Search Results for author:
Found 8 papers, 2 papers with code
Age-of-Information-Aware Distributed Task Offloading and Resource Allocation in Mobile Edge Computing Networks
In existing studies, joint optimization of overall task offloading and UA is seldom considered due to the complexity of combinatorial optimization problems, and in cases where it is considered, linear objective functions such as power consumption are adopted.
Joint Optimization on Uplink OFDMA and MU-MIMO for IEEE 802.11ax: Deep Hierarchical Reinforcement Learning Approach
In unsaturated traffic conditions, considering packet volumes per user introduces a combinatorial problem, requiring the simultaneous optimization of MU-MIMO user selection and RA along the time-frequency-space axis.
Enhancing Sum-Rate Performance in Constrained Multicell Networks: A Low-Information Exchange Approach
Despite the extensive research on massive MIMO systems for 5G telecommunications and beyond, the reality is that many deployed base stations are equipped with a limited number of antennas rather than supporting massive MIMO configurations.
Patch-MI: Enhancing Model Inversion Attacks via Patch-Based Reconstruction
This approach allows the synthesis of images that are similar to the target dataset distribution, even in cases of dissimilar auxiliary dataset distribution.
Deeper Understanding of Black-box Predictions via Generalized Influence Functions
However, growing non-convexity and the number of parameters in modern large-scale models lead to imprecise influence approximation and instability in computations.
Privacy-Protection Drone Patrol System based on Face Anonymization
These attractive advantages such as high-resolution cameras and mobility can be a double-edged sword, i. e., privacy infringement.
Extreme Low Resolution Activity Recognition with Multi-Siamese Embedding Learning
This paper presents an approach for recognizing human activities from extreme low resolution (e. g., 16x12) videos.
Privacy-Preserving Human Activity Recognition from Extreme Low Resolution
We introduce the paradigm of inverse super resolution (ISR), the concept of learning the optimal set of image transformations to generate multiple low-resolution (LR) training videos from a single video.
