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-articleApril 2025
Optimizing reinforcement learning for large action spaces via generative models: Battery pattern selection
AbstractIntrinsic and environmental factors contribute to variability in the performance of cells within a battery pack, affecting the lifespan and safety of battery systems. To solve this problem, active and passive equalization methods are proposed. ...
- research-articleFebruary 2025
A generative and discriminative model for diversity-promoting recommendation
AbstractDiversity-promoting recommender systems with the goal of recommending diverse and relevant results to users, have received significant attention. However, current studies often face a trade-off: they either recommend highly accurate but ...
- research-articleJanuary 2025
Ipdm: identity preserving diffusion model for face sketch and photo synthesis
Machine Vision and Applications (MVAA), Volume 36, Issue 2https://doi.org/10.1007/s00138-024-01658-5AbstractFace sketch and photo synthesis is widely applied in industry and information fields, such as entertainment business and heterogeneous face retrieval. The key challenge lies in completing a face transformation with both good visual effects and ...
- research-articleJanuary 2025
HiddenSinger: High-quality singing voice synthesis via neural audio codec and latent diffusion models
AbstractRecently, denoising diffusion models have demonstrated remarkable performance among generative models in various domains. However, in the speech domain, there are limitations in complexity and controllability to apply diffusion models for time-...
Highlights- Introduce HiddenSinger, a high-quality singing voice synthesis model.
- Propose HiddenSinger-U, an unsupervised learning framework to train with unlabeled datasets.
- Audio samples are available at https://jisang93.github.io/...
- research-articleJanuary 2025
Learning to segment self-generated from externally caused optic flow through sensorimotor mismatch circuits
AbstractEfficient sensory detection requires the capacity to ignore task-irrelevant information, for example when optic flow patterns created by egomotion need to be disentangled from object perception. To investigate how this is achieved in the visual ...
-
- research-articleJanuary 2025
A unified framework of semi-supervised community detection integrating network topology and node content
Information Sciences: an International Journal (ISCI), Volume 686, Issue Chttps://doi.org/10.1016/j.ins.2024.121349AbstractDetecting the community structure within networks is important because it aids in the analysis of complex networks. However, the existence of diverse complex structures in the network topology can limit the topological information’s ability to ...
- research-articleJanuary 2025
A generative design method of airfoil based on conditional variational autoencoder
Engineering Applications of Artificial Intelligence (EAAI), Volume 139, Issue PAhttps://doi.org/10.1016/j.engappai.2024.109461AbstractThe challenges in multi-objective and multi-dimensional optimization design of airfoils, marked by prolonged optimization cycles and low accuracy, call for an efficient solution to expedite airfoil design. This study presents an innovative ...
Highlights- Airfoil-VAE generates diverse airfoils similar to UIUC, solving data scarcity.
- AFD-CVAE reduces error by 65% compared to PG-cWGAN.
- APD-CVAE reduces error by 99.99% compared to Airfoil-Cp-GAN.
- research-articleJanuary 2025
Knowledge-aware audio-grounded generative slot filling for limited annotated data
AbstractManually annotating fine-grained slot-value labels for task-oriented dialogue (ToD) systems is an expensive and time-consuming endeavour. This motivates research into slot-filling methods that operate with limited amounts of labelled data. ...
Highlights- A knowledge-aware audio-grounded (KA2G) generative slot-filling framework is proposed
- KA2G integrates knowledge with two tree-constrained pointer generator (TCPGen)
- 4.6% and 11.2% SLU-F1 increases achieved for rare and unseen ...
- research-articleJanuary 2025
Data augmentation with generative models improves detection of Non-B DNA structures
Computers in Biology and Medicine (CBIM), Volume 184, Issue Chttps://doi.org/10.1016/j.compbiomed.2024.109440AbstractNon-B DNA structures, or flipons, are important functional elements that regulate a large spectrum of cellular programs. Experimental technologies for flipon detection are limited to the subsets that are active at the time of an experiment and ...
Graphical abstractDisplay Omitted
Highlights- Data augmentation with diffusion models improve detection of non-B DNA structures, or flipons.
- Diffusion model outperformed WGAN and VQ-VAE models for Z-DNA and H-DNA.
- WGAN models outperform diffusion models for quadruplexes.
- ...
- ArticleDecember 2024
- research-articleNovember 2024
Explicit-implicit priori knowledge-based diffusion model for generative medical image segmentation
AbstractThe diffusion probabilistic model (DPM) has achieved unparalleled results in current image generation tasks, and some recent research works employed it in several computer vision tasks, such as image super-resolution, object detection, etc. ...
- research-articleNovember 2024
LD-CSNet: A latent diffusion-based architecture for perceptual Compressed Sensing
AbstractCompressed Sensing (CS) is a groundbreaking paradigm in image acquisition, challenging the constraints of the Nyquist–Shannon sampling theorem. This enables high-quality image reconstruction using a minimal number of measurements. Neural Networks’...
Highlights- Latent diffusion-based architecture tackles image compressive sensing challenges.
- Pre-trained generative networks model the prior information of natural images.
- Diffusion models maximize likelihood estimation in a low-dimensional ...
- ArticleOctober 2024
Taming Diffusion for Fashion Clothing Generation with Versatile Condition
AbstractThe intersection of art and artificial intelligence (AI) is rapidly evolving, particularly within the realm of fashion design, where AI’s potential to augment human creativity is being increasingly recognized. Despite the progress achieved through ...
- demonstrationOctober 2024
PronounSE: SFX Synthesizer from Language-Independent Vocal Mimic Representation
UIST Adjunct '24: Adjunct Proceedings of the 37th Annual ACM Symposium on User Interface Software and TechnologyArticle No.: 21, Pages 1–3https://doi.org/10.1145/3672539.3686748Sound creators make various sound effects (SFX) depending on auditory events utilizing knowledge, techniques, and experience. These are challenging tasks for inexperienced creators. In this research, we focus on the fact that it is relatively easy for ...
- research-articleOctober 2024
Dual-enhanced generative model with graph attention network and contrastive learning for aspect sentiment triplet extraction
AbstractCurrently, generative models are showing exceptional abilities to identify and generate triplets expressed within sentences within the field of Aspect Sentiment Triplet Extraction (ASTE). Although these models are capable of recognizing terms and ...
- ArticleOctober 2024
VIMs: Virtual Immunohistochemistry Multiplex Staining via Text-to-Stain Diffusion Trained on Uniplex Stains
AbstractThis paper introduces a Virtual Immunohistochemistry Multiplex staining (VIMs) model designed to generate multiple immunohistochemistry (IHC) stains from a single hematoxylin and eosin (H&E) stained tissue section. IHC stains are crucial in ...
- ArticleOctober 2024
Spot the Difference: Difference Visual Question Answering with Residual Alignment
Medical Image Computing and Computer Assisted Intervention – MICCAI 2024Pages 649–658https://doi.org/10.1007/978-3-031-72086-4_61AbstractDifference Visual Question Answering (DiffVQA) introduces a new task aimed at understanding and responding to questions regarding the disparities observed between two images. Unlike traditional medical VQA tasks, DiffVQA closely mirrors the ...
- research-articleOctober 2024
Synthetic lidar point cloud generation using deep generative models for improved driving scene object recognition
AbstractThe imbalanced distribution of different object categories poses a challenge for training accurate object recognition models in driving scenes. Supervised machine learning models trained on imbalanced data are biased and easily overfit the ...
Highlights- Data augmentation for driving scene object recognition using generative models.
- A systematic benchmark of generative models for lidar point clouds.
- L-GAN boosts point-based and graph-based object recognition methods effectively.
- research-articleOctober 2024
Advancing Image Generation with Denoising Diffusion Probabilistic Model and ConvNeXt-V2: A novel approach for enhanced diversity and quality
Computer Vision and Image Understanding (CVIU), Volume 247, Issue Chttps://doi.org/10.1016/j.cviu.2024.104077AbstractIn the rapidly evolving domain of image generation, the availability of sufficient data is crucial for effective model training. However, obtaining a large dataset is often challenging. Medical imaging, industrial monitoring, and self-driving ...
Highlights- Novel Approach with DDPM and ConvNeXt-V2: Combines DDPM and ConvNeXt-V2 to enhance image diversity and quality from a single input.
- High Performance and Robustness: The model excels with a Pixel Diversity score of 0.87, LPIPS ...
- research-articleOctober 2024
Towards diverse image-to-image translation via adaptive normalization layer and contrast learning
AbstractA nice image-to-image translation framework is able to acquire an explicit and credible mapping relationship between the source domain and target domains while satisfying two requirements. One is simplicity, the other is extensibility over ...
Graphical abstractDisplay Omitted
Highlights- We propose a concise but versatile generative model for image-to-image tasks.
- A novel Semantics-Appearance Spatially Adaptive Normalization is introduced.
- Semantic-aware and Appearance-aware Contrastive Losses are proposed.
- An ...