Jointly exploiting multiple different yet complementary domain information has been proven to be an effective way to perform robust object tracking. This paper focuses on effectively representing and utilizing complementary features from the frame do
main and event domain for boosting object tracking performance in challenge scenarios. Specifically, we propose Common Features Extractor (CFE) to learn potential common representations from the RGB domain and event domain. For learning the unique features of the two domains, we utilize a Unique Extractor for Event (UEE) based on Spiking Neural Networks to extract edge cues in the event domain which may be missed in RGB in some challenging conditions, and a Unique Extractor for RGB (UER) based on Deep Convolutional Neural Networks to extract texture and semantic information in RGB domain. Extensive experiments on standard RGB benchmark and real event tracking dataset demonstrate the effectiveness of the proposed approach. We show our approach outperforms all compared state-of-the-art tracking algorithms and verify event-based data is a powerful cue for tracking in challenging scenes.
With the development of laser technologies, nuclear reactions can happen in high-temperature plasma environments induced by lasers and have attracted a lot of attention from different physical disciplines. However, studies on nuclear reactions in pla
sma are still limited by detecting technologies. This is mainly due to the fact that extremely high electromagnetic pulses (EMPs) can also be induced when high-intensity lasers hit targets to induce plasma, and then cause dysfunction of many types of traditional detectors. Therefore, new particle detecting technologies are highly needed. In this paper, we report a recently developed gated fiber detector which can be used in harsh EMP environments. In this prototype detector, scintillating photons are coupled by fiber and then transferred to a gated photomultiplier tube which is located far away from the EMP source and shielded well. With those measures, the EMPs can be avoided, and this device has the capability to identify a single event of nuclear reaction products generated in laser-induced plasma from noise EMP backgrounds. This new type of detector can be widely used as a Time-of-Flight (TOF) detector in high-intensity laser nuclear physics experiments for detecting neutron, photons, and other charged particles.
The main purpose of this paper is to study the global propagation of singularities of viscosity solution to discounted Hamilton-Jacobi equation begin{equation}label{eq:discount 1}tag{HJ$_lambda$} lambda v(x)+H( x, Dv(x) )=0 , quad xin mathbb{R}^n.
end{equation} We reduce the problem for equation eqref{eq:discount 1} into that for a time-dependent evolutionary Hamilton-Jacobi equation. We proved that the singularities of the viscosity solution of eqref{eq:discount 1} propagate along locally Lipschitz singular characteristics which can extend to $+infty$. We also obtained the homotopy equivalence between the singular set and the complement of associated the Aubry set with respect to the viscosity solution of equation eqref{eq:discount 1}.
Differentiable architecture search (DARTS) is successfully applied in many vision tasks. However, directly using DARTS for Transformers is memory-intensive, which renders the search process infeasible. To this end, we propose a multi-split reversible
network and combine it with DARTS. Specifically, we devise a backpropagation-with-reconstruction algorithm so that we only need to store the last layers outputs. By relieving the memory burden for DARTS, it allows us to search with larger hidden size and more candidate operations. We evaluate the searched architecture on three sequence-to-sequence datasets, i.e., WMT14 English-German, WMT14 English-French, and WMT14 English-Czech. Experimental results show that our network consistently outperforms standard Transformers across the tasks. Moreover, our method compares favorably with big-size Evolved Transformers, reducing search computation by an order of magnitude.
Error-bounded lossy compression is becoming an indispensable technique for the success of todays scientific projects with vast volumes of data produced during the simulations or instrument data acquisitions. Not only can it significantly reduce data
size, but it also can control the compression errors based on user-specified error bounds. Autoencoder (AE) models have been widely used in image compression, but few AE-based compression approaches support error-bounding features, which are highly required by scientific applications. To address this issue, we explore using convolutional autoencoders to improve error-bounded lossy compression for scientific data, with the following three key contributions. (1) We provide an in-depth investigation of the characteristics of various autoencoder models and develop an error-bounded autoencoder-based framework in terms of the SZ model. (2) We optimize the compression quality for main stages in our designed AE-based error-bounded compression framework, fine-tuning the block sizes and latent sizes and also optimizing the compression efficiency of latent vectors. (3) We evaluate our proposed solution using five real-world scientific datasets and comparing them with six other related works. Experiments show that our solution exhibits a very competitive compression quality from among all the compressors in our tests. In absolute terms, it can obtain a much better compression quality (100% ~ 800% improvement in compression ratio with the same data distortion) compared with SZ2.1 and ZFP in cases with a high compression ratio.
Implicit solvent models, such as Poisson-Boltzmann models, play important roles in computational studies of biomolecules. A vital step in almost all implicit solvent models is to determine the solvent-solute interface, and the solvent excluded surfac
e (SES) is the most widely used interface definition in these models. However, classical algorithms used for computing SES are geometry-based, thus neither suitable for parallel implementations nor convenient for obtaining surface derivatives. To address the limitations, we explored a machine learning strategy to obtain a level-set formulation for the SES. The training process was conducted in three steps, eventually leading to a model with over 95% agreement with the classical SES. Visualization of tested molecular surfaces shows that the machine-learned SES overlaps with the classical SES on almost all situations. We also implemented the machine-learned SES into the Amber/PBSA program to study its performance on reaction field energy calculation. The analysis shows that the two sets of reaction field energies are highly consistent with 1% deviation on average. Given its level-set formulation, we expect the machine-learned SES to be applied in molecular simulations that require either surface derivatives or high efficiency on parallel computing platforms.
Room allocation is a challenging task in detention centers since lots of related people need to be held separately with limited rooms. It is extremely difficult and risky to allocate rooms manually, especially for organized crime groups with close co
nnections. To tackle this problem, we develop an intelligent room allocation system for detention centers to provide optimized room allocation schemes automatically. We first formalize the detention room allocation problem as inverse graph partitioning, which can measure the quality of room allocation schemes. Then, we propose two heuristic algorithms to achieve the global optimization and local optimization of detention room allocation. Experiment results on real-world datasets show that the proposed algorithms significantly outperform manual allocation and suggest that the system is of great practical application value.
Capsule endoscopy is an evolutional technique for examining and diagnosing intractable gastrointestinal diseases. Because of the huge amount of data, analyzing capsule endoscope videos is very time-consuming and labor-intensive for gastrointestinal m
edicalists. The development of intelligent long video analysis algorithms for regional positioning and analysis of capsule endoscopic video is therefore essential to reduce the workload of clinicians and assist in improving the accuracy of disease diagnosis. In this paper, we propose a deep model to ground shooting range of small intestine from a capsule endoscope video which has duration of tens of hours. This is the first attempt to attack the small intestine grounding task using deep neural network method. We model the task as a 3-way classification problem, in which every video frame is categorized into esophagus/stomach, small intestine or colorectum. To explore long-range temporal dependency, a transformer module is built to fuse features of multiple neighboring frames. Based on the classification model, we devise an efficient search algorithm to efficiently locate the starting and ending shooting boundaries of the small intestine. Without searching the small intestine exhaustively in the full video, our method is implemented via iteratively separating the video segment along the direction to the target boundary in the middle. We collect 113 videos from a local hospital to validate our method. In the 5-fold cross validation, the average IoU between the small intestine segments located by our method and the ground-truths annotated by broad-certificated gastroenterologists reaches 0.945.
We consider the discrete time quantum random walks on a Sierpinski gasket. We study the hitting probability as the level of fractal goes to infinity in terms of their localization exponents $beta_w$ , total variation exponents $delta_w$ and relative
entropy exponents $eta_w$ . We define and solve the amplitude Green functions recursively when the level of the fractal graph goes to infinity. We obtain exact recursive formulas for the amplitude Green functions, based on which the hitting probabilities and expectation of the first-passage time are calculated. Using the recursive formula with the aid of Monte Carlo integration, we evaluate their numerical values. We also show that when the level of the fractal graph goes to infinity, with probability 1, the quantum random walks will return to origin, i.e., the quantum walks on Sierpinski gasket are recurrent.
Efficient error-controlled lossy compressors are becoming critical to the success of todays large-scale scientific applications because of the ever-increasing volume of data produced by the applications. In the past decade, many lossless and lossy co
mpressors have been developed with distinct design principles for different scientific datasets in largely diverse scientific domains. In order to support researchers and users assessing and comparing compressors in a fair and convenient way, we establish a standard compression assessment benchmark -- Scientific Data Reduction Benchmark (SDRBench). SDRBench contains a vast variety of real-world scientific datasets across different domains, summarizes several critical compression quality evaluation metrics, and integrates many state-of-the-art lossy and lossless compressors. We demonstrate evaluation results using SDRBench and summarize six valuable takeaways that are helpful to the in-depth understanding of lossy compressors.
