Visual understanding goes well beyond object recognition. With one glance at an image, we can effortlessly imagine the world beyond the pixels: for instance, we can infer people's actions, goals, and mental states. While this task is easy for humans, it is tremendously difficult for today's vision systems, requiring higher-order cognition and commonsense reasoning about the world. We formalize this task as Visual Commonsense Reasoning. Given a challenging question about an image, a machine must answer correctly and then provide a rationale justifying its answer.Next, we introduce a new dataset, VCR, consisting of 290k multiple choice QA problems derived from 110k movie scenes. The key recipe for generating non-trivial and highquality problems at scale is Adversarial Matching, a new approach to transform rich annotations into multiple choice questions with minimal bias. Experimental results show that while humans find VCR easy (over 90% accuracy), state-of-the-art vision models struggle (∼45%).To move towards cognition-level understanding, we present a new reasoning engine, Recognition to Cognition Networks (R2C), that models the necessary layered inferences for grounding, contextualization, and reasoning. R2C helps narrow the gap between humans and machines (∼65%); still, the challenge is far from solved, and we provide analysis that suggests avenues for future work.

为了使AI安全地在医院，学校和工作场所等现实世界中安全部署，它必须能够坚定地理解物理世界。这种推理的基础是物理常识：了解可用对象的物理特性和提供的能力，如何被操纵以及它们如何与其他对象进行交互。物理常识性推理从根本上是一项多感官任务，因为物理特性是通过多种模式表现出来的，其中两个是视觉和声学。我们的论文通过贡献PACS来朝着现实世界中的物理常识推理：第一个用于物理常识属性注释的视听基准。 PACS包含13,400对答案对，涉及1,377个独特的物理常识性问题和1,526个视频。我们的数据集提供了新的机会来通过将音频作为此多模式问题的核心组成部分来推进物理推理的研究领域。使用PACS，我们在我们的新挑战性任务上评估了多种最先进的模型。尽管某些模型显示出令人鼓舞的结果（精度为70％），但它们都没有人类的绩效（精度为95％）。我们通过证明多模式推理的重要性并为未来的研究提供了可能的途径来结束本文。

We propose the task of free-form and open-ended Visual Question Answering (VQA). Given an image and a natural language question about the image, the task is to provide an accurate natural language answer. Mirroring real-world scenarios, such as helping the visually impaired, both the questions and answers are open-ended. Visual questions selectively target different areas of an image, including background details and underlying context. As a result, a system that succeeds at VQA typically needs a more detailed understanding of the image and complex reasoning than a system producing generic image captions. Moreover, VQA is amenable to automatic evaluation, since many open-ended answers contain only a few words or a closed set of answers that can be provided in a multiple-choice format. We provide a dataset containing ∼0.25M images, ∼0.76M questions, and ∼10M answers (www.visualqa.org), and discuss the information it provides. Numerous baselines and methods for VQA are provided and compared with human performance. Our VQA demo is available on CloudCV (http://cloudcv.org/vqa).

人类具有出色的能力来推理绑架并假设超出图像的字面内容的内容。通过识别散布在整个场景中的具体视觉线索，我们几乎不禁根据我们的日常经验和对世界的知识来提出可能的推论。例如，如果我们在道路旁边看到一个“ 20英里 /小时”的标志，我们可能会假设街道位于居民区（而不是在高速公路上），即使没有房屋。机器可以执行类似的视觉推理吗？我们提出了Sherlock，这是一个带注释的103K图像的语料库，用于测试机器能力，以超出字面图像内容的绑架推理。我们采用免费观看范式：参与者首先观察并识别图像中的显着线索（例如，对象，动作），然后给定线索，然后提供有关场景的合理推论。我们总共收集了363K（线索，推理）对，该对形成了首个绑架的视觉推理数据集。使用我们的语料库，我们测试了三个互补的绑架推理轴。我们评估模型的能力：i）从大型候选人语料库中检索相关推论； ii）通过边界框来定位推论的证据，iii）比较合理的推论，以匹配人类在新收集的19k李克特级判断的诊断语料库上的判断。尽管我们发现具有多任务目标的微调夹RN50x64优于强大的基准，但模型性能与人类一致之间存在着重要的净空。可在http://visualabduction.com/上获得数据，模型和排行榜

作为人类，我们通过我们所有的感官来驾驭世界，使用每个人从每个人纠正其他人。我们介绍了Merlot Reserve，一个模型，该模型是联合随着时间的推移而表示视频的模型 - 通过从音频，字幕和视频帧学习的新培训目标。给出了一个视频，我们用掩模令牌替换文本和音频的片段;该模型通过选择正确的蒙版片段来学习。我们的目标比替代方面更快地学习，并在规模上表现良好：我们预先逼近2000万YouTube视频。经验结果表明，Merlot Reserve学会通过所有组成模式的视频的强烈陈述。在FineTuned时，它在VCR和TVQA上为VCR和TVQA进行了新的最先进，优先于前勤工作分别为5％和7％。消融表明，两个任务都受益于音频预制 - 甚至录像机，围绕图像中心的QA任务（没有声音）。此外，我们的客观使开箱即用的预测，揭示了强大的多式联合致辞理解。在一个完全零拍摄的环境中，我们的模型在四个视频理解任务中获得竞争结果，甚至优于最近提出的定位推理（星）基准的监督方法。我们分析为什么包含音频导致更好的视觉语言表示，这表明未来研究的重要机会。我们通过讨论多式联运预测的道德和社会影响来得出结论。

Despite progress in perceptual tasks such as image classification, computers still perform poorly on cognitive tasks such as image description and question answering. Cognition is core to tasks that involve not just recognizing, but reasoning about our visual world. However, models used to tackle the rich content in images for cognitive tasks are still being trained using the same datasets designed for perceptual tasks. To achieve success at cognitive tasks, models need to understand the interactions and relationships between objects in

We have seen great progress in basic perceptual tasks such as object recognition and detection. However, AI models still fail to match humans in high-level vision tasks due to the lack of capacities for deeper reasoning. Recently the new task of visual question answering (QA) has been proposed to evaluate a model's capacity for deep image understanding. Previous works have established a loose, global association between QA sentences and images. However, many questions and answers, in practice, relate to local regions in the images. We establish a semantic link between textual descriptions and image regions by object-level grounding. It enables a new type of QA with visual answers, in addition to textual answers used in previous work. We study the visual QA tasks in a grounded setting with a large collection of 7W multiple-choice QA pairs. Furthermore, we evaluate human performance and several baseline models on the QA tasks. Finally, we propose a novel LSTM model with spatial attention to tackle the 7W QA tasks.

In the last year, new models and methods for pretraining and transfer learning have driven striking performance improvements across a range of language understanding tasks. The GLUE benchmark, introduced a little over one year ago, offers a single-number metric that summarizes progress on a diverse set of such tasks, but performance on the benchmark has recently surpassed the level of non-expert humans, suggesting limited headroom for further research. In this paper we present SuperGLUE, a new benchmark styled after GLUE with a new set of more difficult language understanding tasks, a software toolkit, and a public leaderboard. SuperGLUE is available at super.gluebenchmark.com.

Recent years have witnessed an increasing interest in image-based question-answering (QA) tasks. However, due to data limitations, there has been much less work on video-based QA. In this paper, we present TVQA, a largescale video QA dataset based on 6 popular TV shows. TVQA consists of 152,545 QA pairs from 21,793 clips, spanning over 460 hours of video. Questions are designed to be compositional in nature, requiring systems to jointly localize relevant moments within a clip, comprehend subtitle-based dialogue, and recognize relevant visual concepts. We provide analyses of this new dataset as well as several baselines and a multi-stream end-to-end trainable neural network framework for the TVQA task. The dataset is publicly available at http://tvqa.cs.unc.edu.

Artificial Intelligence (AI) and its applications have sparked extraordinary interest in recent years. This achievement can be ascribed in part to advances in AI subfields including Machine Learning (ML), Computer Vision (CV), and Natural Language Processing (NLP). Deep learning, a sub-field of machine learning that employs artificial neural network concepts, has enabled the most rapid growth in these domains. The integration of vision and language has sparked a lot of attention as a result of this. The tasks have been created in such a way that they properly exemplify the concepts of deep learning. In this review paper, we provide a thorough and an extensive review of the state of the arts approaches, key models design principles and discuss existing datasets, methods, their problem formulation and evaluation measures for VQA and Visual reasoning tasks to understand vision and language representation learning. We also present some potential future paths in this field of research, with the hope that our study may generate new ideas and novel approaches to handle existing difficulties and develop new applications.

目前的视觉问题应答（VQA）任务主要考虑回答自然图像的人为注释问题。然而，除了自然图像之外，在视觉理解和推理研究中仍然可以解读具有语义丰富性的抽象图。在这项工作中，我们介绍了ICON问题的新挑战（ICONQA），其目标是在图标图像上下文中回答问题。我们发布了ICONQA，这是一个由107,439个问题和三个子任务组成的大型数据集：多图像选择，多文本选择和填充空白。 ICONQA数据集是由真实世界图中的启发，突出了抽象图理解和综合认知推理的重要性。因此，ICONQA不仅需要对象识别和文本理解等感知技能，而且还需要多种认知推理技能，例如几何推理，致辞推理和算术推理。为了促进潜在的iconqa模型来学习图标图像的语义表示，我们进一步发布了一个图标数据集图标645，其中包含377级上的645,687个彩色图标。我们进行广泛的用户研究和盲目实验，并重现各种先进的VQA方法来基准iconQA任务。此外，我们开发了一个强大的ICONQA基线Patch-TRM，它应用金字塔跨模型变压器，其中包含在图标数据集上预先培训的输入图嵌入式。 iconqa和图标645可在https://iconqa.github.io提供。

Figure 1: Our MovieQA dataset contains 14,944 questions about 408 movies. It contains multiple sources of information: plots, subtitles, video clips, scripts, and DVS transcriptions. In this figure we show example QAs from The Matrix and localize them in the timeline.

作为人类，我们可以通过想象我们的思想中的替代对象或概念来修改对场景的假设。例如，我们可以轻松地预见到雨云（例如，街道会被弄湿），并为此做准备。在本文中，我们介绍了一个新任务/数据集，称为反事实场景（COSIM），旨在评估AI系统对场景变化想象的推论的能力。在此任务/数据集中，为图像提供了模型和一个初始的问题响应对。接下来，应用了反事实想象的场景更改（以文本形式），该模型必须根据此场景更改预测对初始问题的新回答。我们收集3.5k高质量和具有挑战性的数据实例，每个实例都包含图像，一个常识性问题，响应，对反事实变化的描述，对问题的新回答以及三个干扰器响应。我们的数据集包含各种复杂的场景更改类型（例如对象添加/删除/状态更改，事件描述，环境更改等），这些更改需要模型来想象许多不同的场景和原因。我们提出了基于视觉变压器（即LXMERT）和消融研究的基线模型。通过人类的评估，我们证明了较大的人类模型性能差距，这为有望在这项具有挑战性的反事实，场景想象任务上做出有希望的未来工作。我们的代码和数据集可公开可用：https：//github.com/hyounghk/cosim

它仍然是一个管道梦想，电话和AR眼镜的AI助手可以帮助我们的日常生活来解决我们的问题，如“如何调整这款手表日期？”和“如何设置加热持续时间？（指向烤箱的同时）”。传统任务中使用的查询（即视频问题应答，视频检索，时刻定位）通常是有关的，并基于纯文本。相比之下，我们提出了一项名为Cometdancy的问题驱动视频段检索（AQVSR）的新任务。我们每个问题都是一个图像框文本查询，专注于我们日常生活中的物品，并期望从教学视频转录程序段的语料库中检索相关的答案段。为了支持对此AQVSR任务的研究，我们构建一个名为AssionSR的新数据集。我们设计新颖的准则来创造高质量样本。此数据集包含有关1K视频片段的1.4K多模态问题，来自各种日用物品的教学视频。为了解决AQVSR，我们开发了一个称为双重多模式编码器（DME）的简单但有效的模型，显着优于几种基线方法，同时仍然有大型未来改善空间。此外，我们提供了详细的消融分析。我们的代码和数据可以在https://github.com/stanlei52/aqvsr中获得。

相同上下文的可能后果可能会因我们所指的情况而异。但是，当前在自然语言处理中的研究并不集中于多种可能情况下的常识性推理。本研究通过短篇小说文字提出与候选人答案相同的结尾的多个问题来构成这项任务。我们由此产生的数据集，可能的故事，包括超过1.3k的故事文本超过4.5k的问题。我们发现，即使是目前的强训练性语言模型也很难始终如一地回答问题，这强调了无监督环境中最高的准确性（60.2％）远远落后于人类准确性（92.5％）。通过与现有数据集进行比较，我们观察到数据集中的问题包含答案选项中的最小注释伪像。此外，我们的数据集还包括需要反事实推理的示例，以及需要读者的反应和虚构信息的示例，这表明我们的数据集可以作为对未来常识性推理的未来研究的挑战性测试。

为了实现长文档理解的构建和测试模型，我们引入质量，具有中文段的多项选择QA DataSet，具有约5,000个令牌的平均长度，比典型的当前模型更长。与经过段落的事先工作不同，我们的问题是由阅读整个段落的贡献者编写和验证的，而不是依赖摘要或摘录。此外，只有一半的问题是通过在紧缩时间限制下工作的注释器来应答，表明略读和简单的搜索不足以一直表现良好。目前的模型在此任务上表现不佳（55.4％），并且落后于人类性能（93.5％）。

We introduce a new dataset for joint reasoning about natural language and images, with a focus on semantic diversity, compositionality, and visual reasoning challenges. The data contains 107,292 examples of English sentences paired with web photographs. The task is to determine whether a natural language caption is true about a pair of photographs. We crowdsource the data using sets of visually rich images and a compare-and-contrast task to elicit linguistically diverse language. Qualitative analysis shows the data requires compositional joint reasoning, including about quantities, comparisons, and relations. Evaluation using state-of-the-art visual reasoning methods shows the data presents a strong challenge. * Contributed equally. † Work done as an undergraduate at Cornell University. 1 In parts of this paper, we use the term compositional differently than it is commonly used in linguistics to refer to reasoning that requires composition. This type of reasoning often manifests itself in highly compositional language.2 Appendix G contains license information for all photographs used in this paper. 3 The top example is True, while the bottom is False.

多模型对现实世界应用的承诺激发了可视化和理解其内部力学的研究，其最终目标是使利益相关者能够可视化模型行为，执行模型调试并促进对机器学习模型的信任。但是，现代的多模型模型通常是黑盒神经网络，这使得了解其内部力学变得具有挑战性。我们如何能在这些模型中可视化多模式相互作用的内部建模？我们的论文旨在通过提出Multiviz来填补这一空白，这是一种通过将可解释性问题分为4个阶段来分析多模型模型行为的方法：（1）单峰的重要性：每种模式如何有助于下游建模和预测，（2）交叉交叉。 - 模式相互作用：不同模态如何相互关系，（3）多模式表示：如何在决策级特征中表示单峰和跨模式的交互作用，以及（4）多模式预测：决策级特征如何组成以制造一个预言。 Multiviz旨在在不同的模式，模型，任务和研究领域进行操作。通过对6个现实世界任务的8个训练模型的实验，我们表明，Multiviz中的互补阶段共同使用户能够（1）模拟模型预测，（2）将可解释的概念分配给功能，（3）对模型错误分析执行错误分析，（4）使用错误分析到调试模型的见解。 Multiviz公开可用，将定期使用新的解释工具和指标进行更新，并欢迎社区的意见。

From a visual scene containing multiple people, human is able to distinguish each individual given the context descriptions about what happened before, their mental/physical states or intentions, etc. Above ability heavily relies on human-centric commonsense knowledge and reasoning. For example, if asked to identify the "person who needs healing" in an image, we need to first know that they usually have injuries or suffering expressions, then find the corresponding visual clues before finally grounding the person. We present a new commonsense task, Human-centric Commonsense Grounding, that tests the models' ability to ground individuals given the context descriptions about what happened before, and their mental/physical states or intentions. We further create a benchmark, HumanCog, a dataset with 130k grounded commonsensical descriptions annotated on 67k images, covering diverse types of commonsense and visual scenes. We set up a context-object-aware method as a strong baseline that outperforms previous pre-trained and non-pretrained models. Further analysis demonstrates that rich visual commonsense and powerful integration of multi-modal commonsense are essential, which sheds light on future works. Data and code will be available https://github.com/Hxyou/HumanCog.