Enriching visual feature representations for vision–language tasks using spectral transforms
Authors:
- Oscar OndengOOOscar Ondeng
- Heywood OumaHOHeywood Ouma
- Peter AkuonPAPeter Akuon
- 18 December 2024
- journal article
- research article
- Published by Elsevier in Image and Vision Computing
- Vol. 154
Abstract
No abstract availableKeywords
This publication has 8 references indexed in Scilit:
- Vista-llama: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens2024
- GFNet: Global Filter Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- Arrhythmia Disease Diagnosis Based on ECG Time–Frequency Domain Fusion and Convolutional Neural NetworkIEEE Journal of Translational Engineering in Health and Medicine, 2022
- Fractional Fourier Transform in Time Series PredictionIEEE Signal Processing Letters, 2022
- Fractional Fourier Transform Meets Transformer EncoderIEEE Signal Processing Letters, 2022
- VinVL: Revisiting Visual Representations in Vision-Language Models2021
- Attention on Attention for Image Captioning2019
- Accelerating Convolutional Neural Network With FFT on Embedded HardwareIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2018