Modality-Balanced Learning for Multimedia Recommendation
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Jinghao Zhang, Guofan Liu, Qiang Liu, Shu Wu, Liang Wang
Many recommender models have been proposed to investigate how to incorporate multimodal content information into traditional collaborative filtering framework effectively. The use of multimodal information is expected to provide more comprehensive information and lead to superior performance. However, the integration of multiple modalities often encounters the modal imbalance problem: since the information in different modalities is unbalanced, optimizing the same objective across all modalities leads to the under-optimization problem of the weak modalities with a slower convergence rate or lower performance. Even worse, we find that in multimodal recommendation models, all modalities suffer from the problem of insufficient optimization. To address these issues, we propose a Counterfactual Knowledge Distillation method that could solve the imbalance problem and make the best use of all modalities. Through modality-specific knowledge distillation, it could guide the multimodal model to learn modality-specific knowledge from uni-modal teachers. We also design a novel generic-and-specific distillation loss to guide the multimodal student to learn wider-and-deeper knowledge from teachers. Additionally, to adaptively recalibrate the focus of the multimodal model towards weaker modalities during training, we estimate the causal effect of each modality on the training objective using counterfactual inference techniques, through which we could determine the weak modalities, quantify the imbalance degree and re-weight the distillation loss accordingly. Our method could serve as a plug-and-play module for both late-fusion and early-fusion backbones. Extensive experiments on six backbones show that our proposed method can improve the performance by a large margin. The source code will be released at \url{https://github.com/CRIPAC-DIG/Balanced-Multimodal-Rec}
We present a new publicly available dataset with the goal of advancing multi-modality learning by offering vision and language data within the same context. This is achieved by obtaining data from a social media website with posts containing multiple paired images/videos and text, along with comment trees containing images/videos and/or text. With a total of 677k posts, 2.9 million post images, 488k post videos, 1.4 million comment images, 4.6 million comment videos, and 96.9 million comments, data from different modalities can be jointly used to improve performances for a variety of tasks suc…
Nanyang Technological University, Singapore（新加坡南洋理工大学）；DSO National Laboratories, Singapore（新加坡国防科技研究院）
Detecting deception by human behaviors is vital in many fields such as custom security and multimedia anti-fraud. Recently, audio-visual deception detection attracts more attention due to its better performance than using only a single modality. However, in real-world multi-modal settings, the integrity of data can be an issue (e.g., sometimes only partial modalities are available). The missing modality might lead to a decrease in performance, but the model still learns the features of the missed modality. In this paper, to further improve the performance and overcome the missing modality prob…
Balanced Diffusion-Guided Fusion for Multimodal Remote Sensing Classification
Department of Information Engineering and Computer Science, University of Trento（特伦托大学信息工程与计算机科学系）；College of Electrical and Information Engineering, Hunan University（湖南大学电气与信息工程学院）；Key Laboratory of Collaborative Intelligent Systems of Ministry of Education, Xidian University（西安电子科技大学教育部协同智能系统重点实验室）；School of Electronic Engineering, Xidian University（西安电子科技大学电子工程学院）；Academy of Artificial Intelligence, Inner Mongolia Normal University（内蒙古师范大学人工智能学院）
Modality-Collaborative Transformer with Hybrid Feature Reconstruction for Robust Emotion Recognition
Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences（中国科学院声学研究所语音声学与内容理解重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）
Multimodality Invariant Learning for Multimedia-Based New Item Recommendation
Hefei University of Technology（合肥工业大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）；Academy of Cyber（网络空间研究院）；Institute of Artificial Intelligence（人工智能研究院）
Qatar Computing Research Institute（卡塔尔计算研究所）；Hamad Bin Khalifa University（哈马德·本·哈利法大学）
Multimedia content in social media platforms provides significant information during disaster events. The types of information shared include reports of injured or deceased people, infrastructure damage, and missing or found people, among others. Although many studies have shown the usefulness of both text and image content for disaster response purposes, the research has been mostly focused on analyzing only the text modality in the past. In this paper, we propose to use both text and image modalities of social media data to learn a joint representation using state-of-the-art deep learning te…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Recent years have witnessed growing interests in multimedia recommendation, which aims to predict whether a user will interact with an item with multimodal contents. Previous studies focus on modeling user-item interactions with multimodal features included as side information. However, this scheme is not well-designed for multimedia recommendation. Firstly, only collaborative item-item relationships are implicitly modeled through high-order item-user-item co-occurrences. We argue that the latent semantic item-item structures underlying these multimodal contents could be beneficial for learnin…
Accurately matching visual and textual data in cross-modal retrieval has been widely studied in the multimedia community. To address these challenges posited by the heterogeneity gap and the semantic gap, we propose integrating Shannon information theory and adversarial learning. In terms of the heterogeneity gap, we integrate modality classification and information entropy maximization adversarially. For this purpose, a modality classifier (as a discriminator) is built to distinguish the text and image modalities according to their different statistical properties. This discriminator uses its…
MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Peking University（北京大学）；Shandong Normal University（山东师范大学）；Renmin University of China（中国人民大学）；Ant Group（蚂蚁集团）；Nanyang Technological University（南洋理工大学）；University of Oulu（奥卢大学）
Video search has become the main routine for users to discover videos relevant to a text query on large short-video sharing platforms. During training a query-video bi-encoder model using online search logs, we identify a modality bias phenomenon that the video encoder almost entirely relies on text matching, neglecting other modalities of the videos such as vision, audio. This modality imbalanceresults from a) modality gap: the relevance between a query and a video text is much easier to learn as the query is also a piece of text, with the same modality as the video text; b) data bias: most t…
Beyond Modality Collapse: Representations Blending for Multimodal Dataset Distillation
Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore（前沿人工智能研究中心，科技研究局，新加坡）；Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore（高性能计算研究所，科技研究局，新加坡）；National University of Singapore, Singapore（新加坡国立大学）；Zhejiang University, China（浙江大学）
National University of Singapore（新加坡国立大学）；Singapore University of Technology and Design（新加坡科技设计大学）；Goethe University Frankfurt（法兰克福大学）
Although media content is increasingly produced, distributed, and consumed in multiple combinations of modalities, how individual modalities contribute to the perceived emotion of a media item remains poorly understood. In this paper we present MusicVideos (MuVi), a novel dataset for affective multimedia content analysis to study how the auditory and visual modalities contribute to the perceived emotion of media. The data were collected by presenting music videos to participants in three conditions: music, visual, and audiovisual. Participants annotated the music videos for valence and arousal…
Multimodal datasets contain an enormous amount of relational information, which grows exponentially with the introduction of new modalities. Learning representations in such a scenario is inherently complex due to the presence of multiple heterogeneous information channels. These channels can encode both (a) inter-relations between the items of different modalities and (b) intra-relations between the items of the same modality. Encoding multimedia items into a continuous low-dimensional semantic space such that both types of relations are captured and preserved is extremely challenging, especi…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Artificial Intelligence Research, Chinese Academy of Sciences（中国科学院人工智能创新研究院）
Multimedia content is of predominance in the modern Web era. Investigating how users interact with multimodal items is a continuing concern within the rapid development of recommender systems. The majority of previous work focuses on modeling user-item interactions with multimodal features included as side information. However, this scheme is not well-designed for multimedia recommendation. Specifically, only collaborative item-item relationships are implicitly modeled through high-order item-user-item relations. Considering that items are associated with rich contents in multiple modalities, …
Informatics Institute University of Amsterdam Amsterdam The Netherlands；Informatics Institute University of Amsterdam
In this paper we present a novel interactive multimodal learning system, which facilitates search and exploration in large networks of social multimedia users. It allows the analyst to identify and select users of interest, and to find similar users in an interactive learning setting. Our approach is based on novel multimodal representations of users, words and concepts, which we simultaneously learn by deploying a general-purpose neural embedding model. We show these representations to be useful not only for categorizing users, but also for automatically generating user and community profiles…
