Initial Frame Research Articles

Learning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking.

Recently, template-based trackers have become the leading tracking algorithms with promising performance in terms of efficiency and accuracy. However, the correlation operation between query feature and the given template only achieves accurate target localization, but is prone to state estimation error, especially when the target suffers from severe deformation. To address this issue, segmentation-based trackers are proposed that use per-pixel matching to improve the tracking performance of deformable objects effectively. However, most of the existing trackers only match with the target features of the initial frame, thereby lacking the discrimination for handling a variety of challenging factors, e.g., similar distractors, background clutter, and appearance change. To this end, we propose a dynamic compact memory embedding technique to enhance the discrimination of the segmentation-based visual tracking method that can well tell the target from the background. Specifically, we initialize a memory embedding with the target features in the first frame. During the tracking process, the current target features that have certain correlation with the existing memory are updated to the memory embedding online. To further improve the tracking accuracy for deformable objects, we use a weighted point-to-global matching strategy to measure the correlation between the pixelwise query feature and the whole template, so as to capture more detailed deformation information. Extensive evaluations on six challenging tracking benchmarks including VOT2016, VOT2018, VOT2019, GOT-10K, TrackingNet, and LaSOT demonstrate the superiority of our method over recent remarkable trackers. Besides, our tracker outperforms the excellent segmentation-based trackers, i.e., D3S and SiamMask on the DAVIS2017 benchmark. The code is available at https://github.com/peace-love243/CMEDFL.

Mitigating Distractor Challenges in Video Object Segmentation through Shape and Motion Cues

The purpose of semi-supervised video object segmentation (VOS) is to predict and generate object masks in subsequent video frames after being provided with the initial frame’s object mask. Currently, mainstream methods leverage historical frame information for enhancing the network’s performance. However, this approach faces the following issues: (1) They often overlook important shape information, leading to decreased accuracy in segmenting object-edge areas. (2) They often use pixel-level motion estimation to guide the matching for addressing distractor objects. However, this brings heavy computation costs and struggle against occlusion or fast/blurry motion. For the first problem, this paper introduces an object shape extraction module that exploits both the high-level and low-level features to obtain object shape information, by which the shape information can be used to further refine the predicted masks. For the second problem, this paper introduces a novel object-level motion prediction module, in which it stores the representative motion features during the training stage, and predicts the object motion by retrieving them during the inference stage. We evaluate our method on benchmark datasets compared with recent state-of-the-art methods, and the results demonstrate the effectiveness of the proposed method.

Future curriculum‐makers: The role of professional experience placements as sites of learning about curriculum‐making for preservice teachers

AbstractThe teaching profession and initial teacher education face ongoing pressures which challenge how teachers' work with curriculum is positioned. Within Australia, recent reviews into initial teacher education have emphasised the need for ‘classroom ready’ graduates with knowledge of ‘proven’ pedagogical approaches. Parallel to this has been increasing push for ‘ready‐made’ curriculum materials to be made available to all teachers for their use in classrooms. This discourse espouses curriculum as a product, positioning preservice teachers as future ‘deliverers’ of prescriptive forms of curriculum and dismissing their future potential as classroom curriculum‐makers who engage with curriculum as a process, and think systematically and critically about their curriculum choices. In this paper, we explore the classroom curriculum‐making experiences of two preservice teachers, and the role of professional experience placements as key sites of learning about curriculum‐making, noting this as a significantly under‐researched theme in existing literature. Our in‐depth exploration of these individual cases highlights the contrasting opportunities these teachers had to engage with curriculum as a process, identifying, enabling and constraining structures within these placements which impact on preservice teachers' development, and future potential, as curriculum‐makers. We contend that the pursuit of Lawrence Stenhouse's vision of curriculum work as an iterative, enquiry process driven by and for teachers rests not only on the way in which initial teacher education frames curriculum work in theory, but also in the way it is modelled to preservice teachers during their professional experience placements.

Entangled Co-Design with a Trickster: Speculative Framing and Reframing

Speculative design, as a diverse set of methods that aim to offer critique, can be challenging to engage productively. In this design case, we share how a prior, stalled design project—an ambitious vision of interdisciplinary design education partnered with business and housing development projects in Santa Fe, New Mexico—provided compelling precedent as we sought to reframe during the COVID-19 pandemic. We recognized that solution-focused ways of working in the prior project left the design problem undefined. As we began the design work detailed in this case, we leveraged the perspectives and design knowledge of our interdisciplinary team of faculty and students. While design cases often emphasize the designed training or program, we focus on our reframing process, sharing vignettes as we prepared to and participated in activities at a design workshop, and then used our own design practices to engage in problem framing workshops. In sharing these accounts, we characterize the pandemic as a trickster and speculative co-designer, who revealed much about how our efforts were entangled with institutional structures. Across these punctuated vignettes of design work, we highlight how an initial broad problem frame invited this trickster to participate and how the application of problem framing tools wrested framing agency from the trickster. Collectively, this anchored our attention to systemic inequities in ways that troubled notions of sustainability.

Abstract TP141: Understanding Potential Limitations of CTP Imaging in Early Window Large Vessel Anterior Circulation Strokes

Background: Computerized tomography perfusion (CTP) imaging serves as a valuable modality for the assessment of individuals with a large vessel anterior circulation stroke. Current literature proposes that employing CTP imaging in patients within the initial time frame of less than 8 hours, may lead to an overestimation of the projected infarct core, specifically when utilizing cerebral blood flow (CBF) less than 30%. The hypoperfusion intensity ratio (HIR) may result in overestimation. We sought to further investigate the interplay of CTP parameters in patients presenting within 8 hours of symptom onset of stroke, to assess the accuracy of core infarct estimation. Methods: A retrospective cohort study analyzing patients with large vessel anterior occlusion (LVAO) who underwent CTP and mechanical thrombectomy within 24 hours of symptom onset between January 2017 to December 2022. RAPID software estimates the infarct core using CBF <30%. DWI-MRI determined final infarct volume. A multivariate logistic regression model was employed to assess the impact of HIR and reperfusion success on outcomes. Results: Ninety-seven patients were identified within an 8-hour time window. CBF<30% overestimated core infarct volume (mL) in 22 patients (22.6%) with a mean of 15.72 (range 4.4-37.7) and a median of 22.85. Of these, 2 patients experienced poor reperfusion (9%) while 20 had successful reperfusion (91%). Of the patients who did have successful reperfusion, an average of 13.57mL core was overpredicted compared to the DWI volumes. A multivariate logistic regression model adjusting for degree of reperfusion, administration of thrombolytic, and time from symptom onset showed that HIR strongly predicted the probability of core estimation with an odds ratio of 148.6, 95% CI [21.0-1048.8], (p<0.001). Conclusion: HIR exceeding 0.4 demonstrates a predictive capacity for core overestimation in early-window LVAO patients. Our study affirms this observation with statistical significance. The integration of HIR as a parameter for early-window LVAO core computation shows promise, and has potential ramifications for patient selection for thrombectomy. In this context, utilization of further databases is imperative for validation and broader application of HIR.

Research on the Application of Structural Topology Optimisation in the High-Precision Design of a Press Machine Frame

This article aims to optimise the structure of a press machine to enhance its stability and accuracy, as well as reduce the frame deformation during processing. The outer supporting frame of the JH31-250 press machine (Zhejiang Weili Forging Machinery Co., Ltd, Shaoxing, China) is used as a typical sample for exploring optimisation. Commercial software is utilised to conduct a finite element analysis on the three-dimensional model of the press machine frame. A topological optimisation algorithm using the solid isotropic microstructures with penalisation (SIMP) method is then applied to improve the structure of the press frame. The size of the topological structure is further refined with the response surface method and particle swarm optimisation method to ensure it is more relevant to engineering application. The analysis results indicate that the initial frame’s deformation under the static conditions is 0.4229 mm, and after optimisation, the deformed structural displacement is 0.2548 mm, a decrease of 39.75%. Additionally, a simplified experimental method is designed to effectively validate the simulation and the proposed design.

Controllable Video Generation With Text-Based Instructions

Most of the existing studies on controllable video generation either transfer disentangled motion to an appearance without detailed control over motion or generate videos of simple actions such as the movement of arbitrary objects conditioned on a control signal from users. In this study, we introduce Controllable Video Generation with text-based Instructions (CVGI) framework that allows text-based control over action performed on a video. CVGI generates videos where hands interact with objects to perform the desired action by generating hand motions with detailed control through text-based instruction from users. By incorporating the motion estimation layer, we divide the task into two sub-tasks: (1) control signal estimation and (2) action generation. In control signal estimation, an encoder models actions as a set of simple motions by estimating low-level control signals for text-based instructions with given initial frames. In action generation, generative adversarial networks (GANs) generate realistic hand-based action videos as a combination of hand motions conditioned on the estimated low control level signal. Evaluations on several datasets (EPIC-Kitchens-55, BAIR robot pushing, and Atari Breakout) show the effectiveness of CVGI in generating realistic videos and in the control over actions.

Climate Policies and Forest Restoration Challenges in Bahia State South, Brazil

Climate change presents humanity with one of the most complex and pressing challenges of the 21st century. As such, effective public policies and legislation must be implemented to mitigate negative impacts and facilitate the adaptation of societies to new environmental dynamics. These policies are critical in aligning collective efforts toward a more sustainable and resilient economy, providing a crucial legal framework to guide individual, collective, and governmental actions toward climate change mitigation. Thereby, Brazil has committed to restoring 12 million hectares of forests by 2030 as part of its strategy to mitigate climate change. However, the absence of an express initial time frame by law has led to inconsistencies and possible low effectiveness of forest management policies. This study sought to examine Rural Environmental Registries (in Portuguese, Cadastro Ambiental Rural - CAR) of properties in the State of Bahia and assess restoration timetables for legal reserve areas, in addition to the challenges and opportunities associated with the formulation and implementation of forest restoration policies. Considering the implications of forest degradation on the environment and human livelihoods, it is a matter of great significance. As such, it warrants a thorough examination and analysis of the various factors involved, including the role of stakeholders, financial and technical feasibility, and the identification of appropriate goals and targets. The study findings indicate that, in 71% of the properties requiring legal reserve restoration, the timetable exceeded the established legal period of the year 2032. Additionally, in 45% of the cases, the term was calculated from the registration of the rural property in the CAR. Consequently, it was concluded that the erroneous interpretations adopted impede the recovery of native vegetation and, more significantly, the Brazilian goal of forest restoration of 12 million hectares of degraded land by 2030.

Pose estimation via structure-depth information from monocular endoscopy images sequence.

Image-based endoscopy pose estimation has been shown to significantly improve the visualization and accuracy of minimally invasive surgery (MIS). This paper proposes a method for pose estimation based on structure-depth information from a monocular endoscopy image sequence. Firstly, the initial frame location is constrained using the image structure difference (ISD) network. Secondly, endoscopy image depth information is used to estimate the pose of sequence frames. Finally, adaptive boundary constraints are used to optimize continuous frame endoscopy pose estimation, resulting in more accurate intraoperative endoscopy pose estimation. Evaluations were conducted on publicly available datasets, with the pose estimation error in bronchoscopy and colonoscopy datasets reaching 1.43 mm and 3.64 mm, respectively. These results meet the real-time requirements of various scenarios, demonstrating the capability of this method to generate reliable pose estimation results for endoscopy images and its meaningful applications in clinical practice. This method enables accurate localization of endoscopy images during surgery, assisting physicians in performing safer and more effective procedures.

Efficient Visual Tracking Based on Fuzzy Inference for Intelligent Transportation Systems

Remote monitoring is an important application of intelligent transportation systems (ITSs). The combination of monitoring equipment and tracking algorithms can be used to automatically track moving targets. The tracking algorithm based on the Siamese network is both accurate and efficient, and its development potential is better than that of other algorithms. Its output is a detection map that reflects the probability that any position in the search area is the center of the target’s bounding box, and the maximum value of the detection map is the center of the target’s bounding box predicted by the algorithm. Owing to partial occlusion, target deformation, out-of-view, and background clutter, local maxima in the detection map may also be the center of the target’s bounding box. A tracker’s ability to make accurate judgments is currently limited. Furthermore, previous trackers extracted only the target features in the initial frame as the matching template. Although this matching template is highly reliable, it cannot effectively combine the target features available in the subsequent frames. Therefore, in this study, fuzzy inference is introduced into the tracking process to analyze the reliability of the detection map. When this map is reliable, the target feature of the search area is transformed into a substitute template; otherwise, multiple substitute templates are selected from the template pool for parallel matching as per the set rules. The optimal result is selected from multiple detection results, based on the priority of the detection results when the initial frame is used as the matching template. Experimental results on multiple datasets show that the proposed algorithm is superior to other similar algorithms in terms of multiple assessment metrics and can improve the robustness of remote monitoring tasks in ITSs.

Acceleration-Based Kalman Tracking for Super-Resolution Ultrasound Imaging In Vivo.

Super-resolution ultrasound (SRUS) can image microvascular structure and flow at subwave-diffraction resolution based on localizing and tracking microbubbles (MBs). Currently, tracking MBs accurately under limited imaging frame rates and high MB concentrations remains a challenge, especially under the effect of cardiac pulsatility and in highly curved vessels. In this study, an acceleration-incorporated MB motion model is introduced into a Kalman tracking framework. The tracking performance was evaluated using simulated microvasculature with different MB motion parameters, concentrations, and acquisition frame rates, and in vivo human breast tumor US datasets. The simulation results show that the acceleration-based method outperformed the nonacceleration-based method at different levels of acceleration and acquisition frame rates and achieved significant improvement in true positive rate (TPR; up to 11.3%) and false negative rate (FNR; up to 13.2%). The proposed method can also reduce errors in vasculature reconstruction via the acceleration-based nonlinear interpolation, compared with linear interpolation (up to [Formula: see text]). The tracking results from temporally downsampled low frame rate in vivo datasets from human breast tumors show that the proposed method has better MB tracking performance than the baseline method, if using results from the initial high frame data as a reference. Finally, the acceleration estimated from tracking results also provides a spatial speed gradient map that may contain extra valuable diagnostic information.

Correlation between contrast leakage period of procedural rupture and clinical outcomes in endovascular coiling for cerebral aneurysms.

Intraprocedural rupture (IPR) is a fatal complication of endovascular coiling for cerebral aneurysms. We hypothesized that contrast leakage period may be related to poor clinical outcomes. This study aimed to retrospectively evaluate the relationship between clinical outcomes and contrast leakage period. Data from patients with cerebral aneurysms treated via endovascular coiling between January 2010 and October 2018 were retrospectively assessed. The enrolled patient's demographic data, the aneurysm related findings, endovascular treatment and IPR related findings, rescue treatment, and clinical outcome were analyzed. In total, 2,859 cerebral aneurysms were treated using endovascular coiling during the study period, with IPR occurring in 18 (0.63 %). IPR occurred during initial frame coiling (n=4), coil packing (n=5), stent deployment (n=7), ballooning (n=1), and microcatheter removal after coiling (n=1). Tear sites included the dome (n=14) and neck (n=4). All IPRs were controlled and treated with coil packing, with or without stenting. Flow arrest of the proximal balloon was not observed. Temporary focal neurological deficits developed in two patients (11.1%). At clinical follow-up, 14 patients were classified as modified Rankin Scale (mRS) 0, three as mRS 2, and one as mRS 4. The mean contrast leakage period of IPR was 11.2 min (range: 1-31 min). Cerebral aneurysms with IPR were divided into late (n=9, mean time: 17.11 min) and early (n=9, mean time: 5.22 min) control groups based on the criteria of 10 min of contrast leakage period. No significant between-group differences regarding clinical outcomes were observed after IPR (p=1). In our series, all patients with IPR were controlled with further coil packing or stenting without proximal balloon occlusion within 31 min of contrast leakage. There was no difference in clinical outcomes when the long contrast leakage period group and short contrast leakage period group were compared.

Remarks on Naimark dilation theorem

AbstractAlthough Naimark dilation theorem was originally stated in 1940, it still finds many important applications in various areas. The objective of this paper is to introduce a method for explicitly constructing the vectors of complementary frames in the Naimark dilation theorem, specifically in cases where the initial Parseval frame contains a Riesz basis as a subset. These findings serve as a foundation for the construction of dual frames.

Construction of self-standing MnO2-based films for reversible and practical electrolytic Zn//MnO2 batteries in acidic environment

In acidic environment, electrolytic Zn//MnO2 batteries possess high potential to reach high energy density on the promise of high safety, low cost, and high power density. However, several serious challenges still need to be overcome, mainly including suitable current collector that can be stable in strong acidic and oxidizing environment, optimal cathode that can promote massive and uniform deposition of the MnO2, and Zn-plating efficiency and corrosion resistance improvement. Herein, a free-standing and binder-free film composed of graphene powder (GP) and MnSO4 (GP/MS-F) was developed and used as initial cathode frame. The film with a GP: MnSO4 mass ratio of 2:3 and a total areal mass of 13 mg cm−2 exhibits good conductivity and considerable flexibility without the using of any other additives. Matched with C coated ZnO (ZnO@C) modified anode frame and Carboxy Methyl Cellulose Sodium gelled acidic electrolyte, the film can deliver a high areal capacity of 1.4 mAh cm−2, corresponding to a specific capacity of 184 mAh g−1 based on the total mass of initial GP and deposited MnO2 (∼7.6 mg). At 5 mA cm−2, a high Coulombic efficiency of 92 % can be achieved and maintained for 2,100 cycles. At 30 mA cm−2, the cell can work well for 8,000 cycles. Meanwhile, discharge voltage of the cell can reach 1.9 V, exhibiting high practical application prospect.

Three-dimensional reconstruction of mobile binocular stereo vision based on push-broom line structured light for a workpiece surface

Stereo vision technology based on line structured light can effectively solve the problem of a three-dimensional (3D) reconstruction of a smooth surface. A method for 3D reconstruction of mobile binocular stereo vision based on push-broom line structured light for a workpiece surface is presented in this paper. The subpixel coordinates of the light strip centers of the line structured light are obtained by the Steger algorithm while the binocular module moves along the guide rail, and the polar constraint is used to achieve the matching of the extracted light strip centers. As a result, the 3D coordinates of the light strip centers in each location can be calculated because of the known interior and external parameters of the binocular module. To obtain the 3D point cloud data of the entire surface, a relative pose optimization method with respect to the initial frame is proposed, which accurately estimates the pose of the cameras in each location with respect to that in the initial location and unifies the 3D coordinates of the light strip centers in each location to the datum coordinates. The relative pose optimization method first estimates the rough values by using the direct linear transform method, and then iteratively calculates the refined solutions based on the principle of minimizing the re-projection errors. Simulation data and substantial experimental results validate the effectiveness of our method. Our method is compared to the direct linear transform method and the frame-by-frame transfer method, and the root mean square error (RMSE) of the distance from 3D point cloud to fitted plane is used to evaluate the 3D reconstruction accuracy. The repeatability experiment shows that the RMSE from our method is as low as 0.83 mm.

Balancing Rotation Minimizing Frames with Additional Objectives

AbstractWhen moving along 3D curves, one may require local coordinate frames for visited points, such as for animating virtual cameras, controlling robotic motion, or constructing sweep surfaces. Often, consecutive coordinate frames should be similar, avoiding sharp twists. Previous work achieved this goal by using various methods to approximate rotation minimizing frames (RMFs) with respect to a curve's tangent. In this work, we use Householder transformations to construct preliminary tangent‐aligned coordinate frames and then optimize these initial frames under the constraint that they remain tangent‐aligned. This optimization minimizes the weighted sum of squared distances between selected vectors within the new frames and fixed vectors outside them (such as the axes of previous frames). By selecting different vectors for this objective function, we reproduce existing RMF approximation methods and modify them to consider additional objectives beyond rotation minimization. We also provide some example computer graphics use cases for this new frame tracking.

Sticky Frames and What's in a Name: Frames Stick to Particular Objects

A growing literature on sequential framing effects has documented a negativity bias: In many contexts, attitudes change less when framing switches from negative-to-positive (vs. positive-to-negative). However, it is unclear whether this negativity bias sticks to one attitude object or generalizes beyond it. Novel paradigms in two experiments yielded strong evidence for the first possibility and tentative evidence for the second: Switching to a different object (vs. same object) across time points reduced the negativity bias in reframing. In contrast, superficially rebranding an object (just changing its name) did not reduce negativity bias. The experiments also provide the first evidence that positive frames are somewhat sticky: A positive initial frame somewhat attenuated the impact of a negative subsequent frame on attitudes. The findings are consistent with the possibility that once an object is framed negatively or positively, that conceptualization sticks in the mind and resists subsequent reframing—especially for negative frames.

Revealing the predictive power of neural operators for strain evolution in digital composites

The demand for high-performance materials, along with advanced synthesis technologies such as additive manufacturing and 3D printing, has spurred the development of hierarchical composites with superior properties. However, computational modelling of such composites using physics-based solvers, while enabling the discovery of optimal microstructures, have prohibitively high computational cost hindering their practical application. To this extent, we show that Neural Operators (NOs) can be used to learn and predict the strain evolution in 2D digital composites. Specifically, we consider three architectures, namely, Fourier NO (FNO), Wavelet NO (WNO), and Multi-wavelet NO (MWT). We demonstrate that by providing a few initial strain frames as input, NOs can accurately predict multiple future time steps in an extremely data-efficient fashion, especially WNO. Further, once trained, NOs forecast the strain trajectories for completely unseen boundary conditions. Among NOs, only FNO offers super-resolution capabilities for estimating strains at multiple length scales, which can provide higher material and pixel-wise resolution. We also show that NOs can generalize to arbitrary geometries with finer domain resolution without the need for additional training. Based on all the results presented, we note that the FNO exhibits the best performance among the NOs, while also giving minimum inference time that is almost three orders magnitude lower than the conventional finite element solutions. Thus, FNOs can be used as a surrogate for accelerated simulation of the strain evolution in complex microstructures toward designing the next composite materials.

Structural displacement estimation by a hybrid computer vision approach

Structural displacement is an important indicator of structural safety in structural health monitoring (SHM). As one of the vision-based methods, optical flow can provide displacement measurement of pixels in images. However, estimating structural displacement by predicting the optical flow between the current frame and the initial frame may be subject to limited accuracy due to environmental variations. Alternatively, calculating structural velocity by predicting the optical flow of adjacent frames and integrating to obtain displacement may introduce displacement drift attributable to cumulative errors. This study proposes a hybrid structural displacement estimation method to eliminate the effects of environmental variations and cumulative errors. In comparison to the existing methods, the novelty of the proposed method is to effectively integrate deep learning-based dense optical flow and correlation template matching (CM), for achieving both high accuracy and improved robustness. Deep learning-based dense optical flow was used for optical flow prediction between adjacent frames through correlation calculations and iterative updating to obtain the structural velocity. Pyramid-accelerated CM was employed to locate the regions of interest (ROI) of the structure in each frame, and the structural displacement was then estimated by counting temporal changes in these locations. By fusing estimated structural velocity and displacement using the Kalman filter, optimized structural displacement results were obtained, and temporal cumulative errors using dense optical flow could be eliminated. The proposed method was validated in an indoor shaking table test of a three-story reinforced concrete structure, and an outdoor shaking table test of a cold-formed steel wall system. The results indicated that the proposed method reduced the root mean square error of estimated displacement by over 89% compared with dense optical flow and by over 36% compared with CM. Furthermore, the proposed method was able to process 1080p high-definition images at a rate of 5.43 frames per second, indicating its high efficiency for applications.

Learning Context Restrained Correlation Tracking Filters via Adversarial Negative Instance Generation.

The tracking performance of discriminative correlation filters (DCFs) is often subject to unwanted boundary effects. Many attempts have already been made to address the above issue by enlarging searching regions over the last years. However, introducing excessive background information makes the discriminative filter prone to learn from the surrounding context rather than the target. In this article, we propose a novel context restrained correlation tracking filter (CRCTF) that can effectively suppress background interference via incorporating high-quality adversarial generative negative instances. Concretely, we first construct an adversarial context generation network to simulate the central target area with surrounding background information at the initial frame. Then, we suggest a coarse background estimation network to accelerate the background generation in subsequent frames. By introducing a suppression convolution term, we utilize generative background patches to reformulate the original ridge regression objective through circulant property of correlation and a cropping operator. Finally, our tracking filter is efficiently solved by the alternating direction method of multipliers (ADMM). CRCTF demonstrates the accuracy performance on par with several well-established and highly optimized baselines on multiple challenging tracking datasets, verifying the effectiveness of our proposed approach.