The triplet loss with semi-hard negatives has become the de facto choice for image-caption retrieval (ICR) methods that are optimized from scratch. Recent progress in metric learning has given rise to new loss functions that outperform the triplet loss on tasks such as image retrieval and representation learning. We ask whether these findings generalize to the setting of ICR by comparing three loss functions on two ICR methods. We answer this question negatively: the triplet loss with semi-hard negative mining still outperforms newly introduced loss functions from metric learning on the ICR task. To gain a better understanding of these outcomes, we introduce an analysis method to compare loss functions by counting how many samples contribute to the gradient w.r.t. the query representation during optimization. We find that loss functions that result in lower evaluation scores on the ICR task, in general, take too many (non-informative) samples into account when computing a gradient w.r.t. the query representation, which results in sub-optimal performance. The triplet loss with semi-hard negatives is shown to outperform the other loss functions, as it only takes one (hard) negative into account when computing the gradient.
Stanford University（斯坦福大学）；Meta AI；University of Surrey（萨里大学）
Multimodal tasks in the fashion domain have significant potential for e-commerce, but involve challenging vision-and-language learning problems - e.g., retrieving a fashion item given a reference image plus text feedback from a user. Prior works on multimodal fashion tasks have either been limited by the data in individual benchmarks, or have leveraged generic vision-and-language pre-training but have not taken advantage of the characteristics of fashion data. Additionally, these works have mainly been restricted to multimodal understanding tasks. To address these gaps, we make two key contrib…
Retrieving relevant images from a catalog based on a query image together with a modifying caption is a challenging multimodal task that can particularly benefit domains like apparel shopping, where fine details and subtle variations may be best expressed through natural language. We introduce a new evaluation dataset, Challenging Fashion Queries (CFQ), as well as a modeling approach that achieves state-of-the-art performance on the existing Fashion IQ (FIQ) dataset. CFQ complements existing benchmarks by including relative captions with positive and negative labels of caption accuracy and con…
Audio-Text retrieval takes a natural language query to retrieve relevant audio files in a database. Conversely, Text-Audio retrieval takes an audio file as a query to retrieve relevant natural language descriptions. Most of the literature train retrieval systems with one audio captioning dataset, but evaluating the benefit of training with multiple datasets is underexplored. Moreover, retrieval systems have to learn the alignment between elaborated sentences describing audio content of variable length ranging from a few seconds to several minutes. In this work, we propose a new collection of w…
Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained on that data. We introduce Spoken ObjectNet, which is designed to remove some of these biases and provide a way to better evaluate how effectively models will perform in real-world scenarios. This dataset expands upon ObjectNet, which is a bias-controlled image dataset that features similar image classes to those present in ImageNet. We detail our data collec…
Do Large Multimodal Models Solve Caption Generation for Scientific Figures? Lessons Learned from SciCap Challenge 2023
Pennsylvania State University（宾夕法尼亚州立大学）；National Tsing Hua University（国立清华大学）；AllSci（奥尔赛公司）；MetaMetrics Inc.（美塔麦特里克公司）；Adobe Research（奥多比研究院）；Institute of Information Science, Academia Sinica（中央研究院资讯科学研究所）
Retrieval-Guided Generation for Safer Histopathology Image Captioning
Kimia Lab, Department of Artificial Intelligence \& Informatics, Mayo Clinic, Rochester, MN, USA；Department of Biomedical Informatics, University of Arkansas for Medical Sciences, Little Rock, AR, USA；Lane Department of Computer Science；Electrical Engineering, West Virginia University, Morgantown, WV, USA；Department of Computer Science；Engineering, Princeton University, Princeton, NJ, USA；Department of Computer Sciences, University of Wisconsin--Madison, Madison, WI, USA
Re$^3$Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning
Taobao & Tmall Group of Alibaba（阿里巴巴淘宝和天猫集团）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
RACap: Relation-Aware Prompting for Lightweight Retrieval-Augmented Image Captioning
School of biological science and medical engineering, Southeast University, China（生物科学与医学工程学院，东南大学，中国）；Department of Neurosurgery, The second affiliated hospital of Xinjiang Medical University, China（神经外科部门，新疆医科大学第二附属医院，中国）
DualCap: Enhancing Lightweight Image Captioning via Dual Retrieval with Similar Scenes Visual Prompts
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）
Soochow University（苏州大学）；Peking University（北京大学）；Hong Kong Polytechnic University（香港理工大学）
An outstanding image-text retrieval model depends on high-quality labeled data. While the builders of existing image-text retrieval datasets strive to ensure that the caption matches the linked image, they cannot prevent a caption from fitting other images. We observe that such a many-to-many matching phenomenon is quite common in the widely-used retrieval datasets, where one caption can describe up to 178 images. These large matching-lost data not only confuse the model in training but also weaken the evaluation accuracy. Inspired by visual and textual entailment tasks, we propose a multi-mod…
There is growing interest in searching for information from large video corpora. Prior works have studied relevant tasks, such as text-based video retrieval, moment retrieval, video summarization, and video captioning in isolation, without an end-to-end setup that can jointly search from video corpora and generate summaries. Such an end-to-end setup would allow for many interesting applications, e.g., a text-based search that finds a relevant video from a video corpus, extracts the most relevant moment from that video, and segments the moment into important steps with captions. To address this…
The University of Sydney（悉尼大学）；Baidu Inc.（百度公司）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai AI Laboratory（上海人工智能实验室）
Most existing text-video retrieval methods focus on cross-modal matching between the visual content of videos and textual query sentences. However, in real-world scenarios, online videos are often accompanied by relevant text information such as titles, tags, and even subtitles, which can be utilized to match textual queries. This insight has motivated us to propose a novel approach to text-video retrieval, where we directly generate associated captions from videos using zero-shot video captioning with knowledge from web-scale pre-trained models (e.g., CLIP and GPT-2). Given the generated capt…
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…
LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts
East China Normal University Shanghai China；Peking University \& Zhongguancun Academy Beijing China；Huazhong University of Science；Beihang University Beijing China；Peking University Beijing China；East China Normal University；Peking University \& Zhongguancun Academy；Beihang University；Peking University
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…
Visual Lifelog Retrieval through Captioning-Enhanced Interpretation
Department of Computer Science；Information Engineering National Taiwan University Taipei, Taiwan；Department of Computer Science National Yang Ming Chiao Tung University Hsinchu, Taiwan；Institute of Information Science Academia Sinica Taipei, Taiwan；Information Engineering AI Research Center (AINTU) National Taiwan University Taipei, Taiwan
Australian AI Institute（澳大利亚人工智能研究所）；University of Technology Sydney（悉尼科技大学）
Existing multi-style image captioning methods show promising results in generating a caption with accurate visual content and desired linguistic style. However, existing methods overlook the relationship between linguistic style and visual content. To overcome this drawback, we propose style-aware contrastive learning for multi-style image captioning. First, we present a style-aware visual encoder with contrastive learning to mine potential visual content relevant to style. Moreover, we propose a style-aware triplet contrast objective to distinguish whether the image, style and caption matched…
