Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJune 2024
Curriculum pre-training for stylized neural machine translation
Applied Intelligence (KLU-APIN), Volume 54, Issue 17-18Pages 7958–7968https://doi.org/10.1007/s10489-024-05586-9AbstractStylized neural machine translation (NMT) aims to translate sentences of one style into sentences of another style, it is essential for the application of machine translation in a real-world scenario. Most existing methods employ an encoder-...
- research-articleMarch 2024
Transformer-based rapid human pose estimation network
Computers and Graphics (CGRS), Volume 116, Issue CPages 317–326https://doi.org/10.1016/j.cag.2023.09.001AbstractMost current human pose estimation methods pursue excellent performance via large models and intensive computational requirements, resulting in slower models. These methods cannot be effectively adopted for human pose estimation in real ...
Graphical abstractDisplay Omitted
Highlights- The multi-scale fusion strategy can be carefully designed to increase speed while maintaining accuracy.
- The dual scale Transformer can learn long-range dependencies from different scale features.
- A low resolution Transformer can ...
- research-articleOctober 2023
Inconsistency Based Active Learning for temporal object detection.
SUI '23: Proceedings of the 2023 ACM Symposium on Spatial User InteractionArticle No.: 62, Pages 1–4https://doi.org/10.1145/3607822.3616412As a promising direction to alleviate the issue of high cost in label annotation, active learning has made a remarkable progress in image recognition. Recently, some efforts have tried to brought it into more visual tasks such as object detection, human-...
- research-articleOctober 2023
Multi-order spatial interaction network for human pose estimation
AbstractRecent vision Transformer has been applied to human pose estimation and has achieved excellent performance by two-order spatial interaction with self-attention. However, it is still unclear whether higher-order spatial interaction can facilitate ...
Highlights- The Triple Interaction Module can be obtained by pure convolutions to make spatial information interactions three times.
- Combining the Triple Interaction Module with traditional CNN and Transformer can improve the performance of ...
- ArticleOctober 2023
Learning High-Performance Spiking Neural Networks with Multi-Compartment Spiking Neurons
AbstractIn recent years, spiking neural networks (SNNs) have gained significant attention due to bio-inspired working mechanism. The VGG-like and ResNet-like architectures are widely used for SNNs modeling. However, the spiking features of such ...
-
- research-articleMay 2023
High‑accuracy Impedance Compound Control of the Actuator for Periodic Gait of Legged Robots
Journal of Intelligent and Robotic Systems (JIRS), Volume 108, Issue 1https://doi.org/10.1007/s10846-023-01845-yAbstractHydraulic driven legged robots have the advantage of large load capacity and strong environmental adaptability, which has a wide range of prospects for military and civilian applications. And its joint is driven by hydraulic actuator, which is ...
- research-articleMarch 2023
HTMatch: An efficient hybrid transformer based graph neural network for local feature matching
Highlights- We present a new spatial embedding module that enhances the two-view geometric constraints into the graph for better feature matching.
Local feature matching plays a vital role in various computer vision tasks. In this work, we present a novel network that combines feature matching and outlier rejection for finding reliable correspondences between image pairs. The ...
- research-articleFebruary 2023
MEID: mixture-of-experts with internal distillation for long-tailed video recognition
AAAI'23/IAAI'23/EAAI'23: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial IntelligenceArticle No.: 161, Pages 1451–1459https://doi.org/10.1609/aaai.v37i2.25230The long-tailed video recognition problem is especially challenging, as videos tend to be long and untrimmed, and each video may contain multiple classes, causing frame-level class imbalance. The previous method tackles the long-tailed video recognition ...
- research-articleFebruary 2023
Towards Robust Neural Graph Collaborative Filtering via Structure Denoising and Embedding Perturbation
ACM Transactions on Information Systems (TOIS), Volume 41, Issue 3Article No.: 59, Pages 1–28https://doi.org/10.1145/3568396Neural graph collaborative filtering has received great recent attention due to its power of encoding the high-order neighborhood via the backbone graph neural networks. However, their robustness against noisy user-item interactions remains largely ...
- research-articleOctober 2022
SD-GAN: Semantic Decomposition for Face Image Synthesis with Discrete Attribute
MM '22: Proceedings of the 30th ACM International Conference on MultimediaPages 2513–2524https://doi.org/10.1145/3503161.3547791Manipulating latent code in generative adversarial networks (GANs) for facial image synthesis mainly focuses on continuous attribute synthesis (e.g., age, pose and emotion), while discrete attribute synthesis (like face mask and eyeglasses) receives ...
- research-articleJanuary 2022
Stereo CenterNet-based 3D object detection for autonomous driving
Neurocomputing (NEUROC), Volume 471, Issue CPages 219–229https://doi.org/10.1016/j.neucom.2021.11.048AbstractRecently, three-dimensional (3D) detection based on stereo images has progressed remarkably; however, most advanced methods adopt anchor-based two-dimensional (2D) detection or depth estimation to address this problem. Nevertheless, ...
- research-articleJanuary 2021
Dynamic Combination Evaluation Method of Rural Environmental Pollution Control Effect
In recent years, the problem of environmental pollution has become more and more serious, and environmental pollution has become a topic of concern. PM2.5, PM10, hazy weather, and other words about environmental pollution have become hot words and topics ...
- ArticleOctober 2012
Simulating Power Supplier's Behavior in Electricity Market
ISCID '12: Proceedings of the 2012 Fifth International Symposium on Computational Intelligence and Design - Volume 01Pages 390–393https://doi.org/10.1109/ISCID.2012.104This paper explores what will bring to the electricity market if power suppliers make changes in decision making rules. in the repeated bidding process, it is assumed that any power supplier can choose to bid based on Cournot adjustment learning as ...
- ArticleDecember 2009
A Mobile Agent Based General Model for Web Testing
ISCID '09: Proceedings of the 2009 Second International Symposium on Computational Intelligence and Design - Volume 02Pages 158–161https://doi.org/10.1109/ISCID.2009.187In this paper, we first introduce the concepts of mobile agent technology, and then look at some related research on mobile agent technology. Mobile agent is a promising technology to face the problems raised by the increasing complexity and size of ...
- ArticleSeptember 2009
MultiAgent Based On-line Monitoring System for MSW Incinerator
SCALCOM-EMBEDDEDCOM '09: Proceedings of the 2009 International Conference on Scalable Computing and Communications; Eighth International Conference on Embedded ComputingPages 375–380https://doi.org/10.1109/EmbeddedCom-ScalCom.2009.74This paper studies and develops multi agent-based on-line monitoring system for MSW incinerator. With the advent of industry facilities toward high speed and automation, the on-line monitoring mechanism becomes important. The traditional time-based ...
- doctoral_thesisJanuary 2008
Techniques for data consistency in large scale distributed systems - a probabilistic perspective
Consistency has been a perpetual topic in distributed systems. The advent of peer-to-peer systems and sensor networks brings new challenges to the consistency problem. We recognize that given the nature of large scale and high dynamism of the new ...
- ArticleJanuary 2006
PaxonDHT: Achieving Consensus in Distributed Hash Tables
SAINT '06: Proceedings of the International Symposium on Applications on InternetPages 236–244https://doi.org/10.1109/SAINT.2006.48Despite the scalability, availability and resiliency potential suggested by Distributed Hash Tables, their lack of support for replication of mutable data and for strong consistency models stands in the way of their becoming widely accepted as a viable ...
- ArticleApril 2004
Adaptive congestion control for hotspot management in structured peer-to-peer systems
CCGRID '04: Proceedings of the 2004 IEEE International Symposium on Cluster Computing and the GridPages 82–89Distributed hash tables (DHT) bring the promise of increased availability of data to wide-area systems, under the assumption of uniform request load. However, they do not intrinsically offer protection against the hotspot phenomenon, when an item ...