This work studies the problem of panoptic symbol spotting, which is to spot
and parse both countable object instances (windows, doors, tables, etc.) and
uncountable stuff (wall, railing, etc.) from computer-aided design (CAD)
drawings. Existing methods typically involve either rasterizing the vector
graphics into images and using image-based methods for symbol spotting, or
directly building graphs and using graph neural networks for symbol
recognition. In this paper, we take a different approach, which treats graphic
primitives as a set of 2D points that are locally connected and use point cloud
segmentation methods to tackle it. Specifically, we utilize a point transformer
to extract the primitive features and append a mask2former-like spotting head
to predict the final output. To better use the local connection information of
primitives and enhance their discriminability, we further propose the attention
with connection module (ACM) and contrastive connection learning scheme (CCL).
Finally, we propose a KNN interpolation mechanism for the mask attention module
of the spotting head to better handle primitive mask downsampling, which is
primitive-level in contrast to pixel-level for the image. Our approach, named
SymPoint, is simple yet effective, outperforming recent state-of-the-art method
GAT-CADNet by an absolute increase of 9.6% PQ and 10.4% RQ on the FloorPlanCAD
dataset. The source code and models will be available at
this https URL

该研究探讨了全局符号定位问题，即如何从计算机辅助设计绘图中找到和解析可数的物体实例（窗户、门、桌子等）和不可数的材料（墙壁、栏杆等）。研究采用了点云分割方法，将图形基元视为一组局部连接的二维点，并利用点变换器提取基元特征，并附加类似于 mask2former 的定位头来进行最终输出预测。另外，为了更好地利用基元的局部连接信息并增强其可区分性，研究还提出了关联模块（ACM）和对比连接学习方案（CCL）。该方法被命名为 SymPoint，简单而有效，在 FloorPlanCAD 数据集上相较于最先进方法 GAT-CADNet 提高了 9.6％的 PQ 和 10.4％的 RQ。

符号作为点：基于点表示的全面符号定位

Symbol as Points: Panoptic Symbol Spotting via Point-based  Representation

2D+3D facial expression recognition (FER) can effectively cope with
illumination changes and pose variations by simultaneously merging 2D texture
and more robust 3D depth information. Most deep learning-based approaches
employ the simple fusion strategy that concatenates the multimodal features
directly after fully-connected layers, without considering the different
degrees of significance for each modality. Meanwhile, how to focus on both 2D
and 3D local features in salient regions is still a great challenge. In this
letter, we propose the adaptive fusion network with masks (AFNet-M) for 2D+3D
FER. To enhance 2D and 3D local features, we take the masks annotating salient
regions of the face as prior knowledge and design the mask attention module
(MA) which can automatically learn two modulation vectors to adjust the feature
maps. Moreover, we introduce a novel fusion strategy that can perform adaptive
fusion at convolutional layers through the designed importance weights
computing module (IWC). Experimental results demonstrate that our AFNet-M
achieves the state-of-the-art performance on BU-3DFE and Bosphorus datasets and
requires fewer parameters in comparison with other models.

本研究提出了一种自适应融合网络，利用人脸显著区域的掩码来增强 2D 和 3D 局部特征，通过设计的调制向量自动学习，以及计算重要性权重的新型融合策略可以在卷积层中执行自适应融合。实验结果表明，该方法在 BU-3DFE 和 Bosphorus 数据集上具有最先进的性能并且需要较少的参数。