Weakly-supervised temporal action localization (WTAL) is a practical yet
challenging task. Due to large-scale datasets, most existing methods use a
network pretrained in other datasets to extract features, which are not
suitable enough for WTAL. To address this problem, researchers design several
modules for feature enhancement, which improve the performance of the
localization module, especially modeling the temporal relationship between
snippets. However, all of them neglect the adverse effects of ambiguous
information, which would reduce the discriminability of others. Considering
this phenomenon, we propose Discriminability-Driven Graph Network (DDG-Net),
which explicitly models ambiguous snippets and discriminative snippets with
well-designed connections, preventing the transmission of ambiguous information
and enhancing the discriminability of snippet-level representations.
Additionally, we propose feature consistency loss to prevent the assimilation
of features and drive the graph convolution network to generate more
discriminative representations. Extensive experiments on THUMOS14 and
ActivityNet1.2 benchmarks demonstrate the effectiveness of DDG-Net,
establishing new state-of-the-art results on both datasets. Source code is
available at https://github.com/XiaojunTang22/ICCV2023-DDGNet.

提出了一种名为 DDG-Net 的方法，通过建模歧义片段和有区分性片段之间的良好连接来防止歧义信息的传播并提升片段级表示的区分能力，同时通过特征一致性损失驱动图卷积网络生成更有区分性的表示。该方法在 THUMOS14 和 ActivityNet1.2 数据集上取得了新的最先进结果。

DDG-Net：基于可区分性的弱监督时序动作定位图网络

DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised  Temporal Action Localization

Finding multiple temporal relationships among locations can benefit a bunch
of urban applications, such as dynamic offline advertising and smart public
transport planning. While some efforts have been made on finding static
relationships among locations, little attention is focused on studying
time-aware location relationships. Indeed, abundant location-based human
activities are time-varying and the availability of these data enables a new
paradigm for understanding the dynamic relationships in a period among
connective locations. To this end, we propose to study a new problem, namely
multi-Temporal relationship inference among locations (Trial for short), where
the major challenge is how to integrate dynamic and geographical influence
under the relationship sparsity constraint. Specifically, we propose a solution
to Trial with a graph learning scheme, which includes a spatially evolving
graph neural network (SEENet) with two collaborative components: spatially
evolving graph convolution module (SEConv) and spatially evolving
self-supervised learning strategy (SE-SSL). SEConv performs the intra-time
aggregation and inter-time propagation to capture the multifaceted spatially
evolving contexts from the view of location message passing. In addition,
SE-SSL designs time-aware self-supervised learning tasks in a global-local
manner with additional evolving constraint to enhance the location
representation learning and further handle the relationship sparsity. Finally,
experiments on four real-world datasets demonstrate the superiority of our
method over several state-of-the-art approaches.

本文提出了一种新的问题 —— 多时期地理位置之间的时间关系推理研究（Trial），提出了一个图学习方法（SEENet），其中包括空间演化图卷积模块（SEConv）和空间演化自监督学习策略（SE-SSL），并在四个真实数据集上进行试验，证明了我们的方法优于几种最先进的方法。

城市区域多时间关系推理

Multi-Temporal Relationship Inference in Urban Areas

This paper proposes a segregated temporal assembly recurrent (STAR) network
for weakly-supervised multiple action detection. The model learns from
untrimmed videos with only supervision of video-level labels and makes
prediction of intervals of multiple actions. Specifically, we first assemble
video clips according to class labels by an attention mechanism that learns
class-variable attention weights and thus helps the noise relieving from
background or other actions. Secondly, we build temporal relationship between
actions by feeding the assembled features into an enhanced recurrent neural
network. Finally, we transform the output of recurrent neural network into the
corresponding action distribution. In order to generate more precise temporal
proposals, we design a score term called segregated temporal gradient-weighted
class activation mapping (ST-GradCAM) fused with attention weights. Experiments
on THUMOS'14 and ActivityNet1.3 datasets show that our approach outperforms the
state-of-the-art weakly-supervised method, and performs at par with the
fully-supervised counterparts.

本文提出了一种 STAR 网络，用于弱监督多个动作的检测，借助于注意力机制聚合视频片段并使用改进的循环神经网络建立动作之间的时间关系。同时，使用 ST-GradCAM 来生成更精确的时间提案，实验表明本方法在 THUMOS'14 和 ActivityNet1.3 数据集上性能优于现有的弱监督方法，并与全监督方法性能相当。