Challenges in cross-learning involve inhomogeneous or even inadequate amount of training data and lack of resources for retraining large pretrained models. Inspired by transfer learning techniques in NLP, adapters and prefix tuning, this paper presents a new model-agnostic plugin architecture for cross-learning, called CM3T, that adapts transformer-based models to new or missing information. We introduce two adapter blocks: multi-head vision adapters for transfer learning and cross-attention adapters for multimodal learning. Training becomes substantially efficient as the backbone and other plugins do not need to be finetuned along with these additions. Comparative and ablation studies on three datasets Epic-Kitchens-100, MPIIGroupInteraction and UDIVA v0.5 show efficacy of this framework on different recording settings and tasks. With only 12.8% trainable parameters compared to the backbone to process video input and only 22.3% trainable parameters for two additional modalities, we achieve comparable and even better results than the state-of-the-art. CM3T has no specific requirements for training or pretraining and is a step towards bridging the gap between a general model and specific practical applications of video classification.
Ochanomizu University（御茶水女子大学）；The University of Tokyo（东京大学）；Keio University（庆应义塾大学）
This paper introduces a new video-and-language dataset with human actions for multimodal logical inference, which focuses on intentional and aspectual expressions that describe dynamic human actions. The dataset consists of 200 videos, 5,554 action labels, and 1,942 action triplets of the form <subject, predicate, object> that can be translated into logical semantic representations. The dataset is expected to be useful for evaluating multimodal inference systems between videos and semantically complicated sentences including negation and quantification.
We present a new dataset with annotated eye movements. The dataset consists of over 800,000 gaze points recorded during a car ride in the real world and in the simulator. In total, the eye movements of 19 subjects were annotated. In this dataset there are several data sources such as the eyelid closure, the pupil center, the optical vector, and a vector into the pupil center starting from the center of the eye corners. These different data sources are analyzed and evaluated individually as well as in combination with respect to their goodness of fit for eye movement classification. These resul…
Due to the high complexity and occlusion, insufficient perception in the crowded urban intersection can be a serious safety risk for both human drivers and autonomous algorithms, whereas CVIS (Cooperative Vehicle Infrastructure System) is a proposed solution for full-participants perception in this scenario. However, the research on roadside multimodal perception is still in its infancy, and there is no open-source dataset for such scenario. Accordingly, this paper fills the gap. Through an IPS (Intersection Perception System) installed at the diagonal of the intersection, this paper proposes …
GAViD: A Large-Scale Multimodal Dataset for Context-Aware Group Affect Recognition from Videos
Department of Computer Science and Engineering, Indian Institute of Technology Roorkee（计算机科学与工程系，印度理工学院Roorkee分校）；Indian Institute of Technology Ropar（印度理工学院Ropar分校）；Zhejiang University（浙江大学）；University of Oulu（奥卢大学）
Remote Sensing Technology Institute, German Aerospace Center（德国航空航天中心遥感技术研究所）；Technical University of Munich（慕尼黑工业大学）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；INRIA（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔理工学院）
As remote sensing (RS) data obtained from different sensors become available largely and openly, multimodal data processing and analysis techniques have been garnering increasing interest in the RS and geoscience community. However, due to the gap between different modalities in terms of imaging sensors, resolutions, and contents, embedding their complementary information into a consistent, compact, accurate, and discriminative representation, to a great extent, remains challenging. To this end, we propose a shared and specific feature learning (S2FL) model. S2FL is capable of decomposing mult…
MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
University of Washington（华盛顿大学）；Salesforce Research（Salesforce研究院）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Stanford University（斯坦福大学）；University of California, Berkeley（加州大学伯克利分校）
In multimodal assistant, where vision is also one of the input modalities, the identification of user intent becomes a challenging task as visual input can influence the outcome. Current digital assistants take spoken input and try to determine the user intent from conversational or device context. So, a dataset, which includes visual input (i.e. images or videos for the corresponding questions targeted for multimodal assistant use cases, is not readily available. The research in visual question answering (VQA) and visual question generation (VQG) is a great step forward. However, they do not …
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；University of Southern California（南加利福尼亚大学）；Intuit Inc.（英图伊特公司）；Chan Zuckerberg Initiative（陈·扎克伯格倡议）
We introduce a new dataset, MELINDA, for Multimodal biomEdicaL experImeNt methoD clAssification. The dataset is collected in a fully automated distant supervision manner, where the labels are obtained from an existing curated database, and the actual contents are extracted from papers associated with each of the records in the database. We benchmark various state-of-the-art NLP and computer vision models, including unimodal models which only take either caption texts or images as inputs, and multimodal models. Extensive experiments and analysis show that multimodal models, despite outperformin…
University of Nantong（南通大学）；Nanjing University of Science and Technology（南京理工大学）
Multimodal emotion analysis performed better in emotion recognition depending on more comprehensive emotional clues and multimodal emotion dataset. In this paper, we developed a large multimodal emotion dataset, named "HED" dataset, to facilitate the emotion recognition task, and accordingly propose a multimodal emotion recognition method. To promote recognition accuracy, "Feature After Feature" framework was used to explore crucial emotional information from the aligned face, body and text samples. We employ various benchmarks to evaluate the "HED" dataset and compare the performance with our…
Collaborative learning is an educational approach that enhances learning through shared goals and working together. Interaction and regulation are two essential factors related to the success of collaborative learning. Since the information from various modalities can reflect the quality of collaboration, a new multimodal dataset with cognitive and emotional triggers is introduced in this paper to explore how regulations affect interactions during the collaborative process. Specifically, a learning task with intentional interventions is designed and assigned to high school students aged 15 yea…
Multimodal machine learning algorithms aim to learn visual-textual correspondences. Previous work suggests that concepts with concrete visual manifestations may be easier to learn than concepts with abstract ones. We give an algorithm for automatically computing the visual concreteness of words and topics within multimodal datasets. We apply the approach in four settings, ranging from image captions to images/text scraped from historical books. In addition to enabling explorations of concepts in multimodal datasets, our concreteness scores predict the capacity of machine learning algorithms to…
Orange Labs（法国电信Orange实验室）；Université Caen Normandie（卡昂诺曼底大学）；Samsung AI Centre（三星人工智能中心）
We tackle the problem of finding good architectures for multimodal classification problems. We propose a novel and generic search space that spans a large number of possible fusion architectures. In order to find an optimal architecture for a given dataset in the proposed search space, we leverage an efficient sequential model-based exploration approach that is tailored for the problem. We demonstrate the value of posing multimodal fusion as a neural architecture search problem by extensive experimentation on a toy dataset and two other real multimodal datasets. We discover fusion architecture…
ProMQA-Assembly: Multimodal Procedural QA Dataset on Assembly
Language Technologies Institute, Carnegie Mellon University（卡内基梅隆大学语言技术研究所）；National Institute of Advanced Industrial Science and Technology (AIST)（国立研究开发法人产业技术综合研究所（AIST））
Understanding and reasoning about cooking recipes is a fruitful research direction towards enabling machines to interpret procedural text. In this work, we introduce RecipeQA, a dataset for multimodal comprehension of cooking recipes. It comprises of approximately 20K instructional recipes with multiple modalities such as titles, descriptions and aligned set of images. With over 36K automatically generated question-answer pairs, we design a set of comprehension and reasoning tasks that require joint understanding of images and text, capturing the temporal flow of events and making sense of pro…
The milestone improvements brought about by deep representation learning and pre-training techniques have led to large performance gains across downstream NLP, IR and Vision tasks. Multimodal modeling techniques aim to leverage large high-quality visio-linguistic datasets for learning complementary information (across image and text modalities). In this paper, we introduce the Wikipedia-based Image Text (WIT) Dataset (https://github.com/google-research-datasets/wit) to better facilitate multimodal, multilingual learning. WIT is composed of a curated set of 37.6 million entity rich image-text e…
Research in massively multilingual image captioning has been severely hampered by a lack of high-quality evaluation datasets. In this paper we present the Crossmodal-3600 dataset (XM3600 in short), a geographically diverse set of 3600 images annotated with human-generated reference captions in 36 languages. The images were selected from across the world, covering regions where the 36 languages are spoken, and annotated with captions that achieve consistency in terms of style across all languages, while avoiding annotation artifacts due to direct translation. We apply this benchmark to model se…
EmoMeta: A Multimodal Dataset for Fine-grained Emotion Classification in Chinese Metaphors
School of Software（软件学院）；Dalian University of Technology（大连理工大学）；School of Foreign Languages and School of Software（外语学院和软件学院）；Faculty of Business Administration（商学院）；University of Macau（澳门大学）；School of Computing Technologies（计算技术学院）；RMIT University（皇家墨尔本理工大学）
University of Maryland, College Park（马里兰大学帕克分校）；ShareChat
We present 3MASSIV, a multilingual, multimodal and multi-aspect, expertly-annotated dataset of diverse short videos extracted from short-video social media platform - Moj. 3MASSIV comprises of 50k short videos (20 seconds average duration) and 100K unlabeled videos in 11 different languages and captures popular short video trends like pranks, fails, romance, comedy expressed via unique audio-visual formats like self-shot videos, reaction videos, lip-synching, self-sung songs, etc. 3MASSIV presents an opportunity for multimodal and multilingual semantic understanding on these unique videos by a…
Lecture slide presentations, a sequence of pages that contain text and figures accompanied by speech, are constructed and presented carefully in order to optimally transfer knowledge to students. Previous studies in multimedia and psychology attribute the effectiveness of lecture presentations to their multimodal nature. As a step toward developing AI to aid in student learning as intelligent teacher assistants, we introduce the Multimodal Lecture Presentations dataset as a large-scale benchmark testing the capabilities of machine learning models in multimodal understanding of educational cont…
Microsoft（微软）；Microsoft Research Asia（微软亚洲研究院）；Southwest Jiaotong University（西南交通大学）；ShanghaiTech University（上海科技大学）
In this paper, we present GEM as a General Evaluation benchmark for Multimodal tasks. Different from existing datasets such as GLUE, SuperGLUE, XGLUE and XTREME that mainly focus on natural language tasks, GEM is a large-scale vision-language benchmark, which consists of GEM-I for image-language tasks and GEM-V for video-language tasks. Comparing with existing multimodal datasets such as MSCOCO and Flicker30K for image-language tasks, YouCook2 and MSR-VTT for video-language tasks, GEM is not only the largest vision-language dataset covering image-language tasks and video-language tasks at the …
TIB – Leibniz Information Centre for Science and Technology（莱布尼茨科技信息中心（TIB））；L3S Research Center, Leibniz University Hannover（汉诺威莱布尼茨大学L3S研究中心）；Jozef Stefan Institute（约瑟夫·斯特凡研究所）
In recent years, the problem of misinformation on the web has become widespread across languages, countries, and various social media platforms. Although there has been much work on automated fake news detection, the role of images and their variety are not well explored. In this paper, we investigate the roles of image and text at an earlier stage of the fake news detection pipeline, called claim detection. For this purpose, we introduce a novel dataset, MM-Claims, which consists of tweets and corresponding images over three topics: COVID-19, Climate Change and broadly Technology. The dataset…
To enhance research on multimodal knowledge base and multimodal information processing, we propose a new task called multimodal entity tagging (MET) with a multimodal knowledge base (MKB). We also develop a dataset for the problem using an existing MKB. In an MKB, there are entities and their associated texts and images. In MET, given a text-image pair, one uses the information in the MKB to automatically identify the related entity in the text-image pair. We solve the task by using the information retrieval paradigm and implement several baselines using state-of-the-art methods in NLP and CV.…
University of Amsterdam（阿姆斯特丹大学）；Google Research（谷歌研究院）；DUniversum（3DUniversum）
Multimodal large-scale datasets for outdoor scenes are mostly designed for urban driving problems. The scenes are highly structured and semantically different from scenarios seen in nature-centered scenes such as gardens or parks. To promote machine learning methods for nature-oriented applications, such as agriculture and gardening, we propose the multimodal synthetic dataset for Enclosed garDEN scenes (EDEN). The dataset features more than 300K images captured from more than 100 garden models. Each image is annotated with various low/high-level vision modalities, including semantic segmentat…
