We present a simple yet effective end-to-end Video-language Pre-training (VidLP) framework, Masked Contrastive Video-language Pretraining (MAC), for video-text retrieval tasks. Our MAC aims to reduce video representation's spatial and temporal redundancy in the VidLP model by a mask sampling mechanism to improve pre-training efficiency. Comparing conventional temporal sparse sampling, we propose to randomly mask a high ratio of spatial regions and only feed visible regions into the encoder as sparse spatial sampling. Similarly, we adopt the mask sampling technique for text inputs for consistency. Instead of blindly applying the mask-then-prediction paradigm from MAE, we propose a masked-then-alignment paradigm for efficient video-text alignment. The motivation is that video-text retrieval tasks rely on high-level alignment rather than low-level reconstruction, and multimodal alignment with masked modeling encourages the model to learn a robust and general multimodal representation from incomplete and unstable inputs. Coupling these designs enables efficient end-to-end pre-training: reduce FLOPs (60% off), accelerate pre-training (by 3x), and improve performance. Our MAC achieves state-of-the-art results on various video-text retrieval datasets, including MSR-VTT, DiDeMo, and ActivityNet. Our approach is omnivorous to input modalities. With minimal modifications, we achieve competitive results on image-text retrieval tasks.
translated by 谷歌翻译
Social media has been one of the main information consumption sources for the public, allowing people to seek and spread information more quickly and easily. However, the rise of various social media platforms also enables the proliferation of online misinformation. In particular, misinformation in the health domain has significant impacts on our society such as the COVID-19 infodemic. Therefore, health misinformation in social media has become an emerging research direction that attracts increasing attention from researchers of different disciplines. Compared to misinformation in other domains, the key differences of health misinformation include the potential of causing actual harm to humans' bodies and even lives, the hardness to identify for normal people, and the deep connection with medical science. In addition, health misinformation on social media has distinct characteristics from conventional channels such as television on multiple dimensions including the generation, dissemination, and consumption paradigms. Because of the uniqueness and importance of combating health misinformation in social media, we conduct this survey to further facilitate interdisciplinary research on this problem. In this survey, we present a comprehensive review of existing research about online health misinformation in different disciplines. Furthermore, we also systematically organize the related literature from three perspectives: characterization, detection, and intervention. Lastly, we conduct a deep discussion on the pressing open issues of combating health misinformation in social media and provide future directions for multidisciplinary researchers.
translated by 谷歌翻译
预训练的视觉模型(例如,剪辑)在许多下游任务中显示出有希望的零弹性概括,并具有正确设计的文本提示。最近的作品不依赖手工设计的提示,而是使用下游任务的培训数据来学习提示。虽然有效,但针对领域数据的培训却降低了模型的概括能力,使其无法看到新领域。在这项工作中,我们提出了测试时间提示调整(TPT),该方法可以通过单个测试样本即时学习自适应提示。对于图像分类,TPT通过使用置信度选择最小化熵来优化提示,以便模型在每个测试样本的不同增强视图上都具有一致的预测。在评估对自然分布变化的概括时,TPT平均将零击的TOP-1精度提高了3.6%,超过了先前需要其他特定于任务的训练数据的迅速调整方法。在评估看不见类别的跨数据集泛化时,TPT与使用其他培训数据的最先进方法相当。项目页面:https://azshue.github.io/tpt。
translated by 谷歌翻译
电子商务搜索的关键是如何最好地利用大型但嘈杂的日志数据。在本文中,我们在Instacart介绍了基于嵌入的杂货搜索模型。该系统通过基于两个塔式变压器的编码器体系结构学习查询和产品表示。为了解决冷门问题,我们专注于基于内容的功能。为了在嘈杂的数据上有效地培训模型,我们提出了一种自我分歧学习方法和级联培训方法。Accon是一个离线人类评估数据集,我们在召回@20方面取得了10%的相对改善,对于在线A/B测试,我们每次搜索(CAPS)获得4.1%的Cart-Addds(CAPS)和1.5%的总商品价值(GMV)改进。我们描述了如何训练和部署基于嵌入的搜索模型,并对我们方法的有效性进行详细分析。
translated by 谷歌翻译
基于文本的人检索旨在根据文本描述找到查询人员。关键是学习视觉文本模式之间的常见潜在空间映射。为了实现这一目标,现有的作品采用细分来获得明确的跨模式对齐方式或利用注意力来探索显着对准。这些方法有两个缺点:1)标记交叉模式比对很耗时。 2)注意方法可以探索显着的跨模式对齐,但可能会忽略一些微妙而有价值的对。为了缓解这些问题,我们为基于文本的人检索引入了一个隐式视觉文本(IVT)框架。与以前的模型不同,IVT利用单个网络来学习两种模式的表示形式,这有助于视觉文本相互作用。为了探索细粒的对准,我们进一步提出了两个隐式语义比对范式:多级比对(MLA)和双向掩码建模(BMM)。 MLA模块在句子,短语和单词级别上探索了更精细的匹配,而BMM模块旨在挖掘视觉和文本模态之间的\ textbf {更多}语义对齐。进行了广泛的实验,以评估公共数据集中提出的IVT,即Cuhk-Pedes,RSTPREID和ICFG-PEDES。即使没有明确的身体部位对准,我们的方法仍然可以达到最先进的表现。代码可在以下网址获得:https://github.com/tencentyouturesearch/personretrieval-ivt。
translated by 谷歌翻译
近年来,图像生成在提高图像质量方面取得了长足的进步,从而产生了高保真性。另外,最近还有一些建筑设计,它使甘恩能够毫不客气地学习不同层中表示的语义属性。但是,对于与人类美学更一致的面部图像仍然缺乏研究。基于Eigengan [He等,ICCV 2021],我们将增强学习的技术构建到Eigengan的发电机中。该代理商试图弄清楚如何将生成的人脸的语义属性更改为更可取的面部。为此,我们训练了一种可以进行面部美容预测的美学评分模型。我们还可以利用此评分模型来分析面部属性和美学得分之间的相关性。从经验上讲,使用增强学习的现成技术无法正常工作。因此,相反,我们提出了一种新的变体,该变体纳入了近年来在强化学习社区中出现的成分。与原始生成的图像相比,调整后的图像显示了有关各种属性的明确区别。实验结果使用思维镜,显示了所提出的方法的有效性。更改的面部图像通常更具吸引力,并有明显改善的美学水平。
translated by 谷歌翻译
将多模式的知识用于抽象性摘要任务是一个正在进行的研究领域,目前的技术遗传了融合,然后代范式。由于计算机视觉和自然语言处理之间的语义差距,当前方法通常将多个数据点视为单独的对象,并依靠注意机制搜索连接以融合在一起。此外,从许多框架中缺少对跨模式匹配的认识会导致性能降低。为了解决这两个缺点,我们提出了一个迭代对比对准框架(ICAF),该框架使用反复对齐和对比度来捕获图像和文本之间的连贯性。具体而言,我们设计了一个经常性比对(RA)层,以逐步研究图像贴片和文本令牌之间的细粒语义关系。在编码过程中的每个步骤中,跨模式对比度损耗被应用以直接优化嵌入式空间。根据Rouge的说法,相关得分和人类评估,我们的模型表现优于MSMO数据集上最新的基线。还进行了有关我们提出的框架和超参数设置的适用性的实验。
translated by 谷歌翻译
对于真实世界形象超分辨率的深度学习方法,最关键的问题是对训练的配对低和高分辨率图像是否准确反映了真实相机的采样过程。由现有的退化模型(例如,双臂下采样)合成的低分辨率(LR $ \ SIM $ HR)图像对偏离现实中的模型;因此,当应用于真实图像时,由这些合成的LR $ \ SIM $ HR图像对训练的超分辨率CNN不会表现良好。为了解决问题,我们提出了一种新的数据采集过程,使用真实相机拍摄一大集的LR $ \ SIM $ HR图像对。图像显示在超高质量屏幕上并以不同的分辨率捕获。由此产生的LR $ \ SIM $ HR图像对可以通过新颖的空间频率二元域注册方法与非常高的子像素精度对齐,因此它们为超级分辨率的学习任务提供了高质量的培训数据。此外,捕获的HR图像和原始数字图像提供了双引用来提高学习性能。实验结果表明,我们的LR $ \ SIM $ HR DataSet培训超分辨率CNN,而不是文献中的其他数据集培训更高的图像质量。
translated by 谷歌翻译
具有大量空间和时间跨境的情景中的人重新识别(RE-ID)尚未完全探索。这部分原因是,现有的基准数据集主要由有限的空间和时间范围收集,例如,使用在校园特定区域的相机录制的视频中使用的视频。这种有限的空间和时间范围使得难以模拟真实情景中的人的困难。在这项工作中,我们贡献了一个新的大型时空上次最后一个数据集,包括10,862个图像,具有超过228k的图像。与现有数据集相比,最后一个具有挑战性和高度多样性的重新ID设置,以及显着更大的空间和时间范围。例如,每个人都可以出现在不同的城市或国家,以及在白天到夜间的各个时隙,以及春季到冬季的不同季节。为了我们的最佳知识,最后是一个新的Perse Re-ID数据集,具有最大的时空范围。基于最后,我们通过对14个RE-ID算法进行全面的绩效评估来验证其挑战。我们进一步提出了一种易于实施的基线,适用于如此挑战的重新ID设置。我们还验证了初步训练的模型可以在具有短期和更改方案的现有数据集中概括。我们期待持续激发未来的工程,以更现实和挑战的重新识别任务。有关DataSet的更多信息,请访问https://github.com/shuxjweb/last.git。
translated by 谷歌翻译
Weakly-supervised object localization aims to indicate the category as well as the scope of an object in an image given only the image-level labels. Most of the existing works are based on Class Activation Mapping (CAM) and endeavor to enlarge the discriminative area inside the activation map to perceive the whole object, yet ignore the co-occurrence confounder of the object and context (e.g., fish and water), which makes the model inspection hard to distinguish object boundaries. Besides, the use of CAM also brings a dilemma problem that the classification and localization always suffer from a performance gap and can not reach their highest accuracy simultaneously. In this paper, we propose a casual knowledge distillation method, dubbed KD-CI-CAM, to address these two under-explored issues in one go. More specifically, we tackle the co-occurrence context confounder problem via causal intervention (CI), which explores the causalities among image features, contexts, and categories to eliminate the biased object-context entanglement in the class activation maps. Based on the de-biased object feature, we additionally propose a multi-teacher causal distillation framework to balance the absorption of classification knowledge and localization knowledge during model training. Extensive experiments on several benchmarks demonstrate the effectiveness of KD-CI-CAM in learning clear object boundaries from confounding contexts and addressing the dilemma problem between classification and localization performance.
translated by 谷歌翻译