collaborators

6 papers

cs.LG2025

Indirect Attention: Turning Context Misalignment into a Feature

Bissmella Bahaduri, Hicham Talaoubrid, Fangchen Feng +2

The attention mechanism has become a cornerstone of modern deep learning architectures, where keys and values are typically derived from the same underlying sequence or representat…

cs.CV2024

Interactive Masked Image Modeling for Multimodal Object Detection in Remote Sensing

Minh-Duc Vu, Zuheng Ming, Fangchen Feng +2

Object detection in remote sensing imagery plays a vital role in various Earth observation applications. However, unlike object detection in natural scene images, this task is part…

eess.IV2024

Universal End-to-End Neural Network for Lossy Image Compression

Bouzid Arezki, Fangchen Feng, Anissa Mokraoui

This paper presents variable bitrate lossy image compression using a VAE-based neural network. An adaptable image quality adjustment strategy is proposed. The key innovation involv…

eess.IV2024

Convolutional Transformer-Based Image Compression

Bouzid Arezki, Fangchen Feng, Anissa Mokraoui

In this paper, we present a novel transformer-based architecture for end-to-end image compression. Our architecture incorporates blocks that effectively capture local dependencies…

eess.IV2024

Efficient Image Compression Using Advanced State Space Models

Bouzid Arezki, Anissa Mokraoui, Fangchen Feng

Transformers have led to learning-based image compression methods that outperform traditional approaches. However, these methods often suffer from high complexity, limiting their p…

cs.CV2024

Multimodal Transformer Using Cross-Channel attention for Object Detection in Remote Sensing Images

Bissmella Bahaduri, Zuheng Ming, Fangchen Feng +1

Object detection in Remote Sensing Images (RSI) is a critical task for numerous applications in Earth Observation (EO). Differing from object detection in natural images, object de…