![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Chapter and Conference Paper
Improving Few-shot Learning by Spatially-aware Matching and CrossTransformer
Current few-shot learning models capture visual object relations in the so-called meta-learning setting under a fixed-resolution input. However, such models have a limited generalization ability under the scal...
-
Chapter and Conference Paper
Fine-Grained Video Deblurring with Event Camera
Despite CNN-based deblurring models have shown their superiority on solving motion blurs, how to restore photorealistic images from severe motion blurs remains an ill-posed problem due to the loss of temporal ...
-
Chapter and Conference Paper
ANF: Attention-Based Noise Filtering Strategy for Unsupervised Few-Shot Classification
How to learn concepts from few-shot samples remains an open challenge in the deep learning era. The previous meta-learning methods require a large number of annotated samples in the training phase, which still...
-
Chapter and Conference Paper
Aperiodic Control Strategy for Multi-agent Systems with Time-Varying Delays
This note discusses event-triggered strategies for the multi-agent systems(MAS) with time-varying delays. Each agent’s state information will be broadcasted to its neighbors when the error exceeds the threshol...
-
Chapter and Conference Paper
Few-Shot Action Recognition with Permutation-Invariant Attention
Many few-shot learning models focus on recognising images. In contrast, we tackle a challenging task of few-shot action recognition from videos. We build on a C3D encoder for spatio-temporal video blocks to ca...
-
Chapter and Conference Paper
Model Selection for Generalized Zero-Shot Learning
In the problem of generalized zero-shot learning, the datapoints from unknown classes are not available during training. The main challenge for generalized zero-shot learning is the unbalanced data distributio...
-
Chapter and Conference Paper
Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond
We study an open problem of artwork identification and propose a new dataset dubbed Open Museum Identification Challenge (Open MIC). It contains photos of exhibits captured in 10 distinct exhibition spaces of ...
-
Chapter and Conference Paper
A Novel Hybrid Last Level Cache Based on Multi-retention STT-RAM Cells
Spin-transfer torque random access memory (STT-RAM) is one of the most promising substitutes for universal main memory and cache due to its excellent scalability, high storage density and low leakage power. A...
-
Chapter and Conference Paper
Coarse Granularity Data Migration Based Power Management Mechanism for 3D DRAM Cache
3D-stacked technology is a promising solution to improve the performance of on-chip memory system. In our work, a 3D DRAM Cache with high density and wide bandwidth is utilized as the Last Level Cache (LLC). ...
-
Chapter and Conference Paper
Study on Exhaust Heat Recovery Utilizing Organic Rankine Cycle for Diesel Engine at Full-load Conditions
In this paper, organic rankine cycle (ORC) system was utilized to recover diesel engine exhaust heat. The performance of ORC was discussed under the full-load conditions of diesel engine. The results indicate ...
-
Chapter and Conference Paper
Parametric Robust Stability Analysis of a PID Controller for Variable Nozzle Turbocharger
There are many uncertain errors during the A/D and the D/A processes, and also in the fixed-point calculation when proportional-integral-derivative (PID) controller was employed in the engine control module. T...