Automatic image captioning has improved significantly over the last few years, but the problem is far from being solved, with state of the art models still often producing low quality captions when used in the wild. In this paper, we focus on the task of Quality Estimation (QE) for image captions, which attempts to model the caption quality from a human perspective and without access to ground-truth references, so that it can be applied at prediction time to detect low-quality captions produced on previously unseen images. For this task, we develop a human evaluation process that collects coarse-grained caption annotations from crowdsourced users, which is then used to collect a large scale dataset spanning more than 600k caption quality ratings. We then carefully validate the quality of the collected ratings and establish baseline models for this new QE task. Finally, we further collect fine-grained caption quality annotations from trained raters, and use them to demonstrate that QE models trained over the coarse ratings can effectively detect and filter out low-quality image captions, thereby improving the user experience from captioning systems.
We examine the possibility that recent promising results in automatic caption generation are due primarily to language models. By varying image representation quality produced by a convolutional neural network, we find that a state-of-the-art neural captioning algorithm is able to produce quality captions even when provided with surprisingly poor image representations. We replicate this result in a new, fine-grained, transfer learned captioning domain, consisting of 66K recipe image/title pairs. We also provide some experiments regarding the appropriateness of datasets for automatic captioning…
SynthVLM: Towards High-Quality and Efficient Synthesis of Image-Caption Datasets for Vision-Language Models
Peking University Beijing China；Huawei Technologies Ltd. Beijing China；Shanghai AI Laboratory Shanghai China；Peking University Center for Machine Learning Research Beijing China；Peking University School of Computer Science \& Key Lab of High Confidence Software Technologies (MOE) Beijing China；Peking University；Huawei Technologies Ltd.；Shanghai AI Laboratory
本文提出 SynthVLM 数据合成方法，利用扩散模型从文本描述合成并精选图像生成精确对齐的图像-文本对，构建了 SynthVLM-100K 数据集，并训练出在 VQA 任务上达到 SOTA 且保留语言能力的多模态大模型。
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…
Although significant progress has been made in the field of automatic image captioning, it is still a challenging task. Previous works normally pay much attention to improving the quality of the generated captions but ignore the diversity of captions. In this paper, we combine determinantal point process (DPP) and reinforcement learning (RL) and propose a novel reinforcing DPP (R-DPP) approach to generate a set of captions with high quality and diversity for an image. We show that R-DPP performs better on accuracy and diversity than using noise as a control signal (GANs, VAEs). Moreover, R-DPP…
University of Washington（华盛顿大学）；Allen Institute for AI（艾伦人工智能研究所）
We establish THumB, a rubric-based human evaluation protocol for image captioning models. Our scoring rubrics and their definitions are carefully developed based on machine- and human-generated captions on the MSCOCO dataset. Each caption is evaluated along two main dimensions in a tradeoff (precision and recall) as well as other aspects that measure the text quality (fluency, conciseness, and inclusive language). Our evaluations demonstrate several critical problems of the current evaluation practice. Human-generated captions show substantially higher quality than machine-generated ones, espe…
Mitsubishi electric research laboratories（三菱电机研究实验室）
Video captioning is an essential technology to understand scenes and describe events in natural language. To apply it to real-time monitoring, a system needs not only to describe events accurately but also to produce the captions as soon as possible. Low-latency captioning is needed to realize such functionality, but this research area for online video captioning has not been pursued yet. This paper proposes a novel approach to optimize each caption's output timing based on a trade-off between latency and caption quality. An audio-visual Trans-former is trained to generate ground-truth caption…
CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；The University of Hong Kong（香港大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
We use coherence relations inspired by computational models of discourse to study the information needs and goals of image captioning. Using an annotation protocol specifically devised for capturing image--caption coherence relations, we annotate 10,000 instances from publicly-available image--caption pairs. We introduce a new task for learning inferences in imagery and text, coherence relation prediction, and show that these coherence annotations can be exploited to learn relation classifiers as an intermediary step, and also train coherence-aware, controllable image captioning models. The re…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Microsoft Research（微软研究院）；University of California, Santa Barbara（加利福尼亚大学圣巴巴拉分校）
This paper presents a new metric called TIGEr for the automatic evaluation of image captioning systems. Popular metrics, such as BLEU and CIDEr, are based solely on text matching between reference captions and machine-generated captions, potentially leading to biased evaluations because references may not fully cover the image content and natural language is inherently ambiguous. Building upon a machine-learned text-image grounding model, TIGEr allows to evaluate caption quality not only based on how well a caption represents image content, but also on how well machine-generated captions match…
ADAPT Research Centre（ADAPT研究中心）；Dublin City University（都柏林城市大学）；National Institute of Standards and Technology（美国国家标准与技术研究院）；Dakota Consulting, Inc.（达科他咨询公司）；Insight Centre for Data Analytics（洞察数据分析中心）
We present Direct Assessment, a method for manually assessing the quality of automatically-generated captions for video. Evaluating the accuracy of video captions is particularly difficult because for any given video clip there is no definitive ground truth or correct answer against which to measure. Automatic metrics for comparing automatic video captions against a manual caption such as BLEU and METEOR, drawn from techniques used in evaluating machine translation, were used in the TRECVid video captioning task in 2016 but these are shown to have weaknesses. The work presented here brings hum…
INESC-ID；Instituto Superior Técnico（高等技术学院）；University of Lisbon（里斯本大学）；University of Copenhagen（哥本哈根大学）
Inspired by retrieval-augmented language generation and pretrained Vision and Language (V&L) encoders, we present a new approach to image captioning that generates sentences given the input image and a set of captions retrieved from a datastore, as opposed to the image alone. The encoder in our model jointly processes the image and retrieved captions using a pretrained V&L BERT, while the decoder attends to the multimodal encoder representations, benefiting from the extra textual evidence from the retrieved captions. Experimental results on the COCO dataset show that image captioning can be ef…
ByteDance Inc.（字节跳动公司）；Institute of Software Chinese Academy of Sciences（中国科学院软件研究所）
This paper describes our champion solution for the CVPR2022 Generic Event Boundary Captioning (GEBC) competition. GEBC requires the captioning model to have a comprehension of instantaneous status changes around the given video boundary, which makes it much more challenging than conventional video captioning task. In this paper, a Dual-Stream Transformer with improvements on both video content encoding and captions generation is proposed: (1) We utilize three pre-trained models to extract the video features from different granularities. Moreover, we exploit the types of boundary as hints to he…
POSTECH（浦项科技大学）；Seoul National University（首尔国立大学）；Google Research（谷歌研究院）
Human ratings are currently the most accurate way to assess the quality of an image captioning model, yet most often the only used outcome of an expensive human rating evaluation is a few overall statistics over the evaluation dataset. In this paper, we show that the signal from instance-level human caption ratings can be leveraged to improve captioning models, even when the amount of caption ratings is several orders of magnitude less than the caption training data. We employ a policy gradient method to maximize the human ratings as rewards in an off-policy reinforcement learning setting, whe…
EAMA : Entity-Aware Multimodal Alignment Based Approach for News Image Captioning
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；School of Electronics Engineering and Computer Science, Peking University（北京大学电子工程与计算机科学学院）
In this paper, we study the impact of motion blur, a common quality flaw in real world images, on a state-of-the-art two-stage image captioning solution, and notice a degradation in solution performance as blur intensity increases. We investigate techniques to improve the robustness of the solution to motion blur using training data augmentation at each or both stages of the solution, i.e., object detection and captioning, and observe improved results. In particular, augmenting both the stages reduces the CIDEr-D degradation for high motion blur intensity from 68.7 to 11.7 on MS COCO dataset, …
Benefiting from advances in machine vision and natural language processing techniques, current image captioning systems are able to generate detailed visual descriptions. For the most part, these descriptions represent an objective characterisation of the image, although some models do incorporate subjective aspects related to the observer's view of the image, such as sentiment; current models, however, usually do not consider the emotional content of images during the caption generation process. This paper addresses this issue by proposing novel image captioning models which use facial expres…
University of Modena and Reggio Emilia（摩德纳和雷焦艾米利亚大学）
Image captioning models have lately shown impressive results when applied to standard datasets. Switching to real-life scenarios, however, constitutes a challenge due to the larger variety of visual concepts which are not covered in existing training sets. For this reason, novel object captioning (NOC) has recently emerged as a paradigm to test captioning models on objects which are unseen during the training phase. In this paper, we present a novel approach for NOC that learns to select the most relevant objects of an image, regardless of their adherence to the training set, and to constrain …
Current image captioning methods are usually trained via (penalized) maximum likelihood estimation. However, the log-likelihood score of a caption does not correlate well with human assessments of quality. Standard syntactic evaluation metrics, such as BLEU, METEOR and ROUGE, are also not well correlated. The newer SPICE and CIDEr metrics are better correlated, but have traditionally been hard to optimize for. In this paper, we show how to use a policy gradient (PG) method to directly optimize a linear combination of SPICE and CIDEr (a combination we call SPIDEr): the SPICE score ensures our c…
University of Modena and Reggio Emilia（摩德纳和雷焦艾米利亚大学）
Current captioning approaches can describe images using black-box architectures whose behavior is hardly controllable and explainable from the exterior. As an image can be described in infinite ways depending on the goal and the context at hand, a higher degree of controllability is needed to apply captioning algorithms in complex scenarios. In this paper, we introduce a novel framework for image captioning which can generate diverse descriptions by allowing both grounding and controllability. Given a control signal in the form of a sequence or set of image regions, we generate the correspondi…
CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning
University of Science and Technology of China（中国科学技术大学）；Shanghai AI Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Innovation Institute（上海创新研究院）；Alibaba Cloud（阿里巴巴云）
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Carnegie Mellon University（卡内基梅隆大学）；Microsoft Research, Redmond（微软研究院雷德蒙德分院）
Popular metrics used for evaluating image captioning systems, such as BLEU and CIDEr, provide a single score to gauge the system's overall effectiveness. This score is often not informative enough to indicate what specific errors are made by a given system. In this study, we present a fine-grained evaluation method REO for automatically measuring the performance of image captioning systems. REO assesses the quality of captions from three perspectives: 1) Relevance to the ground truth, 2) Extraness of the content that is irrelevant to the ground truth, and 3) Omission of the elements in the ima…
Allen Institute for AI（艾伦人工智能研究所）；University of Washington（华盛顿大学）
Image captioning has conventionally relied on reference-based automatic evaluations, where machine captions are compared against captions written by humans. This is in contrast to the reference-free manner in which humans assess caption quality. In this paper, we report the surprising empirical finding that CLIP (Radford et al., 2021), a cross-modal model pretrained on 400M image+caption pairs from the web, can be used for robust automatic evaluation of image captioning without the need for references. Experiments spanning several corpora demonstrate that our new reference-free metric, CLIPSco…
Hefei University of Technology（合肥工业大学）；University of Science and Technology of China（中国科学技术大学）；Nanyang Technological University（南洋理工大学）
Visual attention not only improves the performance of image captioners, but also serves as a visual interpretation to qualitatively measure the caption rationality and model transparency. Specifically, we expect that a captioner can fix its attentive gaze on the correct objects while generating the corresponding words. This ability is also known as grounded image captioning. However, the grounding accuracy of existing captioners is far from satisfactory. To improve the grounding accuracy while retaining the captioning quality, it is expensive to collect the word-region alignment as strong supe…
Automated audio captioning aims at generating textual descriptions for an audio clip. To evaluate the quality of generated audio captions, previous works directly adopt image captioning metrics like SPICE and CIDEr, without justifying their suitability in this new domain, which may mislead the development of advanced models. This problem is still unstudied due to the lack of human judgment datasets on caption quality. Therefore, we firstly construct two evaluation benchmarks, AudioCaps-Eval and Clotho-Eval. They are established with pairwise comparison instead of absolute rating to achieve bet…
Saarland University（萨尔兰大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
Given an image, generating its natural language description (i.e., caption) is a well studied problem. Approaches proposed to address this problem usually rely on image features that are difficult to interpret. Particularly, these image features are subdivided into global and local features, where global features are extracted from the global representation of the image, while local features are extracted from the objects detected locally in an image. Although, local features extract rich visual information from the image, existing models generate captions in a blackbox manner and humans have …
VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning
Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学深圳分校）；Chinese Academy of Sciences（中国科学院）；Kuaishou Technology（快手科技）
University of California, Santa Barbara（加州大学圣巴巴拉分校）；ByteDance AI Lab（字节跳动人工智能实验室）
We present a new large-scale multilingual video description dataset, VATEX, which contains over 41,250 videos and 825,000 captions in both English and Chinese. Among the captions, there are over 206,000 English-Chinese parallel translation pairs. Compared to the widely-used MSR-VTT dataset, VATEX is multilingual, larger, linguistically complex, and more diverse in terms of both video and natural language descriptions. We also introduce two tasks for video-and-language research based on VATEX: (1) Multilingual Video Captioning, aimed at describing a video in various languages with a compact uni…
Language and vision are processed as two different modal in current work for image captioning. However, recent work on Super Characters method shows the effectiveness of two-dimensional word embedding, which converts text classification problem into image classification problem. In this paper, we propose the SuperCaptioning method, which borrows the idea of two-dimensional word embedding from Super Characters method, and processes the information of language and vision together in one single CNN model. The experimental results on Flickr30k data shows the proposed method gives high quality imag…
University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）
Image captioning models aim at connecting Vision and Language by providing natural language descriptions of input images. In the past few years, the task has been tackled by learning parametric models and proposing visual feature extraction advancements or by modeling better multi-modal connections. In this paper, we investigate the development of an image captioning approach with a kNN memory, with which knowledge can be retrieved from an external corpus to aid the generation process. Our architecture combines a knowledge retriever based on visual similarities, a differentiable encoder, and a…
Department of Applied Informatics, Graduate School of Science
We propose a simple yet effective image captioning framework that can determine the quality of an image and notify the user of the reasons for any flaws in the image. Our framework first determines the quality of images and then generates captions using only those images that are determined to be of high quality. The user is notified by the flaws feature to retake if image quality is low, and this cycle is repeated until the input image is deemed to be of high quality. As a component of the framework, we trained and evaluated a low-quality image detection model that simultaneously learns diffi…
Image caption generation systems are typically evaluated against reference outputs. We show that it is possible to predict output quality without generating the captions, based on the probability assigned by the neural model to the reference captions. Such pre-gen metrics are strongly correlated to standard evaluation metrics.
Researchers use figures to communicate rich, complex information in scientific papers. The captions of these figures are critical to conveying effective messages. However, low-quality figure captions commonly occur in scientific articles and may decrease understanding. In this paper, we propose an end-to-end neural framework to automatically generate informative, high-quality captions for scientific figures. To this end, we introduce SCICAP, a large-scale figure-caption dataset based on computer science arXiv papers published between 2010 and 2020. After pre-processing - including figure-type …
ST Engineering Mission Software & Services Pte. Ltd（新加坡科技工程任务软件服务私人有限公司）
In this paper, we propose an algorithm, Epochal Difficult Captions, to supplement the training of any model for the Automated Audio Captioning task. Epochal Difficult Captions is an elegant evolution to the keyword estimation task that previous work have used to train the encoder of the AAC model. Epochal Difficult Captions modifies the target captions based on a curriculum and a difficulty level determined as a function of current epoch. Epochal Difficult Captions can be used with any model architecture and is a lightweight function that does not increase training time. We test our results on…
