With the continuous growth of the population, crowd counting plays a crucial role in intelligent monitoring systems for the Internet of Things (IoT) and smart city development. Accurate monitoring of crowd density not...
详细信息
Enhancing website security is crucial to combat malicious activities,and CAPTCHA(Completely Automated Public Turing tests to tell computers and Humans Apart)has become a key method to distinguish humans from *** text-...
详细信息
Enhancing website security is crucial to combat malicious activities,and CAPTCHA(Completely Automated Public Turing tests to tell computers and Humans Apart)has become a key method to distinguish humans from *** text-based CAPTCHAs are designed to challenge machines while remaining human-readable,recent advances in deep learning have enabled models to recognize them with remarkable *** this regard,we propose a novel two-layer visual attention framework for CAPTCHA recognition that builds on traditional attention mechanisms by incorporating Guided Visual Attention(GVA),which sharpens focus on relevant visual *** have specifically adapted the well-established image captioning task to address this *** approach utilizes the first-level attention module as guidance to the second-level attention component,incorporating two LSTM(Long Short-Term Memory)layers to enhance CAPTCHA *** extensive evaluation across four diverse datasets—Weibo,BoC(Bank of China),Gregwar,and Captcha 0.3—shows the adaptability and efficacy of our *** approach demonstrated impressive performance,achieving an accuracy of 96.70%for BoC and 95.92%for *** results underscore the effectiveness of our method in accurately recognizing and processing CAPTCHA datasets,showcasing its robustness,reliability,and ability to handle varied challenges in CAPTCHA recognition.
Two anaerobic ammonia oxidation(anammox)systems,one with adding nano-scale zerovalent iron modified biochar(nZVI@BC)and the other with adding biochar,were constructed to explore the feasibility of nZVI@BC for enhancin...
详细信息
Two anaerobic ammonia oxidation(anammox)systems,one with adding nano-scale zerovalent iron modified biochar(nZVI@BC)and the other with adding biochar,were constructed to explore the feasibility of nZVI@BC for enhancing the resistance of low-nitrogen anammox processes to low *** results showed that the average nitrogen removal efficiency with nZVI@BC addition at lowtemperatureswas maintained at about 80%,while that with biochar addition gradually decreased to 69.49%.The heme-c content of biomass with nZVI@BC was significantly higher by 36.60%-91.45%.Additional,nZVI@BC addition resulted in more extracellular polymeric substances,better biomass granulation,and a higher abundance of anammox *** particularly,anammox genes hzsA/B/C,hzo and hdh played a pivotal role in maintaining nitrogen removal performance at 15℃.These findings suggest that nZVI@BC has the potential to enhance the resistance of low-nitrogen anammox processes to low temperatures,making it a valuable approach for practical applications in low-nitrogen and low-temperature wastewater treatment.
With the development of deep learning and computer vision, face detection has achieved rapid progress owing. Face detection has several application domains, including identity authentication, security protection, medi...
详细信息
Vehicular crowdsensing has recently received considerable attention, due to its promising capability of collecting useful information for the Internet of Vehicles. However, existing researches in crowdsensing mainly f...
详细信息
In order to improve the detonation characteristics of RDX,a RDX-based composite explosive with TiH_(2)powders was *** effects of content and particle size of TiH_(2)powders on thermal safety,shock wave parameters and ...
详细信息
In order to improve the detonation characteristics of RDX,a RDX-based composite explosive with TiH_(2)powders was *** effects of content and particle size of TiH_(2)powders on thermal safety,shock wave parameters and thermal damage effects of RDX-based composite explosive were studied with the C80 microcalorimeter,air blast experiment system and colorimetric thermometry *** results showed that TiH_(2)powders could enhance the thermal stability of RDX-based composite explosive and increase its ultimate decomposition *** content and particle size of TiH_(2)powders also had significant effects on the thermal safety,detonation velocity,shock wave parameters,fireball temperature and duration of RDX-based composite ***,the differences of TiH_(2)and Ti powders on the detonation energy output rules of RDX-based composite explosives were also compared,showing that TiH_(2)powders had better influences on improving the explosion power and thermal damage effect of RDX-based composite explosives than Ti powders,for the participation of free H_(2)released by TiH_(2)powders in the detonation ***_(2)powders have important research values as a novel energetic additive in the field of military composite explosives.
Preserving formal style in neural machine translation (NMT) is essential, yet often overlooked as an optimization objective of the training processes. This oversight can lead to translations that, though accurate, lac...
详细信息
Preserving formal style in neural machine translation (NMT) is essential, yet often overlooked as an optimization objective of the training processes. This oversight can lead to translations that, though accurate, lack formality. In this paper, we propose how to improve NMT formality with large language models (LLMs), which combines the style transfer and evaluation capabilities of an LLM and the high-quality translation generation ability of NMT models to improve NMT formality. The proposed method (namely INMTF) encompasses two approaches. The first involves a revision approach using an LLM to revise the NMT-generated translation, ensuring a formal translation style. The second approach employs an LLM as a reward model for scoring translation formality, and then uses reinforcement learning algorithms to fine-tune the NMT model to maximize the reward score, thereby enhancing the formality of the generated translations. Considering the substantial parameter size of LLMs, we also explore methods to reduce the computational cost of INMTF. Experimental results demonstrate that INMTF significantly outperforms baselines in terms of translation formality and translation quality, with an improvement of +9.19 style accuracy points in the German-to-English task and +2.16 COMET score in the Russian-to-English task. Furthermore, our work demonstrates the potential of integrating LLMs within NMT frameworks to bridge the gap between NMT outputs and the formality required in various real-world translation scenarios.
This study presents an overview on intelligent reflecting surface(IRS)-enabled sensing and communication for the forthcoming sixth-generation(6G) wireless networks, in which IRSs are strategically deployed to proactiv...
详细信息
This study presents an overview on intelligent reflecting surface(IRS)-enabled sensing and communication for the forthcoming sixth-generation(6G) wireless networks, in which IRSs are strategically deployed to proactively reconfigure wireless environments to improve both sensing and communication(S&C) performance. First, we exploit a single IRS to enable wireless sensing in the base station's(BS's) non-line-of-sight(NLoS) area. In particular, we present three IRS-enabled NLoS target sensing architectures with fully-passive, semi-passive, and active IRSs, respectively. We compare their pros and cons by analyzing the fundamental sensing performance limits for target detection and parameter estimation. Next, we consider a single IRS to facilitate integrated sensing and communication(ISAC), in which the transmit signals at the BS are used for achieving both S&C functionalities, aided by the IRS through reflective beamforming. We present joint transmit signal and receiver processing designs for realizing efficient ISAC, and jointly optimize the transmit beamforming at the BS and reflective beamforming at the IRS to balance the fundamental performance tradeoff between S&C. Furthermore, we discuss multi-IRS networked ISAC, by particularly focusing on multi-IRS-enabled multi-link ISAC, multi-region ISAC, and ISAC signal routing, respectively. Finally, we highlight various promising research topics in this area to motivate future work.
In the electronic manufacturing industry, accurate detection of PCB defects is crucial as it directly impacts product quality and reliability. The primary challenges in PCB defect detection include missed detections a...
详细信息
Graph neural networks (GNNs) have gained increasing popularity, while usually suffering from unaffordable computations for real-world large-scale applications. Hence, pruning GNNs is of great need but largely unexplor...
详细信息
Graph neural networks (GNNs) have gained increasing popularity, while usually suffering from unaffordable computations for real-world large-scale applications. Hence, pruning GNNs is of great need but largely unexplored. The recent work Unified GNN Sparsification (UGS) studies lottery ticket learning for GNNs, aiming to find a subset of model parameters and graph structures that can best maintain the GNN performance. However, it is tailed for the transductive setting, failing to generalize to unseen graphs, which are common in inductive tasks like graph classification. In this work, we propose a simple and effective learning paradigm, Inductive Co-Pruning of GNNs (ICPG), to endow graph lottery tickets with inductive pruning capacity. To prune the input graphs, we design a predictive model to generate importance scores for each edge based on the input. To prune the model parameters, it views the weight’s magnitude as their importance scores. Then we design an iterative co-pruning strategy to trim the graph edges and GNN weights based on their importance scores. Although it might be strikingly simple, ICPG surpasses the existing pruning method and can be universally applicable in both inductive and transductive learning settings. On 10 graph-classification and two node-classification benchmarks, ICPG achieves the same performance level with 14.26%–43.12% sparsity for graphs and 48.80%–91.41% sparsity for the GNN model.
暂无评论