PVNAS : 3D Neural Architecture Search With Point-Voxel Convolution
3D neural networks are widely used in real-world applications (e.g., AR/VR headsets, self-driving cars). They are required to be fast and accurate; however, limited hardware resources on edge devic…
Post-selection Inference of High-dimensional Logistic Regression Under Caseâ€â€¦
Confidence sets are of key importance in high-dimensional statistical inference. Under case–control study, a popular response-selective sampling design in medical study or econometrics, we consid…
Background-Click Supervision for Temporal Action Localization
Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion. To overcome…
Comparison of Beyond 1 GHz C-Plane Freestanding and Sapphire-Substrate GaN-Ba…
With ever-growing demand for 6G networks technology, visible light communication (VLC) as a vital component of 6G has challenging requirement for superior performance of light source. Herein, 20 μ…
Low-Light Image and Video Enhancement Using Deep Learning: A Survey
Low-light image enhancement (LLIE) aims at improving the perception or interpretability of an image captured in an environment with poor illumination. Recent advances in this area are dominated by …
GAN Compression: Efficient Architectures for Interactive Conditional GANs
Conditional Generative Adversarial Networks (cGANs) have enabled controllable image synthesis for many vision and graphics applications. However, recent cGANs are 1-2 orders of magnitude more compu…
Distilled Siamese Networks for Visual Tracking
In recent years, Siamese network based trackers have significantly advanced the state-of-the-art in real-time tracking. Despite their success, Siamese trackers tend to suffer from high memory costs…
Photonic Generation of a Windowed Phase-Coded Microwave Waveform With Suppres…
An approach to photonic generation of a windowed binary phase-coded microwave waveform with suppressed spectrum sidelobes is proposed and demonstrated. An optical double sideband plus carrier signa…
Online Attention Accumulation for Weakly Supervised Semantic Segmentation
Object attention maps generated by image classifiers are usually used as priors for weakly supervised semantic segmentation. However, attention maps usually locate the most discriminative object pa…
A Distributed Model Predictive Control-Based Method for Multidifferent-Target…
This article proposes a framework for multidifferent-target search in unknown environments based on swarm intelligence. In this framework, the idea of distributed model predictive control is introd…
Karya Umum 
Filsafat 
Agama 
Ilmu-ilmu Sosial 
Bahasa 
Ilmu-ilmu Murni 
Ilmu-ilmu Terapan 
Kesenian, Hiburan, dan Olahraga 
Kesusastraan 
Geografi dan Sejarah