Related papers: A Lightweight Sparse Focus Transformer for Remote …

Video captioning aims to generate natural language sentences that describe the given video accurately. Existing methods obtain favorable generation by exploring richer visual representations in encode phase or improving the decoding…

Change captioning is to describe the semantic change between a pair of similar images in natural language. It is more challenging than general image captioning, because it requires capturing fine-grained change information while being…

Seismic images obtained by stacking or migration are usually characterized as low signal-to-noise ratio (SNR), low dominant frequency and sparse sampling both in depth (or time) and offset dimensions. For improving the resolution of seismic…

Although convolutional neural networks (CNNs) have achieved remarkable progress in weakly supervised semantic segmentation (WSSS), the effective receptive field of CNN is insufficient to capture global context information, leading to…

Transformers-based methods have achieved significant performance in image deraining as they can model the non-local information which is vital for high-quality image reconstruction. In this paper, we find that most existing Transformers…

We propose reCSE, a self supervised contrastive learning sentence representation framework based on feature reshaping. This framework is different from the current advanced models that use discrete data augmentation methods, but instead…

Weakly supervised semantic segmentation (WSSS), which aims to mine the object regions by merely using class-level labels, is a challenging task in computer vision. The current state-of-the-art CNN-based methods usually adopt…

Digital cameras consume ~0.1 microjoule per pixel to capture and encode video, resulting in a power usage of ~20W for a 4K sensor operating at 30 fps. Imagining gigapixel cameras operating at 100-1000 fps, the current processing model is…

Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches…

Referring remote sensing image segmentation is crucial for achieving fine-grained visual understanding through free-format textual input, enabling enhanced scene and object extraction in remote sensing applications. Current research…

Convolution neural networks (CNNs) have succeeded in compressive image sensing. However, due to the inductive bias of locality and weight sharing, the convolution operations demonstrate the intrinsic limitations in modeling the long-range…

Features based on sparse representation, especially using the synthesis dictionary model, have been heavily exploited in signal processing and computer vision. However, synthesis dictionary learning typically involves NP-hard sparse coding…

Recently, much advance has been made in image captioning, and an encoder-decoder framework has been adopted by all the state-of-the-art models. Under this framework, an input image is encoded by a convolutional neural network (CNN) and then…

Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of elements of the set,…

Normalizing flows (NFs) provide exact likelihoods and deterministic invertible sampling, but have historically lagged behind diffusion models for large-scale image generation. We identify a key obstacle: NFs are required to learn a single…

In this paper, we present a high-performance and light-weight deep learning model for Remote Sensing Image Classification (RSIC), the task of identifying the aerial scene of a remote sensing image. To this end, we first valuate various…

Recently, Transformer architecture has been introduced into image restoration to replace convolution neural network (CNN) with surprising results. Considering the high computational complexity of Transformer with global attention, some…

In recent years, convolutional neural networks (CNNs) have achieved remarkable advancement in the field of remote sensing image super-resolution due to the complexity and variability of textures and structures in remote sensing images…

Transformers have been successfully applied to the visual tracking task and significantly promote tracking performance. The self-attention mechanism designed to model long-range dependencies is the key to the success of Transformers.…

The remote sensing image change detection task is an essential method for large-scale monitoring. We propose HSANet, a network that uses hierarchical convolution to extract multi-scale features. It incorporates hybrid self-attention and…