IEEE

RMemVD: A Simple Restricted Multi-Memory Bank for Video Deblurring

Abstract: Video deblurring relies on leveraging information from adjacent frames in the video sequence to restore the blurred regions in the current frame. The previous methods mainly employ ...
IEEE

Transforming Disability Into Ability: An Explainable Vision-to-Voice Image Captioning Framework Using Transformer Models and Edge Computing

Abstract: Image captioning is an emerging field at the intersection of computer vision and natural language processing (NLP). It has shown great potential to enhance accessibility by automatically ...
marktechpost

This AI Paper Proposes a Novel Dual-Branch Encoder-Decoder Architecture for Unsupervised Speech Enhancement (SE)

Most learning-based speech enhancement pipelines depend on paired clean–noisy recordings, which are expensive or impossible to collect at scale in real-world conditions. Unsupervised routes like ...
GitHub

eca-attention

Audio super-resolution with an ECA-enhanced encoder-decoder CNN. Upsamples low-rate speech (2/4/8 kHz → 16 kHz) to improve ASR performance, trained on LibriSpeech with Wav2Vec2-based perceptual loss.
IEEE

CM2-Net: A Hybrid CNN-Mamba2 Net for 3D Electromagnetic Tomography image reconstruction

Abstract: Three-dimensional electromagnetic tomography (3D EMT) image reconstruction is characterized by larger data volumes, more complex structures, and stronger spatial correlations. These ...
GitHub

encoder-decoder

Store any user state in query parameters; imagine JSON in a browser URL, while keeping types and structure of data, e.g.numbers will be decoded as numbers not strings. With TS validation. Shared state ...
Nature

Machine-learning model generates images using light

Machine-learning models identify relationships in a data set (called the training data set) and use this training to perform operations on data that the model has not encountered before. This could ...