9 Result(s)
-
Chapter and Conference Paper
Optimizing the Parallelism of Communication and Computation in Distributed Training Platform
With the development of deep learning, DNN models have become more complex. Large-scale model parameters enhance the level of AI by improving the accuracy of DNN models. However, they also present more severe ...
-
Chapter and Conference Paper
A Hybrid Kernel Pruning Approach for Efficient and Accurate CNNs
To reduce the overhead of neural network training and inference, several techniques have been widely used to prune neural network models. Pruning algorithms can significantly reduce the number of parameters in...
-
Chapter and Conference Paper
An Efficient Copy-Move Detection Algorithm Based on Superpixel Segmentation and Harris Key-Points
Region duplication is a commonly used operation in digital image processing. Since region duplication could be utilized to easily tamper the raw content by intentional attackers, it has become a very important...
-
Chapter and Conference Paper
Data Hiding-Based Video Error Concealment Method Using Compressed Sensing
The video error concealment based on data hiding (VECDH) method aims to conceal video errors due to transmission according to the auxiliary data directly extracted from the received video file. It has the prop...
-
Chapter and Conference Paper
An Artificial Bee Colony Algorithm with History-Driven Scout Bees Phase
The scout bees phase of artificial bee colony (ABC) algorithm emulates a random restart and cannot make sure the quality of the solution generated. Thus, we propose to use the entire search history to improve ...
-
Chapter and Conference Paper
Improved Bayesian Network Structure Learning with Node Ordering via K2 Algorithm
The precise construction of Bayesian network classifier from database is an NP-hard problem and still one of the most exciting challenges. K2 algorithm can reduce search space effectively, improve learning eff...
-
Chapter and Conference Paper
MMODE: A Memetic Multiobjective Differential Evolution Algorithm
For the multiobjective problems, some global search methods may fail to find the Pareto optima with both accuracy and diversity. To pursue the two goals at the same time, a new memetic multiobjective different...
-
Chapter and Conference Paper
Mobile Internet-Based Compression-Aware Scalable Video Coding - Rate Control for Enhancement Layers
The scalable video codec extension to the H.264 standard (H.264 SVC) is designed deliver the benefits described in the preceding ideal scenario. That is, it can yield decoded video at different frame rates, re...
-
Chapter and Conference Paper
Real-Time Vehicle Detection and Tracking System in Street Scenarios
The paper represents a framework for a vehicle detection, segmentation, and tracking system. The Challenge is to use a single monocular camera as input, in order to achieve a low cost final system that meets t...
