Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Australian National University（澳大利亚国立大学）；JD AI Research（京东人工智能研究院）；Microsoft Research（微软研究院）；University of Adelaide（阿德莱德大学）；Macquarie University（麦考瑞大学）
Peter Anderson, Xiaodong He, Chris Buehler, Damien Teney, Mark Johnson, Stephen Gould, Lei Zhang
备注：
CVPR 2018 full oral, winner of the 2017 Visual Question Answering challenge
Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning. In this work, we propose a combined bottom-up and top-down attention mechanism that enables attention to be calculated at the level of objects and other salient image regions. This is the natural basis for attention to be considered. Within our approach, the bottom-up mechanism (based on Faster R-CNN) proposes image regions, each with an associated feature vector, while the top-down mechanism determines feature weightings. Applying this approach to image captioning, our results on the MSCOCO test server establish a new state-of-the-art for the task, achieving CIDEr / SPICE / BLEU-4 scores of 117.9, 21.5 and 36.9, respectively. Demonstrating the broad applicability of the method, applying the same approach to VQA we obtain first place in the 2017 VQA Challenge.
Sony Interactive Entertainment LLC（索尼互动娱乐有限责任公司）；Georgia Institute of Technology（佐治亚理工学院）；State University of New York at Binghamton（纽约州立大学宾汉姆顿分校）
Image captioning has attracted considerable attention in recent years. However, little work has been done for game image captioning which has some unique characteristics and requirements. In this work we propose a novel game image captioning model which integrates bottom-up attention with a new multi-level residual top-down attention mechanism. Firstly, a lower-level residual top-down attention network is added to the Faster R-CNN based bottom-up attention network to address the problem that the latter may lose important spatial information when extracting regional features. Secondly, an upper…
Australian Centre for Visual Technologies（澳大利亚视觉技术中心）；The University of Adelaide（阿德莱德大学）
Much recent progress in Vision-to-Language problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic concepts, but rather seeks to progress directly from image features to text. In this paper we first propose a method of incorporating high-level concepts into the successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art in both image captioning and visual question answering. We further show that the same mechanism ca…
We propose an Auto-Parsing Network (APN) to discover and exploit the input data's hidden tree structures for improving the effectiveness of the Transformer-based vision-language systems. Specifically, we impose a Probabilistic Graphical Model (PGM) parameterized by the attention operations on each self-attention layer to incorporate sparse assumption. We use this PGM to softly segment an input sequence into a few clusters where each cluster can be treated as the parent of the inside entities. By stacking these PGM constrained self-attention layers, the clusters in a lower layer compose into a …
Object detection plays an important role in current solutions to vision and language tasks like image captioning and visual question answering. However, popular models like Faster R-CNN rely on a costly process of annotating ground-truths for both the bounding boxes and their corresponding semantic labels, making it less amenable as a primitive task for transfer learning. In this paper, we examine the effect of decoupling box proposal and featurization for down-stream tasks. The key insight is that this allows us to leverage a large amount of labeled annotations that were previously unavailabl…
University of Colorado Colorado Springs（科罗拉多大学科罗拉多斯普林斯分校）
Image captioning is the task of automatically generating sentences that describe an input image in the best way possible. The most successful techniques for automatically generating image captions have recently used attentive deep learning models. There are variations in the way deep learning models with attention are designed. In this survey, we provide a review of literature related to attentive deep learning models for image captioning. Instead of offering a comprehensive review of all prior work on deep image captioning models, we explain various types of attention mechanisms used for the …
Department of Computer Science（计算机科学系）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；cs.utexas.edu（德克萨斯大学奥斯汀分校计算机科学系（注：此处原文本中cs.utexas.edu为邮箱域名，按规则不应提取为机构，正确应为The University of Texas at Austin））
Answering visual questions need acquire daily common knowledge and model the semantic connection among different parts in images, which is too difficult for VQA systems to learn from images with the only supervision from answers. Meanwhile, image captioning systems with beam search strategy tend to generate similar captions and fail to diversely describe images. To address the aforementioned issues, we present a system to have these two tasks compensate with each other, which is capable of jointly producing image captions and answering visual questions. In particular, we utilize question and i…
We propose a high-level concept word detector that can be integrated with any video-to-language models. It takes a video as input and generates a list of concept words as useful semantic priors for language generation models. The proposed word detector has two important properties. First, it does not require any external knowledge sources for training. Second, the proposed word detector is trainable in an end-to-end manner jointly with any video-to-language models. To maximize the values of detected words, we also develop a semantic attention mechanism that selectively focuses on the detected …
University of Rochester（罗切斯特大学）；Adobe Research（奥多比研究院）
Automatically generating a natural language description of an image has attracted interests recently both because of its importance in practical applications and because it connects two major artificial intelligence fields: computer vision and natural language processing. Existing approaches are either top-down, which start from a gist of an image and convert it into words, or bottom-up, which come up with words describing various aspects of an image and then combine them. In this paper, we propose a new algorithm that combines both approaches through a model of semantic attention. Our algorit…
HiTZ Basque Center for Language Technologies（HiTZ巴斯克语言技术中心）；University of the Basque Country (UPV/EHU)（巴斯克大学（UPV/EHU））
Integrating outside knowledge for reasoning in visio-linguistic tasks such as visual question answering (VQA) is an open problem. Given that pretrained language models have been shown to include world knowledge, we propose to use a unimodal (text-only) train and inference procedure based on automatic off-the-shelf captioning of images and pretrained language models. Our results on a visual question answering task which requires external knowledge (OK-VQA) show that our text-only model outperforms pretrained multimodal (image-text) models of comparable number of parameters. In contrast, our mod…
Detecting and Understanding Hateful Contents in Memes Through Captioning and Visual Question-Answering
The University of Sydney, School of Computer Science（悉尼大学计算机科学学院）；University of Technology Sydney, School of Computer Science（新南威尔士大学技术学院）；University of Technology Sydney, TD School（新南威尔士大学TD学院）；Australian Catholic University, Peter Faber Business School（澳大利亚天主教大学彼得·法伯商学院）
We present Answer-Me, a task-aware multi-task framework which unifies a variety of question answering tasks, such as, visual question answering, visual entailment, visual reasoning. In contrast to previous works using contrastive or generative captioning training, we propose a novel and simple recipe to pre-train a vision-language joint model, which is multi-task as well. The pre-training uses only noisy image captioning data, and is formulated to use the entire architecture end-to-end with both a strong language encoder and decoder. Our results show state-of-the-art performance, zero-shot gen…
University of Michigan（密歇根大学）；Microsoft Research（微软研究院）；Microsoft Cloud & AI（微软云与人工智能部门）；Microsoft AI & Research（微软人工智能与研究部门）
This paper presents a unified Vision-Language Pre-training (VLP) model. The model is unified in that (1) it can be fine-tuned for either vision-language generation (e.g., image captioning) or understanding (e.g., visual question answering) tasks, and (2) it uses a shared multi-layer transformer network for both encoding and decoding, which differs from many existing methods where the encoder and decoder are implemented using separate models. The unified VLP model is pre-trained on a large amount of image-text pairs using the unsupervised learning objectives of two tasks: bidirectional and sequ…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
Gaze reflects how humans process visual scenes and is therefore increasingly used in computer vision systems. Previous works demonstrated the potential of gaze for object-centric tasks, such as object localization and recognition, but it remains unclear if gaze can also be beneficial for scene-centric tasks, such as image captioning. We present a new perspective on gaze-assisted image captioning by studying the interplay between human gaze and the attention mechanism of deep neural networks. Using a public large-scale gaze dataset, we first assess the relationship between state-of-the-art obje…
Most attention-based image captioning models attend to the image once per word. However, attending once per word is rigid and is easy to miss some information. Attending more times can adjust the attention position, find the missing information back and avoid generating the wrong word. In this paper, we show that attending more times per word can gain improvements in the image captioning task, without increasing the number of parameters. We propose a flexible two-LSTM merge model to make it convenient to encode more attentions than words. Our captioning model uses two LSTMs to encode the word …
Aalto University（阿尔托大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；University of Central Florida（中佛罗里达大学）
To bridge the gap between humans and machines in image understanding and describing, we need further insight into how people describe a perceived scene. In this paper, we study the agreement between bottom-up saliency-based visual attention and object referrals in scene description constructs. We investigate the properties of human-written descriptions and machine-generated ones. We then propose a saliency-boosted image captioning model in order to investigate benefits from low-level cues in language models. We learn that (1) humans mention more salient objects earlier than less salient ones i…
Google Research（谷歌研究院）；Massachusetts Institute of Technology（麻省理工学院）
The traditional image captioning task uses generic reference captions to provide textual information about images. Different user populations, however, will care about different visual aspects of images. In this paper, we propose a new task, Captioning with a Purpose (CapWAP). Our goal is to develop systems that can be tailored to be useful for the information needs of an intended population, rather than merely provide generic information about an image. In this task, we use question-answer (QA) pairs---a natural expression of information need---from users, instead of reference captions, for b…
Deep neural networks have achieved promising results in automatic image captioning due to their effective representation learning and context-based content generation capabilities. As a prominent type of deep features used in many of the recent image captioning methods, the well-known bottomup features provide a detailed representation of different objects of the image in comparison with the feature maps directly extracted from the raw image. However, the lack of high-level semantic information about the relationships between these objects is an important drawback of bottom-up features, despit…
Captioning is a crucial and challenging task for video understanding. In videos that involve active agents such as humans, the agent's actions can bring about myriad changes in the scene. Observable changes such as movements, manipulations, and transformations of the objects in the scene, are reflected in conventional video captioning. Unlike images, actions in videos are also inherently linked to social aspects such as intentions (why the action is taking place), effects (what changes due to the action), and attributes that describe the agent. Thus for video understanding, such as when captio…
Zhejiang University（浙江大学）；Columbia University（哥伦比亚大学）；Shandong University（山东大学）；Tencent AI Lab（腾讯AI实验室）；National University of Singapore（新加坡国立大学）
Visual attention has been successfully applied in structural prediction tasks such as visual captioning and question answering. Existing visual attention models are generally spatial, i.e., the attention is modeled as spatial probabilities that re-weight the last conv-layer feature map of a CNN encoding an input image. However, we argue that such spatial attention does not necessarily conform to the attention mechanism --- a dynamic feature extractor that combines contextual fixations over time, as CNN features are naturally spatial, channel-wise and multi-layer. In this paper, we introduce a …
Global Big Data Technologies Centre, University of Technology Sydney（悉尼科技大学全球大数据技术中心）
Generating natural sentences from images is a fundamental learning task for visual-semantic understanding in multimedia. In this paper, we propose to apply dual attention on pyramid image feature maps to fully explore the visual-semantic correlations and improve the quality of generated sentences. Specifically, with the full consideration of the contextual information provided by the hidden state of the RNN controller, the pyramid attention can better localize the visually indicative and semantically consistent regions in images. On the other hand, the contextual information can help re-calibr…
Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Peng Cheng Laboratory（鹏城实验室）；Anhui University（安徽大学）；Beijing Institute of Technology（北京理工大学）；Sun Yat-Sen University（中山大学）；The Hong Kong Polytechnic University（香港理工大学）
Unpaired Image Captioning (UIC) has been developed to learn image descriptions from unaligned vision-language sample pairs. Existing works usually tackle this task using adversarial learning and visual concept reward based on reinforcement learning. However, these existing works were only able to learn limited cross-domain information in vision and language domains, which restrains the captioning performance of UIC. Inspired by the success of Vision-Language Pre-Trained Models (VL-PTMs) in this research, we attempt to infer the cross-domain cue information about a given image from the large VL…
We present a pre-training approach for vision and language transformer models, which is based on a mixture of diverse tasks. We explore both the use of image-text captioning data in pre-training, which does not need additional supervision, as well as object-aware strategies to pre-train the model. We evaluate the method on a number of textgenerative vision+language tasks, such as Visual Question Answering, visual entailment and captioning, and demonstrate large gains over standard pre-training methods.
University of Science and Technology of China（中国科学技术大学）；Hefei University of Technology（合肥工业大学）
Generating natural language descriptions for videos, i.e., video captioning, essentially requires step-by-step reasoning along the generation process. For example, to generate the sentence "a man is shooting a basketball", we need to first locate and describe the subject "man", next reason out the man is "shooting", then describe the object "basketball" of shooting. However, existing visual reasoning methods designed for visual question answering are not appropriate to video captioning, for it requires more complex visual reasoning on videos over both space and time, and dynamic module composi…
Recent progress on fine-grained visual recognition and visual question answering has featured Bilinear Pooling, which effectively models the 2$^{nd}$ order interactions across multi-modal inputs. Nevertheless, there has not been evidence in support of building such interactions concurrently with attention mechanism for image captioning. In this paper, we introduce a unified attention block -- X-Linear attention block, that fully employs bilinear pooling to selectively capitalize on visual information or perform multi-modal reasoning. Technically, X-Linear attention block simultaneously exploit…
Image captioning systems have recently improved dramatically, but they still tend to produce captions that are insensitive to the communicative goals that captions should meet. To address this, we propose Issue-Sensitive Image Captioning (ISIC). In ISIC, a captioning system is given a target image and an issue, which is a set of images partitioned in a way that specifies what information is relevant. The goal of the captioner is to produce a caption that resolves this issue. To model this task, we use an extension of the Rational Speech Acts model of pragmatic language use. Our extension is bu…
KU Leuven（鲁汶大学）；New York University（纽约大学）；ILLC, University of Amsterdam（阿姆斯特丹大学逻辑、语言与计算研究所）
Many top-performing image captioning models rely solely on object features computed with an object detection model to generate image descriptions. However, recent studies propose to directly use scene graphs to introduce information about object relations into captioning, hoping to better describe interactions between objects. In this work, we thoroughly investigate the use of scene graphs in image captioning. We empirically study whether using additional scene graph encoders can lead to better image descriptions and propose a conditional graph attention network (C-GAT), where the image captio…
BTCChat: Advancing Remote Sensing Bi-temporal Change Captioning with Multimodal Large Language Model
State Key Laboratory of Networking and Switching Technology（网络与交换技术国家重点实验室）；Beijing University of Posts and Telecommunications（北京邮电大学）；Aerospace Information Research Institute（航天信息研究所）；Chinese Academy of Sciences（中国科学院）；School of Geographical Sciences（地理科学学院）；Hunan Normal University（湖南师范大学）
Top-Down Framework for Weakly-supervised Grounded Image Captioning
School of Electrical and Electronic Engineering, Nanyang Technology University（南洋理工大学电气与电子工程学院）；Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University（香港理工大学电气与电子工程系）
The Chinese University of Hong Kong（香港中文大学）；University of Toronto（多伦多大学）；Vector Institute（矢量研究院）；NVIDIA（英伟达）
Mainstream captioning models often follow a sequential structure to generate captions, leading to issues such as introduction of irrelevant semantics, lack of diversity in the generated captions, and inadequate generalization performance. In this paper, we present an alternative paradigm for image captioning, which factorizes the captioning procedure into two stages: (1) extracting an explicit semantic representation from the given image; and (2) constructing the caption based on a recursive compositional procedure in a bottom-up manner. Compared to conventional ones, our paradigm better prese…
We propose UniTAB that Unifies Text And Box outputs for grounded vision-language (VL) modeling. Grounded VL tasks such as grounded captioning require the model to generate a text description and align predicted words with object regions. To achieve this, models must generate desired text and box outputs together, and meanwhile indicate the alignments between words and boxes. In contrast to existing solutions that use multiple separate modules for different outputs, UniTAB represents both text and box outputs with a shared token sequence, and introduces a special <obj> token to naturally indica…
RS-MoE: A Vision-Language Model with Mixture of Experts for Remote Sensing Image Captioning and Visual Question Answering
China Academy of Electronics and Information Technology（中国电子科技集团公司电子科学研究院）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Harbin Institute of Technology（哈尔滨工业大学）；New York University Abu Dhabi（纽约大学阿布扎比分校）
Attention modules connecting encoder and decoders have been widely applied in the field of object recognition, image captioning, visual question answering and neural machine translation, and significantly improves the performance. In this paper, we propose a bottom-up gated hierarchical attention (GHA) mechanism for image captioning. Our proposed model employs a CNN as the decoder which is able to learn different concepts at different layers, and apparently, different concepts correspond to different areas of an image. Therefore, we develop the GHA in which low-level concepts are merged into h…
Renmin University of China（中国人民大学）；INRIA（法国国家信息与自动化研究所）
For an image with multiple scene texts, different people may be interested in different text information. Current text-aware image captioning models are not able to generate distinctive captions according to various information needs. To explore how to generate personalized text-aware captions, we define a new challenging task, namely Question-controlled Text-aware Image Captioning (Qc-TextCap). With questions as control signals, this task requires models to understand questions, find related scene texts and describe them together with objects fluently in human language. Based on two existing …
Visual question answering (VQA) and image captioning require a shared body of general knowledge connecting language and vision. We present a novel approach to improve VQA performance that exploits this connection by jointly generating captions that are targeted to help answer a specific visual question. The model is trained using an existing caption dataset by automatically determining question-relevant captions using an online gradient-based method. Experimental results on the VQA v2 challenge demonstrates that our approach obtains state-of-the-art VQA performance (e.g. 68.4% on the Test-stan…
CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning
Tsinghua University（清华大学）；University of Science and Technology of China（中国科学技术大学）；Microsoft（微软）；Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Innovation Institute（上海创新研究院）；Alibaba Cloud（阿里云）；The Chinese University of Hong Kong（香港中文大学）
UMass Amherst（马萨诸塞大学阿默斯特分校）；Facebook AI Research (FAIR)（Facebook人工智能研究院（FAIR））
Popularized as 'bottom-up' attention, bounding box (or region) based visual features have recently surpassed vanilla grid-based convolutional features as the de facto standard for vision and language tasks like visual question answering (VQA). However, it is not clear whether the advantages of regions (e.g. better localization) are the key reasons for the success of bottom-up attention. In this paper, we revisit grid features for VQA, and find they can work surprisingly well - running more than an order of magnitude faster with the same accuracy (e.g. if pre-trained in a similar fashion). Thro…
In image captioning where fluency is an important factor in evaluation, e.g., $n$-gram metrics, sequential models are commonly used; however, sequential models generally result in overgeneralized expressions that lack the details that may be present in an input image. Inspired by the idea of the compositional neural module networks in the visual question answering task, we introduce a hierarchical framework for image captioning that explores both compositionality and sequentiality of natural language. Our algorithm learns to compose a detail-rich sentence by selectively attending to different …
University of Naples Federico II（那不勒斯费德里科二世大学）；University of Salerno（萨勒诺大学）；Sapienza University of Rome（罗马第一大学）；University of Molise（莫利塞大学）
Visual Question Answering (VQA) is an extremely stimulating and challenging research area where Computer Vision (CV) and Natural Language Processig (NLP) have recently met. In image captioning and video summarization, the semantic information is completely contained in still images or video dynamics, and it has only to be mined and expressed in a human-consistent way. Differently from this, in VQA semantic information in the same media must be compared with the semantics implied by a question expressed in natural language, doubling the artificial intelligence-related effort. Some recent survey…
Carnegie Mellon University（卡内基梅隆大学）；Allen Institute for AI（艾伦人工智能研究所）；University of Utah（犹他大学）
Combining the visual modality with pretrained language models has been surprisingly effective for simple descriptive tasks such as image captioning. More general text generation however remains elusive. We take a step back and ask: How do these models work for more complex generative tasks, i.e. conditioning on both text and images? Are multimodal models simply visually adapted language models, or do they combine they reason jointly over modalities? We investigate these questions in the context of self-rationalization (jointly generating task labels/answers and free-text explanations) of three…
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）；University of Science and Technology Beijing（北京科技大学）；Wuhan University（武汉大学）；University of Chinese Academy of Sciences（中国科学院大学）
Self-attention (SA) network has shown profound value in image captioning. In this paper, we improve SA from two aspects to promote the performance of image captioning. First, we propose Normalized Self-Attention (NSA), a reparameterization of SA that brings the benefits of normalization inside SA. While normalization is previously only applied outside SA, we introduce a novel normalization method and demonstrate that it is both possible and beneficial to perform it on the hidden activations inside SA. Second, to compensate for the major limit of Transformer that it fails to model the geometry …
The internal workings of modern deep learning models stay often unclear to an external observer, although spatial attention mechanisms are involved. The idea of this work is to translate these spatial attentions into natural language to provide a simpler access to the model's function. Thus, I took a neural image captioning model and measured the reactions to external modification in its spatial attention for three different interface methods: a fixation over the whole generation process, a fixation for the first time-steps and an addition to the generator's attention. The experimental results…
Human conversation is a complex mechanism with subtle nuances. It is hence an ambitious goal to develop artificial intelligence agents that can participate fluently in a conversation. While we are still far from achieving this goal, recent progress in visual question answering, image captioning, and visual question generation shows that dialog systems may be realizable in the not too distant future. To this end, a novel dataset was introduced recently and encouraging results were demonstrated, particularly for question answering. In this paper, we demonstrate a simple symmetric discriminative …
