Related papers: Rethinking Attention Module Design for Point Cloud…

To address 3D object retrieval, substantial efforts have been made to generate highly discriminative descriptors of 3D objects represented by a single modality, e.g., voxels, point clouds or multi-view images. It is promising to leverage…

We present an attention-based modular neural framework for computer vision. The framework uses a soft attention mechanism allowing models to be trained with gradient descent. It consists of three modules: a recurrent attention module…

Human attention modelling has proven, in recent years, to be particularly useful not only for understanding the cognitive processes underlying visual exploration, but also for providing support to artificial intelligence models that aim to…

We propose Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks. Given an intermediate feature map, our module sequentially infers attention maps along two…

Humans can naturally and effectively find salient regions in complex scenes. Motivated by this observation, attention mechanisms were introduced into computer vision with the aim of imitating this aspect of the human visual system. Such an…

State-of-the-art transformer models use pairwise dot-product based self-attention, which comes at a computational cost quadratic in the input sequence length. In this paper, we investigate the global structure of attention scores computed…

Transformer plays an increasingly important role in various computer vision areas and remarkable achievements have also been made in point cloud analysis. Since they mainly focus on point-wise transformer, an adaptive channel encoding…

The recent advances in 3D sensing technology have made possible the capture of point clouds in significantly high resolution. However, increased detail usually comes at the expense of high storage, as well as computational costs in terms of…

Recent developments in gradient-based attention modeling have seen attention maps emerge as a powerful tool for interpreting convolutional neural networks. Despite good localization for an individual class of interest, these techniques…

We present a novel method that extends the self-attention mechanism of a vision transformer (ViT) for more accurate object detection across diverse datasets. ViTs show strong capability for image understanding tasks such as object…

We propose a new attention mechanism for neural based question answering, which depends on varying granularities of the input. Previous work focused on augmenting recurrent neural networks with simple attention mechanisms which are a…

The visual quality of point clouds has been greatly emphasized since the ever-increasing 3D vision applications are expected to provide cost-effective and high-quality experiences for users. Looking back on the development of point cloud…

Owing to the development of research on local aggregation operators, dramatic breakthrough has been made in point cloud analysis models. However, existing local aggregation operators in the current literature fail to attach decent…

Attention mechanism has become the dominant module in natural language processing models. It is computationally intensive and depends on massive power-hungry multiplications. In this paper, we rethink variants of attention mechanism from…

Point clouds, as a primary representation of 3D data, can be categorized into scene domain point clouds and object domain point clouds. Point cloud self-supervised learning (SSL) has become a mainstream paradigm for learning 3D…

Transformers are increasingly dominating multi-modal reasoning tasks, such as visual question answering, achieving state-of-the-art results thanks to their ability to contextualize information using the self-attention and co-attention…

Modern foundation model architectures rely on attention mechanisms to effectively capture context. However, these methods require linear or quadratic memory in terms of the number of inputs/datapoints, limiting their applicability in…

Fully exploring correlation among points in point clouds is essential for their feature modeling. This paper presents a novel end-to-end graph model, named Point2Node, to represent a given point cloud. Point2Node can dynamically explore…

Recent advances in 3D point cloud analysis bring a diverse set of network architectures to the field. However, the lack of a unified framework to interpret those networks makes any systematic comparison, contrast, or analysis challenging,…

As 3D point clouds become the prevailing shape representation in computer vision, generating high-quality point clouds remains a challenging problem. Flow-based models have shown strong potential due to exact likelihood estimation and…