This paper introduces a unified framework for video action segmentation via
sequence to sequence (seq2seq) translation in a fully and timestamp supervised
setup. In contrast to current state-of-the-art frame-level prediction methods,
we view action segmentation as a seq2seq translation task, i.e., mapping a
sequence of video frames to a sequence of action segments. Our proposed method
involves a series of modifications and auxiliary loss functions on the standard
Transformer seq2seq translation model to cope with long input sequences opposed
to short output sequences and relatively few videos. We incorporate an
auxiliary supervision signal for the encoder via a frame-wise loss and propose
a separate alignment decoder for an implicit duration prediction. Finally, we
extend our framework to the timestamp supervised setting via our proposed
constrained k-medoids algorithm to generate pseudo-segmentations. Our proposed
framework performs consistently on both fully and timestamp supervised
settings, outperforming or competing state-of-the-art on several datasets. Our
code is publicly available at this https URL

本文提出了一个基于序列到序列解决视频动作分割的统一框架，利用全面时间戳监督设置的 seq2seq 翻译。我们使用 类似于映射视频帧序列到动作分段序列的方法，来解决动作分割这一问题。我们提出了一系列修改和辅助损失函数，以及针对标准 Transformer seq2seq 翻译模型的模块化方法，以应对长输入序列和相对较少的视频输出序列。我们为编码器引入了辅助监督信号，提出了一个独立的对齐解码器用于隐式持续时间预测，最后通过我们提出的有限 k-medoid 算法将框架扩展到基于时间戳的监督设置，用于生成伪分割。我们的框架在完全和时间戳监督设置中表现一致，胜过或与几个数据集上的最先进算法相竞争。

基于序列到序列翻译的融合全程和时间戳监督的暂态行动分割

Unified Fully and Timestamp Supervised Temporal Action Segmentation via  Sequence to Sequence Translation

Truth can vary over time. Fact-checking decisions on claim veracity should
therefore take into account temporal information of both the claim and
supporting or refuting evidence. In this work, we investigate the hypothesis
that the timestamp of a Web page is crucial to how it should be ranked for a
given claim. We delineate four temporal ranking methods that constrain evidence
ranking differently and simulate hypothesis-specific evidence rankings given
the evidence timestamps as gold standard. Evidence ranking in three
fact-checking models is ultimately optimized using a learning-to-rank loss
function. Our study reveals that time-aware evidence ranking not only surpasses
relevance assumptions based purely on semantic similarity or position in a
search results list, but also improves veracity predictions of time-sensitive
claims in particular.

本研究探讨了时间信息对于事实检验和证据排序的影响，提出了四种不同的证据排序方式，并利用学习排序方法探究了基于时间信息的排名模型在检验真实性时的表现优越性。结果显示，在时间敏感的声明检验中，基于时间信息的排序方法不仅超越了纯语义相似性或搜索结果列表中位置的相关假设，而且提高了真实性预测的效果。

基于时间的事实核查证据排序

Time-Aware Evidence Ranking for Fact-Checking

This technical report details a family of time warp distances on the set of
discrete time series. This family is constructed as an editing distance whose
elementary operations apply on linear segments. A specific parameter allows
controlling the stiffness of the elastic matching. It is well suited for the
processing of event data for which each data sample is associated with a
timestamp, not necessarily obtained according to a constant sampling rate. Some
properties verified by these distances are proposed and proved in this report.

本技术报告详细介绍了一组时间扭曲距离，适用于离散时间序列上的编辑距离，其中基本操作应用于线性段，可控制弹性匹配的刚度；同时可用于处理事件数据，其中每个数据样本关联时间戳，不一定按照恒定采样速率获得。文中还提出并证明了这些距离具有的一些特性。