate the patterned substrate suitable for electrohydrodynamic lithography. This integration showcases the adaptability and enhances the scalability and efficiency of the process of breath figure lithography in different fabrication methods. This process has a scope to lower the feature size in each step. Thus, it offers a tool for adjusting wavelength and altering the feature shape and size of the microstructures (micro craters and microwells). This whole process includes the preservation of soft microstructures through rheological petrification. The novelty of this work lies in its experimental techniques within the concept of soft lithographic patterning that solely depends upon conventional processes like microcontact printing, breath figure lithography, elastomeric surface modification, and electrohydrodynamic lithography. Ultimately, four different lengthscales in the feature sizes are achieved using this easy-to-fabricate technique.

Spatial-Temporal Contextual Aggregation Siamese Network for UAV Tracking

In recent years, many studies have used Siamese networks (SNs) for UAV tracking. However, there are two problems with SNs for UAV tracking. Firstly, the information sources of the SNs are the invariable template patch and the current search frame. The static template information lacks the perception of dynamic feature information flow, and the shallow feature extraction and linear sequential mapping severely limit the mining of feature expressiveness. This makes it difficult for many existing SNs to cope with the challenges of UAV tracking, such as scale variation and viewpoint change caused by the change in height and angle of the UAV, and the challenges of background clutter and occlusion caused by complex aviation backgrounds. Secondly, the SNs trackers for UAV tracking still struggle with extracting lightweight and effective features. A tracker with a heavy-weighted backbone is not welcome due to the limited computing power of the UAV platform. Therefore, we propose a lightweight spatial-temporal contextual Siamese tracking system for UAV tracking (SiamST). The proposed SiamST improves the UAV tracking performance by augmenting the horizontal spatial information and introducing vertical temporal information to the Siamese network. Specifically, a high-order multiscale spatial module is designed to extract multiscale remote high-order spatial information, and a temporal template transformer introduces temporal contextual information for dynamic template updating. The evaluation and contrast results of the proposed SiamST with many state-of-the-art trackers on three UAV benchmarks show that the proposed SiamST is efficient and lightweight.

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.

Dynamic predictive templates in perception

Hallucinations are vivid and transient experiences of objects, such as images or sounds, that occur in the absence of a corresponding stimulus.1,2,3,4,5,6,7,8,9 To understand the neurocomputational mechanisms of hallucinations, cognitive neuroscience has focused on experiments that induce false alarms (FAs) in healthy participants,1,2,3,4,5,9 psychosis-prone individuals,1,3,4 and patients diagnosed with schizophrenia.5 FAs occur when participants make decisions about difficult-to-detect stimuli and indicate the presence of a signal that was, in fact, not presented. Since FAs are, at heart, reports, they must meet two criteria to serve as an experimental proxy for hallucinations: first, FAs should reflect perceptual states that are characterized by specific contents10,11,12 (criterion 1). Second, FAs should occur on a timescale compatible with the temporal dynamics of hallucinations13,14 (criterion 2). In this work, we combined a classification image approach15 with hidden Markov models16 to show that FAs can match the perceptual and temporal characteristics of hallucinations. We asked healthy human participants to discriminate visual stimuli from noise and found that FAs were more likely to occur during an internal mode of sensory processing, a minute-long state of the brain during which perception is strongly biased toward previous experiences17 (serial dependency). Our results suggest that hallucinations are driven by dynamic predictive templates that transform noise into transient, coherent, and meaningful perceptual experiences.

Online discrimination-correction subnet for background suppression and dynamic template updating in Siamese visual tracking

The offline Siamese tracking methods have recently attracted much attention due to their impressive performance on speed and accuracy. However, they ignore the target and background information during tracking, thus lacking sufficient discrimination ability to handle complex background interference, and cannot robustly adapt to sharp appearance variations in challenging situations, such as scale variation, rotation, occlusion, and background clutter. To address the drawbacks above, we propose an online discrimination-correction subnet, which discriminates and corrects the tracking results obtained by the Siamese tracker through online learning, and further guides the template update. Firstly, a feature refinement module is designed to enhance the discriminative ability of features, which compresses and combines target features based on the importance of feature channels to obtain target-specific features. On this basis, an online discriminator module is proposed to learn the decision boundary between target and background through samples collected online to suppress background interference. In addition, a sample equilibrium strategy is proposed to alleviate the imbalance in the distribution of positive and negative samples during online training. Finally, to handle sharp target appearance variations, a robust template updating strategy is proposed to screen high-quality historical samples to generate dynamic templates. To evaluate the generalization ability and effectiveness of our method, we apply it to four classical Siamese trackers, namely SiamFC, SiamRPN++, SiamCAR, and TransT. Extensive experiments on seven challenging benchmarks demonstrate that our method significantly improves the baseline methods and achieves outstanding performance compared with state-of-the-art trackers.

Leaded Bronze Foams As Innovative Electrodes for Organic Electrosynthesis

The electrification of organic synthesis represents an outstanding green alternative to prepare valuable and fine chemicals. However, the design of electrode materials for organic electrosynthesis remains as an open field to investigate. Motivated by the superior performance of leaded bronzes as electrodes for reductive transformations,[1, 2, 3] we have developed highly porous binary and ternary leaded metal foams through the dynamic hydrogen bubble template method [4] and tested them as cathodes in the electro-organic synthesis of 2,6-dichlorobenzonitrile from 2,6-dichlorobenzaldoxime.[5]The electrocatalytic performance of the novel leaded foams was compared to the one of the planar CuSn7Pb15 leaded bronze. The novel porous leaded foams outperformed the CuSn7Pb15 electrodes in terms of chemical yield and energy efficiency. Furthermore, due to their highly crystalline surface, these materials are mechanically more stable and less prone to cathodic corrosion than flat Pb and CuSn7Pb15 electrodes.

Preparation of Porous Ni-W Alloys Electrodeposited by Dynamic Hydrogen Bubble Template and Their Alkaline HER Properties

Nickel–tungsten (Ni-W) alloys are gaining significant attention due to their superior hardness, wear resistance, anti-corrosion and electrochemical hydrogen evolution reaction (HER) activity. In this work, porous and crack Ni-W alloys with different W contents were prepared in a pyrophosphate bath. The key to forming a porous structure is a very high current density over 300 mA cm−2. The HER activity of porous and crack Ni-W alloys was studied by means of electrochemical technologies of linear sweep voltammetry (LSV), Tafel curves (Taf) and electrochemical impedance spectroscopy (EIS). Compared with the crack Ni-W alloy, the porous Ni-W alloy exhibits improved alkaline electrochemical HER performances, which can deliver a current density of 10 mA cm−2 at 166 mV (η10) vs. RHE (reversible hydrogen electrode).

3D Nickel–Manganese bimetallic electrocatalysts for an enhanced hydrogen evolution reaction performance in simulated seawater/alkaline natural seawater

In this paper, we report an inexpensive one-step synthesis of self-supported 3D nickel-manganese (NiMn) bimetallic coatings and their application for the hydrogen evolution reaction in simulated seawater (1 M KOH + 0.5 M NaCl) and alkaline natural seawater (1 M KOH + natural seawater). These binary coatings were electrodeposited on a titanium substrate using a facile electrochemical deposition method by a dynamic hydrogen bubble template technique. The as-deposited NiMn coatings with variable Mn amounts produce typical globular and unique porous architecture with abundant pores of different sizes. The activity of these fabricated catalysts towards the hydrogen evolution reaction was investigated by linear sweep voltammetry towards simulated seawater and alkaline natural seawater at different temperatures. The surface morphology and composition of the catalysts were also characterized by scanning electron microscopy and inductively coupled plasma optical emission spectroscopy. The as-prepared NiMn/Ti electrocatalyst, which was electrodeposited using a chemical bath containing Ni2+ and Mn2+ ions with a molar ratio of Ni2+:Mn2+ = 1:5, exhibits excellent hydrogen evolution activity in simulated seawater with an ultra-low overpotential of 64.2 mV to reach a current density of 10 mA cm−2. It is noteworthy that this NiMn/Ti electrocatalyst also achieves a current density of 10 mA cm−2 in alkaline natural seawater with a comparably low overpotential of 79.3 mV. The current densities increase by ca. 1.75–2.35 times with an increase in temperature from 25 °C to 75 °C for hydrogen evolution in both electrolytes. This bimetallic catalyst has shown excellent long-term stability at a constant potential of −0.23 V (vs. RHE) and a constant current density of 10 mA cm−2 for 10 h, which ensures higher durability and robustness for practical application of seawater splitting technology.

Hunt-inspired Transformer for visual object tracking

This paper presents a hunt-inspired Transformer for visual object tracking, dubbed as HuntFormer. The HuntFormer focuses on robust target detection and identification, simulating natural hunting processes. Specifically, the HuntFormer comprises two essential module designs including a predictor for detection and a verifier for identification. The predictor emulates the detection stage by designing a motion trajectory guided particle filter, which identifies potential target locations by predicting the motion state within a particle filtering framework. The predictor utilizes spatio-temporal correlation scores between dynamic target templates and the search region to guide the learning process to generate a set of reliable particles. This enables the base tracker to narrow its search range to focus on the target, and swiftly re-detect the target in case of model drift. Once the target is re-detected, the verifier assesses the detection result as a reliable tracked item. The verifier initially maintains a dynamic memory that stores reliable target templates and their corresponding locations in the motion trajectory. It then models the uncertainty of appearance information within this memory probabilistically. The output uncertainty score determines whether the memory gets updated or not. Ultimately, the predictor and the verifier collaborate, ensuring a robust tracking outcome. Extensive evaluations on six challenging benchmark datasets demonstrate HuntFormer’s favorable performance against various state-of-the-art trackers. Notably, in the VOT-LT2022 tracking challenge, the HuntFormer won the third place with an F-score of 0.598, closely competing for the second place with an F-score of 0.600.

Visual Object Tracking Based on the Motion Prediction and Block Search in UAV Videos

With the development of computer vision and Unmanned Aerial Vehicles (UAVs) technology, visual object tracking has become an indispensable core technology for UAVs, and it has been widely used in both civil and military fields. Visual object tracking from the UAV perspective experiences interference from various complex conditions such as background clutter, occlusion, and being out of view, which can easily lead to tracking drift. Once tracking drift occurs, it will lead to almost complete failure of the subsequent tracking. Currently, few trackers have been designed to solve the tracking drift problem. Thus, this paper proposes a tracking algorithm based on motion prediction and block search to address the tracking drift problem caused by various complex conditions. Specifically, when the tracker experiences tracking drift, we first use a Kalman filter to predict the motion state of the target, and then use a block search module to relocate the target. In addition, to improve the tracker’s ability to adapt to changes in the target’s appearance and the environment, we propose a dynamic template updating network (DTUN) that allows the tracker to make appropriate template decisions based on various tracking conditions. We also introduce three tracking evaluation metrics: namely, average peak correlation energy, size change ratio, and tracking score. They serve as prior information for tracking status identification in the DTUN and the block prediction module. Extensive experiments and comparisons with many competitive algorithms on five aerial benchmarks, UAV20L, UAV123, UAVDT, DTB70, and VisDrone2018-SOT, demonstrate that our method achieves significant performance improvements. Especially in UAV20L long-term tracking, our method outperforms the baseline in terms of success rate and accuracy by 19.1% and 20.8%, respectively. This demonstrates the superior performance of our method in the task of long-term tracking from the UAV perspective, and we achieve a real-time speed of 43 FPS.

Tailoring the Active Sites of Nanosheet NiSe/NiSe2 Catalyst by Pulse Electrodeposition on the 3D Microporous Ni-Cu/NF Substrate for both Hydrogen and Oxygen Evolution Reactions

Establishing proper intrinsic catalysts with nanostructured high active surfaces endows the paramount electrocatalytic activity. A Ni-Se@Cu-Ni/NF catalyst for hydrogen and oxygen evolution reactions (HER and OER) is prepared via an efficient two-step pulse current (PC) electrodeposition method. The initial 3D film of Cu-Ni is synthesized via the dynamic hydrogen bubble template (DHBT) method to attain further active surface area. Then, Ni-Se film is prepared by direct current (DC) and PC electrodeposition. Morphological, chemical, and electrocatalytic characteristics of the Ni-Se electrodeposited films are evaluated. X-ray photoelectron spectroscopy and high-resolution transmission electron microscopy results show a NiSe/NiSe2 nanofilm on the 3D microporous nanostructured Cu-Ni substrate which reveals an efficient bifunctional electrocatalytic behavior with overpotentials of 74 and 272 mV in the current density of 10 mA cm−2, and Tafel slopes of 78 and 50 mV dec−1 for HER and OER, respectively. The two-electrode examination with NiSe/NiSe2@Cu-Ni/NF catalyst in overall water splitting indicates a required potential of 1.57 V in the current density of 10 mA cm−2.

Adaptive sparse attention-based compact transformer for object tracking

The Transformer-based Siamese networks have excelled in the field of object tracking. Nevertheless, a notable limitation persists in their reliance on ResNet as backbone, which lacks the capacity to effectively capture global information and exhibits constraints in feature representation. Furthermore, these trackers struggle to effectively attend to target-relevant information within the search region using multi-head self-attention (MSA). Additionally, they are prone to robustness challenges during online tracking and tend to exhibit significant model complexity. To address these limitations, We propose a novel tracker named ASACTT, which includes a backbone network, feature fusion network and prediction head. First, we improve the Swin-Transformer-Tiny to enhance its global information extraction capabilities. Second, we propose an adaptive sparse attention (ASA) to focus on target-specific details within the search region. Third, we leverage position encoding and historical candidate data to develop a dynamic template updater (DTU), which ensures the preservation of the initial frame’s integrity while gracefully adapting to variations in the target’s appearance. Finally, we optimize the network model to maintain accuracy while minimizing complexity. To verify the effectiveness of our proposed tracker, ASACTT, experiments on five benchmark datasets demonstrated that the proposed tracker was highly comparable to other state-of-the-art methods. Notably, in the GOT-10K1 evaluation, our tracker achieved an outstanding success score of 75.3% at 36 FPS, significantly surpassing other trackers with comparable model parameters.