视频文本预训练(VTP)旨在从大规模的网络视频中学习可转移的代表。迄今为止,几乎所有现有的VTP方法都仅限于基于检索的下游任务,例如视频检索,而它们在基于本地化的任务(例如时间基础)上的转移潜力不足。在本文中,我们实验分析并证明了当前VTP方法与本地化任务的不相容性,并提出了一种新颖的面向定位的视频文本预训练框架,称为LocvTP。具体而言,我们执行细粒对比度对准作为通过剪贴字对数发现方案对粗粒粒度的补充。为了进一步增强学习功能的时间推理能力,我们提出了一个上下文投影头和暂时意识的对比损失,以感知上下文关系。对六个数据集的四个下游任务进行的广泛实验表明,我们的LOCVTP在基于检索和基于本地化的任务上都达到了最先进的性能。此外,我们进行了全面的消融研究和彻底的分析,以探索最佳的模型设计和培训策略。
translated by 谷歌翻译
我们研究了视频引用表达理解(REC)的问题,该问题旨在将句子中描述的引用对象定位为视频帧中的视觉区域。尽管取得了最近的进展,但现有方法却遇到了两个问题:1)视频帧之间的本地化结果不一致; 2)参考对象和上下文对象之间的混淆。为此,我们提出了一个新颖的双对应网络(称为DCNET),该网络明确增强了框架间和跨模式的密集关联。首先,我们旨在为框架内所有现有实例建立框架间的相关性。具体而言,我们计算框架间的斑点余弦相似性,以估计密集的对齐方式,然后执行框架间的对比度学习以在特征空间中映射它们。其次,我们建议构建细粒斑点字对齐,以将每个贴片与某些单词相关联。由于缺乏这种详细的注释,我们还通过余弦相似性预测了斑点字的对应关系。广泛的实验表明,我们的DCNET在视频和图像基准测试中都达到了最先进的性能。此外,我们进行了全面的消融研究和彻底的分析,以探索最佳模型设计。值得注意的是,我们的框架间和跨模式对比损失是插件功能,适用于任何视频架构架构。例如,通过在共同接地之上进行构建,我们在vid-sentence数据集的Accu。0.5上提高了1.48%的性能。
translated by 谷歌翻译
Video-language pre-training has advanced the performance of various downstream video-language tasks. However, most previous methods directly inherit or adapt typical image-language pre-training paradigms to video-language pre-training, thus not fully exploiting the unique characteristic of video, i.e., temporal. In this paper, we propose a Hierarchical Temporal-Aware video-language pre-training framework, HiTeA, with two novel pre-training tasks for modeling cross-modal alignment between moments and texts as well as the temporal relations of video-text pairs. Specifically, we propose a cross-modal moment exploration task to explore moments in videos, which results in detailed video moment representation. Besides, the inherent temporal relations are captured by aligning video-text pairs as a whole in different time resolutions with multi-modal temporal relation exploration task. Furthermore, we introduce the shuffling test to evaluate the temporal reliance of datasets and video-language pre-training models. We achieve state-of-the-art results on 15 well-established video-language understanding and generation tasks, especially on temporal-oriented datasets (e.g., SSv2-Template and SSv2-Label) with 8.6% and 11.1% improvement respectively. HiTeA also demonstrates strong generalization ability when directly transferred to downstream tasks in a zero-shot manner. Models and demo will be available on ModelScope.
translated by 谷歌翻译
视频文本检索一直是多模式研究中的至关重要和基本任务。大型多模式对比预训练的发展,视频文本检索的开发已大大促进,这主要侧重于粗粒或细粒对比。然而,在先前的研究中很少探索过跨粒度的对比,这是粗粒表示和细粒度表示之间的对比。与细粒度或粗粒的对比相比,交叉粒度对比度计算了粗粒粒度特征与每个细粒特征之间的相关性,并且能够过滤出不必要的细颗粒特征,这些特征由粗粒度的特征引导相似性计算,从而提高了检索的准确性。为此,本文提出了一种新型的多透明对比模型,即X-CLIP,用于视频文本检索。但是,另一个挑战在于相似性聚集问题,该问题旨在将细粒度和跨粒度相似性矩阵与实例级别的相似性汇总。为了应对这一挑战,我们提出了对相似性矩阵(AOSM)模块的关注,以使模型重点放在基本帧和单词之间的对比度上,从而降低了不必要的帧和单词对检索结果的影响。 X-CLIP具有多透明的对比度和提议的AOSM模块,在五个广泛使用的视频文本检索数据集上取得了出色的性能,包括MSR-VTT(49.3 R@1),MSVD(50.4 R@1),LSMDC(26.11)(26.1 r@1),didemo(47.8 r@1)和ActivityNet(46.2 r@1)。它的表现优于先前的最先前, +6.3%, +6.6%, +11.1%, +6.7%, +3.8%的相对改善对这些基准测试,这表明了多透明的对比度和AOSM的优势。
translated by 谷歌翻译
This paper presents SimVTP: a Simple Video-Text Pretraining framework via masked autoencoders. We randomly mask out the spatial-temporal tubes of input video and the word tokens of input text and then feed them into a unified autencoder to reconstruct the missing pixels and words. Our SimVTP has several properties: 1) Thanks to the unified autoencoder, SimVTP reconstructs the masked signal of one modality with the help from another modality, which implicitly learns the cross-modal alignment between video tubes and text tokens. 2) SimVTP not only benefits from a high video masking ratio (e.g. 90%) due to the temporal redundancy of video, but also needs a high text masking ratio (e.g. 75%), which is much higher than BERT (e.g. 15%), to achieve optimal performance. This is because the aid of video modality makes text reconstruction less challenging, which thus needs a higher mask ratio to make the pretext harder for useful feature learning. 3) Equipping SimVTP with video-text contrastive learning (VTC) and video-text matching (VTM), which are two commonly used cross-modal training strategies, could further improve the transferable performance significantly. 4) SimVTP is dataefficent, e.g., pre-training only on 10% data of WebVid-2M, SimVTP achieves surprisingly good results (43.8 R@1) on MSRVTT, which is far above recent state-of-the-art methods pre-trained on both CC3M and WebVid-2M. We transfer our pre-trained model to various downstream tasks and achieve superior performance. The codes and models will be released at https://github.com/mayuelala/SimVTP.
translated by 谷歌翻译
Text-Video Retrieval plays an important role in multi-modal understanding and has attracted increasing attention in recent years. Most existing methods focus on constructing contrastive pairs between whole videos and complete caption sentences, while overlooking fine-grained cross-modal relationships, e.g., clip-phrase or frame-word. In this paper, we propose a novel method, named Hierarchical Cross-Modal Interaction (HCMI), to explore multi-level cross-modal relationships among video-sentence, clip-phrase, and frame-word for text-video retrieval. Considering intrinsic semantic frame relations, HCMI performs self-attention to explore frame-level correlations and adaptively cluster correlated frames into clip-level and video-level representations. In this way, HCMI constructs multi-level video representations for frame-clip-video granularities to capture fine-grained video content, and multi-level text representations at word-phrase-sentence granularities for the text modality. With multi-level representations for video and text, hierarchical contrastive learning is designed to explore fine-grained cross-modal relationships, i.e., frame-word, clip-phrase, and video-sentence, which enables HCMI to achieve a comprehensive semantic comparison between video and text modalities. Further boosted by adaptive label denoising and marginal sample enhancement, HCMI achieves new state-of-the-art results on various benchmarks, e.g., Rank@1 of 55.0%, 58.2%, 29.7%, 52.1%, and 57.3% on MSR-VTT, MSVD, LSMDC, DiDemo, and ActivityNet, respectively.
translated by 谷歌翻译
Most existing text-video retrieval methods focus on cross-modal matching between the visual content of offline videos and textual query sentences. However, in real scenarios, online videos are frequently accompanied by relevant text information such as titles, tags, and even subtitles, which can be utilized to match textual queries. This inspires us to generate associated captions from offline videos to help with existing text-video retrieval methods. To do so, we propose to use the zero-shot video captioner with knowledge of pre-trained web-scale models (e.g., CLIP and GPT-2) to generate captions for offline videos without any training. Given the captions, one question naturally arises: what can auxiliary captions do for text-video retrieval? In this paper, we present a novel framework Cap4Video, which makes use of captions from three aspects: i) Input data: The video and captions can form new video-caption pairs as data augmentation for training. ii) Feature interaction: We perform feature interaction between video and caption to yield enhanced video representations. iii) Output score: The Query-Caption matching branch can be complementary to the original Query-Video matching branch for text-video retrieval. We conduct thorough ablation studies to demonstrate the effectiveness of our method. Without any post-processing, our Cap4Video achieves state-of-the-art performance on MSR-VTT (51.4%), VATEX (66.6%), MSVD (51.8%), and DiDeMo (52.0%).
translated by 谷歌翻译
预先训练的图像文本模型(如剪辑)已经证明了从大规模的Web收集的图像文本数据中学到的视觉表示的强大力量。鉴于学习良好的视觉特征,一些现有的作品将图像表示转移到视频域并取得良好的结果。但是,如何利用图像语言预训练的模型(例如,剪辑)进行视频培训(后培训)仍在探索。在本文中,我们研究了两个问题:1)阻碍后期剪辑的因素是什么因素,以进一步提高视频语言任务的性能? 2)如何减轻这些因素的影响?通过一系列比较实验和分析,我们发现语言源之间的数据量表和域间隙具有很大的影响。由这些动机,我们提出了一种配备了视频代理机制的Omnisource跨模式学习方法,即剪辑,即剪辑VIP。广泛的结果表明,我们的方法可以提高视频检索的剪辑的性能。我们的模型还可以在包括MSR-VTT,DIDEMO,LSMDC和ActivityNet在内的各种数据集上实现SOTA结果。我们在https://github.com/microsoft/xpretrain/tree/main/main/main/clip-vip上发布了代码和预训练的剪辑模型。
translated by 谷歌翻译
Learning fine-grained interplay between vision and language allows to a more accurate understanding for VisionLanguage tasks. However, it remains challenging to extract key image regions according to the texts for semantic alignments. Most existing works are either limited by textagnostic and redundant regions obtained with the frozen detectors, or failing to scale further due to its heavy reliance on scarce grounding (gold) data to pre-train detectors. To solve these problems, we propose Self-Locator Aided Network (SLAN) for cross-modal understanding tasks without any extra gold data. SLAN consists of a region filter and a region adaptor to localize regions of interest conditioned on different texts. By aggregating cross-modal information, the region filter selects key regions and the region adaptor updates their coordinates with text guidance. With detailed region-word alignments, SLAN can be easily generalized to many downstream tasks. It achieves fairly competitive results on five cross-modal understanding tasks (e.g., 85.7% and 69.2% on COCO image-to-text and text-to-image retrieval, surpassing previous SOTA methods). SLAN also demonstrates strong zero-shot and fine-tuned transferability to two localization tasks.
translated by 谷歌翻译
现代视频文本检索框架基本上由三个部分组成:视频编码器,文本编码器和相似性。随着Visual和Textual表示学习的成功,在视频文本检索领域也采用了基于变压器的编码器和融合方法。在本报告中,我们呈现Clip2TV,旨在探索关键元素在基于变压器的方法中。为实现这一目标,我们首先重新审视一些对多模态学习的工作,然后将一些技术介绍到视频文本检索中,最后通过不同配置的大量实验进行评估。值得注意的是,Clip2TV在MSR-VTT数据集上实现了52.9 @ R1,优先表现出先前的SOTA结果为4.1%。
translated by 谷歌翻译
培训有效的视频和语言模型直观地需要多个帧作为模型输入。但是,目前尚不清楚使用多个帧是否有利于下游任务,如果是的话,性能增益是否值得通过使用更多帧产生的巨大计算和内存成本。在这项工作中,我们探索了视频和语言学习的单帧模型。在各种视频和语言任务(包括文本到视频检索和视频问题)上,我们显示出令人惊讶的结果,即通过大规模的预训练和适当的框架合奏在推理时,与使用多个训练的现有方法相比,不考虑时间信息的单帧训练模型可以实现更好的性能。该结果揭示了流行的视频和语言数据集中存在强烈的“静态外观偏差”。因此,为了对视频和语言模型进行更全面的评估,我们建议基于现有的细粒度识别数据集,提出了两个新的检索任务,以鼓励时间建模。我们的代码可从https://github.com/jayleicn/singularity获得
translated by 谷歌翻译
We introduce LaViLa, a new approach to learning video-language representations by leveraging Large Language Models (LLMs). We repurpose pre-trained LLMs to be conditioned on visual input, and finetune them to create automatic video narrators. Our auto-generated narrations offer a number of advantages, including dense coverage of long videos, better temporal synchronization of the visual information and text, and much higher diversity of text. The video-text embedding learned contrastively with these additional auto-generated narrations outperforms the previous state-of-the-art on multiple first-person and third-person video tasks, both in zero-shot and finetuned setups. Most notably, LaViLa obtains an absolute gain of 10.1% on EGTEA classification and 5.9% Epic-Kitchens-100 multi-instance retrieval benchmarks. Furthermore, LaViLa trained with only half the narrations from the Ego4D dataset outperforms baseline models trained on the full set, and shows positive scaling behavior on increasing pre-training data and model size.
translated by 谷歌翻译
最近,通过引入大规模的数据集和强大的变压器网络,视频预培训表明尤其是检索的巨大成功。然而,现有的视频语言变压器模型没有明确细粒度的语义对齐。在这项工作中,我们呈现了对象感知的变换器,以对象为中心的方法,该对象方法扩展了视频语言变压器来合并对象表示。关键的想法是利用边界框和对象标签来指导培训过程。我们在四个广泛使用的基准测试中评估了我们的三个标准子任务的模型。我们还提供了深入的分析和详细消融关于所提出的方法。我们在考虑的所有任务和数据集中表现出清晰的性能,展示将对象表示的模型中的型号集成到视频架构中。代码将以\ URL {https://github.com/fingerrec/oa -transformer}释放。
translated by 谷歌翻译
BERT型结构导致了视觉语言预培训的革命,并在众多视觉语言下游任务上实现最先进的结果。现有解决方案主要用掩码令牌的多模态输入大小化,以触发基于掩码的代理预训练任务(例如,屏蔽语言建模和屏蔽对象/帧预测)。在这项工作中,我们认为这种掩码的输入将不可避免地引入跨模型匹配代理任务的噪声,从而留下探索的固有视觉语言协会。作为替代方案,我们推导出一种特定形式的用于视频预培训的跨模型代理目标,即对比跨模型匹配和去噪(Coco)。通过将蒙版帧/单词序列视为主要取消屏蔽的噪声增强,通过同时追求掩蔽和未掩蔽输入之间的模态匹配和模态匹配和模态的帧间匹配和模态的帧内偏离,通过对比方式来加强视频协会。我们的CoCo代理目标可以进一步集成到用于视频预训练的任何BERT型编码器解码器结构中,被命名为对比跨模态伯特(Coco-Bert)。我们在电视数据集上预先火车Coco-Bert以及新收集的大型GIF视频数据集(动作)。通过广泛的下游任务(例如,跨模型检索,视频问题回答和视频标题)进行广泛的实验,我们证明了Coco-Bert作为预训练的结构的优越性。
translated by 谷歌翻译
构建一个通用视频语言模型,用于解决各种视频理解任务(例如,文本视频检索,视频问答)是对机器学习领域的开放挑战。为了实现这一目标,最近的尝试训练模型,通常由单峰和跨模式的特征编码器组成,并具有受监督或成对的对比度的预文本任务。尽管提供了有吸引力的通用性,但最终的模型必须在效率和性能之间妥协。我们认为这些缺陷是由它们的预训练策略\ Textemdash引起的,它们不能很好地对齐和融合不同方式的特征。然后,我们将三叶草(一种相关的视频预培训方法)介绍给一个通用的视频语言模型,该模型用于解决既不效率也不妥协的多个视频理解任务。它通过新的三模式比对预训练任务来改善跨模式特征对齐和融合。此外,我们建议通过合并蒙面样品的学习和新颖的成对排名损失来增强三模式对齐。三叶草表现出了出色的一般性。它在多个下游任务上建立了新的最新技术,包括零射击和微调设置的三个检索任务,以及八个视频问答任务。代码和预培训模型将在https://github.com/leeyn-43/clover上发布。
translated by 谷歌翻译
视觉检索中的大多数现有方法是通过比较其全局特征向量的两种方式,该矢量错过了足够的信息并缺乏可解释性,检测图像或视频中的对象,并将文本与依赖复杂的模型设计或建模的精细元素对齐通过较低效率遭受视觉和文本令牌的交叉注意相互作用。为了解决这些局限性,最近的一些作品简单地汇总了代币的相似性以实现细粒度的对齐方式,但它们缺乏直观的解释,并且忽略了令牌级特征和具有高级语义的全球表示之间的关系。在这项工作中,我们重新考虑细粒度的跨模式对准,并为其设计一种新的模型不合命固式配方。我们还揭开了最近的流行作品的神秘面纱,并将其纳入我们的计划。此外,受最佳运输理论的启发,我们引入了\ emph {tokenflow},这是对拟议方案的实例化。通过仅修改相似性函数,我们方法的性能与主要视频文本检索基准上具有重型模型设计的SOTA算法相当。可视化进一步表明\ emph {tokenflow}成功利用细粒度的信息并获得了更好的解释性。
translated by 谷歌翻译
我们研究了联合视频和语言(VL)预培训,以实现跨模型学习和益处丰富的下游VL任务。现有的作品要么提取低质量的视频特征或学习有限的文本嵌入,但忽略了高分辨率视频和多样化的语义可以显着提高跨模型学习。在本文中,我们提出了一种新的高分辨率和多样化的视频 - 语言预训练模型(HD-VILA),用于许多可视任务。特别是,我们收集具有两个不同属性的大型数据集:1)第一个高分辨率数据集包括371.5k小时的720p视频,2)最多样化的数据集涵盖15个流行的YouTube类别。为了启用VL预培训,我们通过学习丰富的时空特征的混合变压器联合优化HD-VILA模型,以及多峰变压器,用于强制学习视频功能与多样化文本的交互。我们的预训练模式实现了新的最先进的导致10 VL了解任务和2个新颖的文本到视觉生成任务。例如,我们以零拍摄MSR-VTT文本到视频检索任务的相对增加38.5%R @ 1的相对增长,高分辨率数据集LSMDC为53.6%。学习的VL嵌入也有效地在文本到视觉操纵和超分辨率任务中产生视觉上令人愉悦和语义相关结果。
translated by 谷歌翻译
Previous work on action representation learning focused on global representations for short video clips. In contrast, many practical applications, such as video alignment, strongly demand learning the intensive representation of long videos. In this paper, we introduce a new framework of contrastive action representation learning (CARL) to learn frame-wise action representation in a self-supervised or weakly-supervised manner, especially for long videos. Specifically, we introduce a simple but effective video encoder that considers both spatial and temporal context by combining convolution and transformer. Inspired by the recent massive progress in self-supervised learning, we propose a new sequence contrast loss (SCL) applied to two related views obtained by expanding a series of spatio-temporal data in two versions. One is the self-supervised version that optimizes embedding space by minimizing KL-divergence between sequence similarity of two augmented views and prior Gaussian distribution of timestamp distance. The other is the weakly-supervised version that builds more sample pairs among videos using video-level labels by dynamic time wrapping (DTW). Experiments on FineGym, PennAction, and Pouring datasets show that our method outperforms previous state-of-the-art by a large margin for downstream fine-grained action classification and even faster inference. Surprisingly, although without training on paired videos like in previous works, our self-supervised version also shows outstanding performance in video alignment and fine-grained frame retrieval tasks.
translated by 谷歌翻译
本文研究了时间句子接地的多媒体问题(TSG),该问题旨在根据给定的句子查询准确地确定未修剪视频中的特定视频段。传统的TSG方法主要遵循自上而下或自下而上的框架,不是端到端。他们严重依靠耗时的后处理来完善接地结果。最近,提出了一些基于变压器的方法来有效地对视频和查询之间的细粒语义对齐进行建模。尽管这些方法在一定程度上达到了显着的性能,但它们同样将视频的框架和查询的单词视为用于关联的变压器输入,未能捕获其不同水平的粒度与独特的语义。为了解决这个问题,在本文中,我们提出了一种新型的等级局部 - 全球变压器(HLGT)来利用这种层次结构信息,并模拟不同粒度的不同级别的相互作用和不同的模态之间的相互作用,以学习更多细粒度的多模式表示。具体而言,我们首先将视频和查询分为单个剪辑和短语,以通过时间变压器学习其本地上下文(相邻依赖关系)和全局相关性(远程依赖)。然后,引入了全球本地变压器,以了解本地级别和全球级别语义之间的相互作用,以提供更好的多模式推理。此外,我们开发了一种新的跨模式周期一致性损失,以在两种模式之间实施相互作用,并鼓励它们之间的语义一致性。最后,我们设计了一个全新的跨模式平行变压器解码器,以集成编码的视觉和文本特征,以进行最终接地。在三个具有挑战性的数据集上进行了广泛的实验表明,我们提出的HLGT实现了新的最新性能。
translated by 谷歌翻译
最近,跨模式的预训练任务一直是一个热点,因为它在各种下文研究中广泛应用,包括检索,字幕,问题答案等。然而,退出的方法采用单媒体预训练模型来探索进行跨模式检索的联合视觉表示,这很容易遭受计算爆炸的影响。此外,尽管常规的双流结构非常有效,但它们仍然缺乏重要的跨模式相互作用,导致性能低。在这些挑战的激励下,我们提出了一个对比的跨模式知识共享预训练(Cookie),以掌握联合文本图像表示。从结构上讲,Cookie由于可接受的时间消耗而采用了传统的双流结构。为了克服上述双流结构的固有缺陷,我们精心设计了两个有效的模块。具体而言,第一个模块是一个体重共享的变压器,它构建在视觉和文本编码器的头上,旨在将语义对齐文本和图像对齐。该设计使视觉和文本路径集中在相同的语义上。另一个是三个专门设计的对比学习,旨在分享不同模型之间的知识。共享的跨模式知识大大发展了单峰表示的研究,从而促进了单模式检索任务。对多模式匹配研究的广泛实验结果,包括跨模式检索,文本匹配和图像检索揭示了我们的计算效率和我们预训练模型的统计指标的上级。
translated by 谷歌翻译