Image-text retrieval is an important task in bridging vision and language, and its key challenge is to achieve an accurate and efficient semantic alignment between the two modalities. Although advancements have been achieved, there are still the following two limitations: (1) While current methods utilize self-attention to capture region-level relationships within samples, cross-sample and cross-modal relationships are often overlooked, making it difficult to align image and text semantics in a shared embedding space. (2)Image-text retrieval typically involves contrastive learning within batches containing positive and negative samples; however, the batch size, constrained by GPU limitations, limits the scale of negative samples and consequently the model’s learning capability. To address these problems, we propose a novel Latent Space Semantic Alignment Network(LSAN) based on momentum contrast for ITR. Specifically, we introduce a Latent Space Attention Alignment Module that replaces the original region-level self-attention with shared latent space attention, effectively identifying subtle semantic differences and semantic consistency across modalities. Concurrently, a cross-modal momentum contrastive framework, composed of a momentum encoder and a dynamic queue, decouples the number of negative samples from the batch size, which expands the quantity of negative samples. Extensive experiments conducted on Flickr30K and MSCOCO demonstrate that our LSAN not only outperforms existing state-of-the-art methods but also maintains efficient inference performance.

Images captured in hazy or foggy weather conditions are seriously degraded by the scattering of atmospheric particles, which directly influences the performance of outdoor computer vision systems. In this paper, a fast algorithm for single image dehazing is proposed based on linear transformation by assuming that a linear relationship exists in the minimum channel between the hazy image and the haze-free image. First, the principle of linear transformation is analyzed. Accordingly, the method of estimating a medium transmission map is detailed and the weakening strategies are introduced to solve the problem of the brightest areas of distortion. To accurately estimate the atmospheric light, an additional channel method is proposed based on quad-tree subdivision. In this method, average grays and gradients in the region are employed as assessment criteria. Finally, the haze-free image is obtained using the atmospheric scattering model. Numerous experimental results show that this algorithm can clearly and naturally recover the image, especially at the edges of sudden changes in the depth of field. It can, thus, achieve a good effect for single image dehazing. Furthermore, the algorithmic time complexity is a linear function of the image size. This has obvious advantages in running time by guaranteeing a balance between the running speed and the processing effect.

Hazy images hinder image understanding in many applications such as autonomous vehicle. In this paper, we propose an efficient method to improve image quality of hazy images. Our method estimates the transmission function based on a linear model that allows efficient computation and employs quadtree to search for a region that best represents the scatter of airlight. Experiments were conducted using publicly available images. It is demonstrated that our proposed method achieved comparable results to the state-of-the-art ones. In the estimation of sunlight radiance, the quadtree that integrates local brightness and gradient as well as spatial constraint provide a robust means to identify region of sky. Most significantly, our proposed method greatly improved the efficiency. When dealing with moderate and large size image, the improvement could be more than thirty-fold.