Related papers: SCSA: Exploring the Synergistic Effects Between Sp…
Recent advances in contrastive language-image pretraining (CLIP) have demonstrated strong capabilities in zero-shot classification by aligning visual representations with target text embeddings in an image level. However, in dense…
Self-attention mechanisms, especially multi-head self-attention (MSA), have achieved great success in many fields such as computer vision and natural language processing. However, many existing vision transformer (ViT) works simply inherent…
This paper studies the task of matching image and sentence, where learning appropriate representations across the multi-modal data appears to be the main challenge. Unlike previous approaches that predominantly deploy symmetrical…
Attention mechanisms are the core of foundation models, but their quadratic complexity remains a critical bottleneck for scaling. This challenge has driven the development of efficient attention mechanisms, with sparsity emerging as the…
Informative features play a crucial role in the single image super-resolution task. Channel attention has been demonstrated to be effective for preserving information-rich features in each layer. However, channel attention treats each…
Contextual information has been shown to be powerful for semantic segmentation. This work proposes a novel Context-based Tandem Network (CTNet) by interactively exploring the spatial contextual information and the channel contextual…
Local features at neighboring spatial positions in feature maps have high correlation since their receptive fields are often overlapped. Self-attention usually uses the weighted sum (or other functions) with internal elements of each local…
Recently, many methods have been proposed for object detection. They cannot detect objects by semantic features, adaptively. In this work, according to channel and spatial attention mechanisms, we mainly analyze that different methods…
In this paper, we proposed an integrated model of semantic-aware and contrast-aware saliency combining both bottom-up and top-down cues for effective saliency estimation and eye fixation prediction. The proposed model processes visual…
Recently, crowd counting is a hot topic in crowd analysis. Many CNN-based counting algorithms attain good performance. However, these methods only focus on the local appearance features of crowd scenes but ignore the large-range pixel-wise…
Semantic Change Detection (SCD) in remote sensing imagery requires accurately identifying land-cover changes across multi-temporal image pairs. Despite substantial advancements, including the introduction of transformer-based architectures,…
We study the problem of traffic forecasting, aiming to predict the inflow and outflow of a region in the subsequent time slot. The problem is complex due to the intricate spatial and temporal interdependence among regions. Prior works study…
Change detection (CD) is a fundamental and important task for monitoring the land surface dynamics in the earth observation field. Existing deep learning-based CD methods typically extract bi-temporal image features using a weight-sharing…
Existing semi-supervised video object segmentation methods either focus on temporal feature matching or spatial-temporal feature modeling. However, they do not address the issues of sufficient target interaction and efficient parallel…
Interpreting the internal reasoning of vision-language models is essential for deploying AI in safety-critical domains. Concept-based explainability provides a human-aligned lens by representing a model's behavior through semantically…
In conventional multichannel audio signal enhancement, spatial and spectral filtering are often performed sequentially. In contrast, it has been shown that for neural spatial filtering a joint approach of spectro-spatial filtering is more…
In this paper, we present a so-called interlaced sparse self-attention approach to improve the efficiency of the \emph{self-attention} mechanism for semantic segmentation. The main idea is that we factorize the dense affinity matrix as the…
Most multi-view clustering methods are limited by shallow models without sound nonlinear information perception capability, or fail to effectively exploit complementary information hidden in different views. To tackle these issues, we…
Current feature matching methods focus on point-level matching, pursuing better representation learning of individual features, but lacking further understanding of the scene. This results in significant performance degradation when…
Semantic segmentation in very high resolution (VHR) aerial images is one of the most challenging tasks in remote sensing image understanding. Most of the current approaches are based on deep convolutional neural networks (DCNNs). However,…