Multi-class 3D object detection aims to localize and classify objects of
multiple categories from point clouds. Due to the nature of point clouds, i.e.
unstructured, sparse and noisy, some features benefit-ting multi-class
discrimination are underexploited, such as shape information. In this paper, we
propose a novel 3D shape signature to explore the shape information from point
clouds. By incorporating operations of symmetry, convex hull and chebyshev
fitting, the proposed shape sig-nature is not only compact and effective but
also robust to the noise, which serves as a soft constraint to improve the
feature capability of multi-class discrimination. Based on the proposed shape
signature, we develop the shape signature networks (SSN) for 3D object
detection, which consist of pyramid feature encoding part, shape-aware grouping
heads and explicit shape encoding objective. Experiments show that the proposed
method performs remarkably better than existing methods on two large-scale
datasets. Furthermore, our shape signature can act as a plug-and-play component
and ablation study shows its effectiveness and good scalability

本文提出了一种新颖的 3D 形状签名来探索点云的形状信息，称为形状签名网络（SSN），并使用 SSN 进行 3D 物体检测，实验结果表明该方法表现明显优于现有方法，并具有良好的扩展性。

SSN: 基于形状特征的点云多类物体检测神经网络

SSN: Shape Signature Networks for Multi-class Object Detection from  Point Clouds

Normalization methods improve both optimization and generalization of
ConvNets. To further boost performance, the recently-proposed switchable
normalization (SN) provides a new perspective for deep learning: it learns to
select different normalizers for different convolution layers of a ConvNet.
However, SN uses softmax function to learn importance ratios to combine
normalizers, leading to redundant computations compared to a single normalizer.
This work addresses this issue by presenting Sparse Switchable Normalization
(SSN) where the importance ratios are constrained to be sparse. Unlike $\ell_1$
and $\ell_0$ constraints that impose difficulties in optimization, we turn this
constrained optimization problem into feed-forward computation by proposing
SparsestMax, which is a sparse version of softmax. SSN has several appealing
properties. (1) It inherits all benefits from SN such as applicability in
various tasks and robustness to a wide range of batch sizes. (2) It is
guaranteed to select only one normalizer for each normalization layer, avoiding
redundant computations. (3) SSN can be transferred to various tasks in an
end-to-end manner. Extensive experiments show that SSN outperforms its
counterparts on various challenging benchmarks such as ImageNet, Cityscapes,
ADE20K, and Kinetics.

本研究提出了一种稀疏切换归一化（SSN）方法，通过 SparsestMax 算法将学习的重要性约束为稀疏条件，保证每个规范化层只选择一个归一化器，从而提高了深度学习的性能，并在 ImageNet，Cityscapes，ADE20K 和 Kinetics 等数据集上得到了验证 。

通过 SparsestMax 学习稀疏可切换归一化的 SSN

SSN: Learning Sparse Switchable Normalization via SparsestMax

Detecting actions in untrimmed videos is an important yet challenging task.
In this paper, we present the structured segment network (SSN), a novel
framework which models the temporal structure of each action instance via a
structured temporal pyramid. On top of the pyramid, we further introduce a
decomposed discriminative model comprising two classifiers, respectively for
classifying actions and determining completeness. This allows the framework to
effectively distinguish positive proposals from background or incomplete ones,
thus leading to both accurate recognition and localization. These components
are integrated into a unified network that can be efficiently trained in an
end-to-end fashion. Additionally, a simple yet effective temporal action
proposal scheme, dubbed temporal actionness grouping (TAG) is devised to
generate high quality action proposals. On two challenging benchmarks, THUMOS14
and ActivityNet, our method remarkably outperforms previous state-of-the-art
methods, demonstrating superior accuracy and strong adaptivity in handling
actions with various temporal structures.

本文提出了一种基于结构化分割网络 (SSN) 的新型框架，该框架可以通过一个结构化的时间金字塔模型来建模每个动作实例的时间结构，并通过划分的判别模型有效地区分正面提议和背景或不完整的提议，在 THUMOS14 和 ActivityNet 数据集上表现优于现有方法。