Semi-supervised learning (SSL), thanks to the significant reduction of data annotation costs, has been an active research topic for large-scale 3D scene understanding. However, the existing SSL-based methods suffer fr...
详细信息
Mobile Crowdsensing (MCS) is often accompanied by various adverse objectives when performing data collection, which makes it difficult to collect accurate data of the entire target area with low cost. Therefore, how t...
详细信息
Quantum dot light-emitting diodes(QLEDs)are a class of high-performance solution-processed electroluminescent(EL)devices highly attractive for next-generation display *** the encouraging advances in the mechanism inve...
详细信息
Quantum dot light-emitting diodes(QLEDs)are a class of high-performance solution-processed electroluminescent(EL)devices highly attractive for next-generation display *** the encouraging advances in the mechanism investigation,material chemistry,and device engineering of QLEDs,the lack of standard protocols for the characterization of QLEDs may cause inaccurate measurements of device parameters and invalid comparison of different ***,we report a comprehensive study on the characterizations of QLEDs using various *** show that the emission non-uniformity across the active area,nonLambertian angular distributions of EL intensity,and discrepancies in the adopted spectral luminous efficiency functions could introduce significant errors in the device *** errors in the operational-lifetime measurements may arise from the inaccurate determination of the initial luminance and inconsistent methods for analyzing the luminance-decay ***,we suggest a set of recommended practices and a checklist for device characterizations,aiming to help the researchers in the QLED field to achieve accurate and reliable measurements.
Single-shot ultrafast multidimensional optical imaging(UMOI) combines ultrahigh temporal resolution with multidimensional imaging capabilities in a snapshot, making it an essential tool for real-time detection and ana...
Single-shot ultrafast multidimensional optical imaging(UMOI) combines ultrahigh temporal resolution with multidimensional imaging capabilities in a snapshot, making it an essential tool for real-time detection and analysis of ultrafast scenes. However, current single-shot UMOI techniques cannot simultaneously capture the spatial-temporal-spectral complex amplitude information, hampering it from complete analyses of ultrafast *** address this issue, we propose a single-shot spatial-temporal-spectral complex amplitude imaging(STS-CAI)technique using wavelength and time multiplexing. By employing precise modulation of a broadband pulse via an encoding plate in coherent diffraction imaging and spatial-temporal shearing through a wide-open-slit streak camera, dual-mode multiplexing image reconstruction of wavelength and time is achieved, which significantly enhances the efficiency of information acquisition. Experimentally, a custom-built STS-CAI apparatus precisely measures the spatiotemporal characteristics of picosecond spatiotemporally chirped and spatial vortex pulses, respectively. STS-CAI demonstrates both ultrahigh temporal resolution and robust phase sensitivity. Prospectively, this technique is valuable for spatiotemporal coupling measurements of large-aperture ultrashort pulses and offers promising applications in both fundamental research and applied sciences.
Identity-preserving human detection is important for the privacy-protecting applications. IPHD [1] is a newly collected identity-preserving dataset that only contains depth and thermal images, which have much less inf...
详细信息
ISBN:
(数字)9781728130798
ISBN:
(纸本)9781728130804
Identity-preserving human detection is important for the privacy-protecting applications. IPHD [1] is a newly collected identity-preserving dataset that only contains depth and thermal images, which have much less information than RGB images. While less information and weakly labeled ground-truth boxes make it difficult to locate the objects correctly. In this paper, we adopt an efficient depth-thermal fusion approach to combine these two different inputs and enhance the representation. Moreover, a noise robust hard example mining algorithm is proposed to deal with weakly labeled data. The experiments show that our single model with single scale testing can get the AP=88.1 at IoU=0.5, which is a significant improvement compared with other competition results.
Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean test images, yet consistently predicts a...
详细信息
ISBN:
(数字)9781728171685
ISBN:
(纸本)9781728171692
Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean test images, yet consistently predicts a particular target class for any test examples that contain the trigger pattern. As such, backdoor attacks are hard to detect, and have raised severe security concerns in real-world applications. Thus far, backdoor research has mostly been conducted in the image domain with image classification models. In this paper, we show that existing image backdoor attacks are far less effective on videos, and outline 4 strict conditions where existing attacks are likely to fail: 1) scenarios with more input dimensions (eg. videos), 2) scenarios with high resolution, 3) scenarios with a large number of classes and few examples per class (a ``sparse dataset"), and 4) attacks with access to correct labels (eg. clean-label attacks). We propose the use of a universal adversarial trigger as the backdoor trigger to attack video recognition models, a situation where backdoor attacks are likely to be challenged by the above 4 strict conditions. We show on benchmark video datasets that our proposed backdoor attack can manipulate state-of-the-art video models with high success rates by poisoning only a small proportion of training data (without changing the labels). We also show that our proposed backdoor attack is resistant to state-of-the-art backdoor defense/detection methods, and can even be applied to improve image backdoor attacks. Our proposed video backdoor attack not only serves as a strong baseline for improving the robustness of video models, but also provides a new perspective for more understanding more powerful backdoor attacks.
Video transformers have achieved impressive results on major video recognition benchmarks, which however suffer from high computational cost. In this paper, we present STTS, a token selection framework that dynamicall...
详细信息
Deep Neural Networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding human-imperceptible perturbations to the benign inputs. Simultaneously, adversarial examples exhibit transferability acro...
详细信息
The rapid advancement of artificial intelligence(AI) has significantly impacted photonics, creating a symbiotic relationship that accelerates the development and applications of both fields. From the perspective of AI...
The rapid advancement of artificial intelligence(AI) has significantly impacted photonics, creating a symbiotic relationship that accelerates the development and applications of both fields. From the perspective of AI aiding photonics, deep-learning methods and various intelligent algorithms have been developed for designing complex photonic structures, where traditional design approaches fall short. AI's capability to process and analyze large data sets has enabled the discovery of novel materials, such as for photovoltaics,leading to enhanced light absorption and efficiency. AI is also significantly transforming the field of optical imaging with improved performance. In addition, AI-driven techniques have revolutionized optical communication systems by optimizing signal processing and enhancing the bandwidth and reliability of data transmission. Conversely, the contribution of photonics to AI is equally profound. Photonic technologies offer unparalleled advantages in the development of AI hardware, providing solutions to overcome the bottlenecks of electronic systems. The implementation of photonic neural networks, leveraging the high speed and parallelism of optical computing, demonstrates significant improvements in the processing speed and energy efficiency of AI computations. Furthermore, advancements in optical sensors and imaging technologies not only enrich AI applications with high-quality data but also expand the capabilities of AI in fields such as autonomous vehicles and medical imaging. We provide comprehensive knowledge and a detailed analysis of the current state of the art, addressing both challenges and opportunities at the intersection of AI and photonics. The multifaceted interactions between AI and photonics will be explored, illustrating how AI has become an indispensable tool in the development of photonics and how photonics, in turn,facilitates advancements in AI. Through a collection of case studies and examples, we underscore the potential
Commit messages are natural language descriptions of code changes, which are important for software evolution such as code understanding and maintenance. However, previous methods are trained on the entire dataset wit...
详细信息
暂无评论