Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- surveyJuly 2024
Review and Analysis of RGBT Single Object Tracking Methods: A Fusion Perspective
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Volume 20, Issue 8Article No.: 259, Pages 1–27https://doi.org/10.1145/3651308Visual tracking is a fundamental task in computer vision with significant practical applications in various domains, including surveillance, security, robotics, and human-computer interaction. However, it may face limitations in visible light data, such ...
- research-articleJuly 2024
A siamese-based verification system for open-set architecture attribution of synthetic images
Pattern Recognition Letters (PTRL), Volume 180, Issue CApr 2024, Pages 75–81https://doi.org/10.1016/j.patrec.2024.03.002AbstractDespite the wide variety of methods developed for synthetic image attribution, most of them can only attribute images generated by models or architectures included in the training set and do not work with unknown architectures, hindering their ...
Highlights- New verification framework for open-set architecture attribution of synthetic images.
- Tested with several types of generative architectures in closed and open set scenarios.
- Generalization tests prove that the system can verify ...
- research-articleJuly 2024
DualGAD: Dual-bootstrapped self-supervised learning for graph anomaly detection
Information Sciences: an International Journal (ISCI), Volume 668, Issue CMay 2024https://doi.org/10.1016/j.ins.2024.120520AbstractGraph anomaly detection (GAD) is an emerging and essential research field for discovering anomalous individuals (e.g., nodes or edges) that deviate significantly from the normal majority in an attributed graph. Unlike other anomaly types (e.g., ...
- research-articleJuly 2024
An analytical subthreshold I–V model of SiC MOSFETs
- Yi Li,
- Tao Zhou,
- Geng Jiang,
- Liangbin Deng,
- Zixuan Guo,
- Qiaoling Sun,
- Bangyong Yin,
- Yuqiu Yang,
- Junyao Wu,
- Huan Cai,
- Jun Wang,
- Jungang Yin,
- Qin Liu,
- Linfeng Deng
Microelectronics Journal (MICROJ), Volume 146, Issue CApr 2024https://doi.org/10.1016/j.mejo.2024.106138AbstractIn this article, an analytical I–V model for calculating subthreshold current of SiC MOSFETs is presented. This model starts with planar MOSFETs and utilizes the one-dimensional Poisson’s equation to derive an analytical expression for the ...
- research-articleJuly 2024
Data-driven dynamic pricing and inventory management of an omni-channel retailer in an uncertain demand environment
Expert Systems with Applications: An International Journal (EXWA), Volume 244, Issue CJun 2024https://doi.org/10.1016/j.eswa.2023.122948AbstractIn recent years, omni-channel retailing has become immensely popular among both retailers and consumers. In this approach, retailers often leverage their brick-and-mortar stores to fulfill online orders, leading to the need for simultaneous ...
-
- research-articleJune 2024
EMAT: Efficient feature fusion network for visual tracking via optimized multi-head attention
AbstractThe tracking methods based on Transformer have shown great potential in visual tracking and achieved significant tracking performance. The traditional transformer based feature fusion network divides a whole feature map into multiple image ...
- review-articleJune 2024
A survey on algorithms for Nash equilibria in finite normal-form games
Computer Science Review (COMPSR), Volume 51, Issue CFeb 2024https://doi.org/10.1016/j.cosrev.2023.100613AbstractNash equilibrium is one of the most influential solution concepts in game theory. With the development of computer science and artificial intelligence, there is an increasing demand on Nash equilibrium computation, especially for Internet ...
Highlights- A classification on Nash equilibrium algorithms in the literature with basic ideas on design and analysis presented.
- A comprehensive comparison on Nash equilibrium algorithms in the literature over different kinds of games.
- ...
- research-articleJune 2024
Sentence-level sentiment classification based on multi-attention bidirectional gated spiking neural P systems
Applied Soft Computing (APSC), Volume 152, Issue CFeb 2024https://doi.org/10.1016/j.asoc.2024.111231AbstractThe GSNP model is a new recurrent-like network inspired by nonlinear spiking mechanisms in nonlinear spiking neural P systems. In this study, a novel sentiment classification model MA-BiGSNP is established by using bidirectional GSNP model ...
Highlights- A bidirectional GSNP recurrent-like model is constructed, called BiGSNP.
- A multi-attention mechanism is designed for sentence and document representations.
- BiGSNP and the multi-attention is used to propose a sentiment ...
- research-articleJune 2024
Settling the variance of multi-agent policy gradients
- Jakub Grudzien Kuba,
- Muning Wen,
- Linghui Meng,
- Shangding Gu,
- Haifeng Zhang,
- David Henry Mguni,
- Jun Wang,
- Yaodong Yang
NIPS '21: Proceedings of the 35th International Conference on Neural Information Processing SystemsDecember 2021, Article No.: 1031, Pages 13458–13470Policy gradient (PG) methods are popular reinforcement learning (RL) methods where a baseline is often applied to reduce the variance of gradient estimates. In multi-agent RL (MARL), although the PG theorem can be naturally extended, the effectiveness of ...
- research-articleJune 2024
Neural auto-curricula
NIPS '21: Proceedings of the 35th International Conference on Neural Information Processing SystemsDecember 2021, Article No.: 268, Pages 3504–3517When solving two-player zero-sum games, multi-agent reinforcement learning (MARL) algorithms often create populations of agents where, at each iteration, a new agent is discovered as the best response to a mixture over the opponent population. Within ...
- research-articleJune 2024
Research on Key Technologies for Intelligent Detection of High-Speed Railway Pantograph System Status Based on Deep learning
CVDL '24: Proceedings of the International Conference on Computer Vision and Deep LearningJanuary 2024, Article No.: 43, Pages 1–6https://doi.org/10.1145/3653781.3653827Abstract: This research proposes an innovative intelligent detection methodology tailored for the high-speed train catenary system, leveraging FPGA-accelerated MobileNetV2. Exploiting the exceptional computational capabilities of the MobileNetV2 ...
- research-articleMay 2024
Invariant learning via probability of sufficient and necessary causes
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 3496, Pages 79832–79857Out-of-distribution (OOD) generalization is indispensable for learning models in the wild, where testing distribution typically unknown and different from the training. Recent methods derived from causality have shown great potential in achieving OOD ...
- research-articleMay 2024
Online PCA in converging self-consistent field equations
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 2088, Pages 48138–48149Self-consistent Field (SCF) equation is a type of nonlinear eigenvalue problem in which the matrix to be eigen-decomposed is a function of its own eigenvectors. It is of great significance in computational science for its connection to the Schrödinger ...
- research-articleMay 2024
D-separation for causal self-explanation
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 1890, Pages 43620–43633Rationalization is a self-explaining framework for NLP models. Conventional work typically uses the maximum mutual information (MMI) criterion to find the rationale that is most indicative of the target label. However, this criterion can be influenced by ...
- research-articleMay 2024
Lending interaction wings to recommender systems with conversational agents
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 1213, Pages 27951–27979Recommender systems trained on offline historical user behaviors are embracing conversational techniques to online query user preference. Unlike prior conversational recommendation approaches that systemically combine conversational and recommender parts ...
- research-articleMay 2024
Interpretable reward redistribution in reinforcement learning: a causal approach
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 887, Pages 20208–20229A major challenge in reinforcement learning is to determine which state-action pairs are responsible for future rewards that are delayed. Reward redistribution serves as a solution to re-assign credits for each time step from observed sequences. While ...
- research-articleMay 2024
UltraRE: enhancing RecEraser for recommendation unlearning via error decomposition
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 553, Pages 12611–12625With growing concerns regarding privacy in machine learning models, regulations have committed to granting individuals the right to be forgotten while mandating companies to develop non-discriminatory machine learning systems, thereby fueling the study ...
- research-articleMay 2024
ChessGPT: bridging policy learning and language modeling
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 316, Pages 7216–7262When solving decision-making tasks, humans typically depend on information from two key sources: (1) Historical policy data, which provides interaction replay from the environment, and (2) Analytical insights in natural language form, exposing the ...
- research-articleMay 2024
An efficient end-to-end training approach for zero-shot human-AI coordination
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 119, Pages 2636–2658The goal of zero-shot human-AI coordination is to develop an agent capable of collaborating with humans without relying on human data. Prevailing two-stage population-based methods require a diverse population of mutually distinct policies to simulate ...
- research-articleMay 2024
Aggregating Neighbourhood Information of Items with Knowledge Graph and User Intent Information behind Interaction for Recommendation
DSDE '24: Proceedings of the 2024 7th International Conference on Data Storage and Data EngineeringFebruary 2024, Pages 25–33https://doi.org/10.1145/3653924.3653929In knowledge graph-based recommendation systems, modeling based on item features is a crucial direction. To further enhance the effectiveness of recommendation, we can study common similarities among items based on their shared attributes. The attribute ...