The heterogeneity gap problem is the main challenge in cross-modal retrieval. Because cross-modal data (e.g. audiovisual) have different distributions and representations that cannot be directly compared. To bridge the gap between audiovisual modalities, we learn a common subspace for them by utilizing the intrinsic correlation in the natural synchronization of audio-visual data with the aid of annotated labels. TNN-CCCA is the best audio-visual cross-modal retrieval (AV-CMR) model so far, but the model training is sensitive to hard negative samples when learning common subspace by applying triplet loss to predict the relative distance between inputs. In this paper, to reduce the interference of hard negative samples in representation learning, we propose a new AV-CMR model to optimize semantic features by directly predicting labels and then measuring the intrinsic correlation between audio-visual data using complete cross-triple loss. In particular, our model projects audio-visual features into label space by minimizing the distance between predicted label features after feature projection and ground label representations. Moreover, we adopt complete cross-triplet loss to optimize the predicted label features by leveraging the relationship between all possible similarity and dissimilarity semantic information across modalities. The extensive experimental results on two audio-visual double-checked datasets have shown an improvement of approximately 2.1% in terms of average MAP over the current state-of-the-art method TNN-CCCA for the AV-CMR task, which indicates the effectiveness of our proposed model.
University of Tübingen（蒂宾根大学）；MPI for Informatics（马克斯·普朗克信息学研究所）；Tencent PCG（腾讯平台与内容事业群）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Having access to multi-modal cues (e.g. vision and audio) empowers some cognitive tasks to be done faster compared to learning from a single modality. In this work, we propose to transfer knowledge across heterogeneous modalities, even though these data modalities may not be semantically correlated. Rather than directly aligning the representations of different modalities, we compose audio, image, and video representations across modalities to uncover richer multi-modal knowledge. Our main idea is to learn a compositional embedding that closes the cross-modal semantic gap and captures the task…
Cross-modal retrieval aims to retrieve data in one modality by a query in another modality, which has been a very interesting research issue in the field of multimedia, information retrieval, and computer vision, and database. Most existing works focus on cross-modal retrieval between text-image, text-video, and lyrics-audio.Little research addresses cross-modal retrieval between audio and video due to limited audio-video paired datasets and semantic information. The main challenge of audio-visual cross-modal retrieval task focuses on learning joint embeddings from a shared subspace for comput…
Learning common subspace is prevalent way in cross-modal retrieval to solve the problem of data from different modalities having inconsistent distributions and representations that cannot be directly compared. Previous cross-modal retrieval methods focus on projecting the cross-modal data into a common space by learning the correlation between them to bridge the modality gap. However, the rich semantic information in the video and the heterogeneous nature of audio-visual data leads to more serious heterogeneous gaps intuitively, which may lead to the loss of key semantic content of video with …
Learning to Unify Audio, Visual and Text for Audio-Enhanced Multilingual Visual Answer Localization
Systems Engineering Institute（系统工程研究所）；Xi’an Jiaotong University（西安交通大学）；Shenzhen Institute of Advanced Technology（深圳先进技术研究院）；Chinese Academy of Sciences（中国科学院）
Deep learning has successfully shown excellent performance in learning joint representations between different data modalities. Unfortunately, little research focuses on cross-modal correlation learning where temporal structures of different data modalities, such as audio and video, should be taken into account. Music video retrieval by given musical audio is a natural way to search and interact with music contents. In this work, we study cross-modal music video retrieval in terms of emotion similarity. Particularly, audio of an arbitrary length is used to retrieve a longer or full-length musi…
Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences（中国科学院西安光学精密机械研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Northwestern Polytechnical University（西北工业大学）
Audio is the main form for the visually impaired to obtain information. In reality, all kinds of visual data always exist, but audio data does not exist in many cases. In order to help the visually impaired people to better perceive the information around them, an image-to-audio-description (I2AD) task is proposed to generate audio descriptions from images in this paper. To complete this totally new task, a modal translation network (MT-Net) from visual to auditory sense is proposed. The proposed MT-Net includes three progressive sub-networks: 1) feature learning, 2) cross-modal mapping, and 3…
Cross-modal audio-visual perception has been a long-lasting topic in psychology and neurology, and various studies have discovered strong correlations in human perception of auditory and visual stimuli. Despite works in computational multimodal modeling, the problem of cross-modal audio-visual generation has not been systematically studied in the literature. In this paper, we make the first attempt to solve this cross-modal generation problem leveraging the power of deep generative adversarial training. Specifically, we use conditional generative adversarial networks to achieve cross-modal aud…
EAR: Enhancing Uni-Modal Representations for Weakly Supervised Audio-Visual Video Parsing
School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications（智能工程与自动化学院，北京邮电大学）；State Grid Corporation of China（国家电网公司）；School of Artificial Intelligence, Beijing University of Posts and Telecommunications（人工智能学院，北京邮电大学）
Indian Institute of Technology Ropar（印度理工学院罗帕尔分校）；Monash University（莫纳什大学）
We propose detection of deepfake videos based on the dissimilarity between the audio and visual modalities, termed as the Modality Dissonance Score (MDS). We hypothesize that manipulation of either modality will lead to dis-harmony between the two modalities, eg, loss of lip-sync, unnatural facial and lip movements, etc. MDS is computed as an aggregate of dissimilarity scores between audio and visual segments in a video. Discriminative features are learnt for the audio and visual channels in a chunk-wise manner, employing the cross-entropy loss for individual modalities, and a contrastive loss…
Indian Institute of Technology, Bombay（印度理工学院孟买分校）
We focus on the audio-visual video parsing (AVVP) problem that involves detecting audio and visual event labels with temporal boundaries. The task is especially challenging since it is weakly supervised with only event labels available as a bag of labels for each video. An existing state-of-the-art model for AVVP uses a hybrid attention network (HAN) to generate cross-modal features for both audio and visual modalities, and an attentive pooling module that aggregates predicted audio and visual segment-level event probabilities to yield video-level event probabilities. We provide a detailed ana…
Weakly-supervised audio-visual violence detection aims to distinguish snippets containing multimodal violence events with video-level labels. Many prior works perform audio-visual integration and interaction in an early or intermediate manner, yet overlooking the modality heterogeneousness over the weakly-supervised setting. In this paper, we analyze the modality asynchrony and undifferentiated instances phenomena of the multiple instance learning (MIL) procedure, and further investigate its negative impact on weakly-supervised audio-visual learning. To address these issues, we propose a modal…
AVRT: Audio-Visual Reasoning Transfer through Single-Modality Teachers
University of Tübingen, Germany（图宾根大学）；MIT, Cambridge MA, USA（麻省理工学院）；IBM Research, USA（IBM研究院）；MIT-IBM Watson AI Lab, USA（麻省理工-IBM沃森人工智能实验室）；Tuebingen AI Center, Germany（图宾根人工智能中心）
VGGSounder: Audio-Visual Evaluations for Foundation Models
Technical University of Munich, MCML（慕尼黑技术大学，MCML）；University of Tübingen（图宾根大学）；Tübingen AI Center（图宾根人工智能中心）；MPI for Intelligent Systems, ELLIS Institute（智能系统Max Planck研究所，ELLIS研究所）
Audio-visual learning helps to comprehensively understand the world by fusing practical information from multiple modalities. However, recent studies show that the imbalanced optimization of uni-modal encoders in a joint-learning model is a bottleneck to enhancing the model's performance. We further find that the up-to-date imbalance-mitigating methods fail on some audio-visual fine-grained tasks, which have a higher demand for distinguishable feature distribution. Fueled by the success of cosine loss that builds hyperspherical feature spaces and achieves lower intra-class angular variability,…
Active speaker detection in videos addresses associating a source face, visible in the video frames, with the underlying speech in the audio modality. The two primary sources of information to derive such a speech-face relationship are i) visual activity and its interaction with the speech signal and ii) co-occurrences of speakers' identities across modalities in the form of face and speech. The two approaches have their limitations: the audio-visual activity models get confused with other frequently occurring vocal activities, such as laughing and chewing, while the speakers' identity-based m…
A Unified Framework for Modality-Agnostic Deepfakes Detection
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空间安全学院）；University at Buffalo, State University of New York（纽约州立大学布法罗分校）；RealAI Inc（RealAI公司）
This paper aims to test whether a multi-modal approach for music emotion recognition (MER) performs better than a uni-modal one on high-level song features and lyrics. We use 11 song features retrieved from the Spotify API, combined lyrics features including sentiment, TF-IDF, and Anew to predict valence and arousal (Russell, 1980) scores on the Deezer Mood Detection Dataset (DMDD) (Delbouys et al., 2018) with 4 different regression models. We find that out of the 11 high-level song features, mainly 5 contribute to the performance, multi-modal features do better than audio alone when predictin…
Austrian Institute of Technology（奥地利技术研究所）；TU Wien（维也纳工业大学）
We present an approach to unsupervised audio representation learning. Based on a triplet neural network architecture, we harnesses semantically related cross-modal information to estimate audio track-relatedness. By applying Latent Semantic Indexing (LSI) we embed corresponding textual information into a latent vector space from which we derive track relatedness for online triplet selection. This LSI topic modelling facilitates fine-grained selection of similar and dissimilar audio-track pairs to learn the audio representation using a Convolution Recurrent Neural Network (CRNN). By this we dir…
Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillation
Columbia University（哥伦比亚大学）；University of Washington（华盛顿大学）
Information Technologies Institute, CERTH（希腊研究与技术基金会信息技术研究所）；Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）
In this work, we address the problem of audio-based near-duplicate video retrieval. We propose the Audio Similarity Learning (AuSiL) approach that effectively captures temporal patterns of audio similarity between video pairs. For the robust similarity calculation between two videos, we first extract representative audio-based video descriptors by leveraging transfer learning based on a Convolutional Neural Network (CNN) trained on a large scale dataset of audio events, and then we calculate the similarity matrix derived from the pairwise similarity of these descriptors. The similarity matrix …
University of Science and Technology of China（中国科学技术大学）；Tencent Corporation（腾讯公司）；Georgia Institute of Technology（佐治亚理工学院）；The Chinese University of Hong Kong（香港中文大学）；University of Enna Kore（恩纳科雷大学）
In this paper, we propose two techniques, namely joint modeling and data augmentation, to improve system performances for audio-visual scene classification (AVSC). We employ pre-trained networks trained only on image data sets to extract video embedding; whereas for audio embedding models, we decide to train them from scratch. We explore different neural network architectures for joint modeling to effectively combine the video and audio modalities. Moreover, data augmentation strategies are investigated to increase audio-visual training set size. For the video modality the effectiveness of sev…
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）
Pre-training technique has gained tremendous success in enhancing model performance on various tasks, but found to perform worse than training from scratch in some uni-modal situations. This inspires us to think: are the pre-trained models always effective in the more complex multi-modal scenario, especially for the heterogeneous modalities such as audio and visual ones? We find that the answer is No. Specifically, we explore the effects of pre-trained models on two audio-visual learning scenarios: cross-modal initialization and multi-modal joint learning. When cross-modal initialization is ap…
Nanyang Technological University（南洋理工大学）；ZJU-Hangzhou Global Scientific and Technological Innovation Center（浙江大学杭州国际科创中心）；Zhejiang University（浙江大学）
Audio-visual speech recognition (AVSR) has gained remarkable success for ameliorating the noise-robustness of speech recognition. Mainstream methods focus on fusing audio and visual inputs to obtain modality-invariant representations. However, such representations are prone to over-reliance on audio modality as it is much easier to recognize than video modality in clean conditions. As a result, the AVSR model underestimates the importance of visual stream in face of noise corruption. To this end, we leverage visual modality-specific representations to provide stable complementary information f…
As audio-visual systems are being deployed for safety-critical tasks such as surveillance and malicious content filtering, their robustness remains an under-studied area. Existing published work on robustness either does not scale to large-scale dataset, or does not deal with multiple modalities. This work aims to study several key questions related to multi-modal learning through the lens of robustness: 1) Are multi-modal models necessarily more robust than uni-modal models? 2) How to efficiently measure the robustness of multi-modal learning? 3) How to fuse different modalities to achieve a …
IIT Kanpur（印度理工学院坎普尔分校）；University of Warwick（华威大学）；NEC Labs America（NEC美国实验室）
We present an audio-visual multimodal approach for the task of zeroshot learning (ZSL) for classification and retrieval of videos. ZSL has been studied extensively in the recent past but has primarily been limited to visual modality and to images. We demonstrate that both audio and visual modalities are important for ZSL for videos. Since a dataset to study the task is currently not available, we also construct an appropriate multimodal dataset with 33 classes containing 156,416 videos, from an existing large scale audio event dataset. We empirically show that the performance improves by addin…
In this paper we propose a multi-modal multi-correlation learning framework targeting at the task of audio-visual speech separation. Although previous efforts have been extensively put on combining audio and visual modalities, most of them solely adopt a straightforward concatenation of audio and visual features. To exploit the real useful information behind these two modalities, we define two key correlations which are: (1) identity correlation (between timbre and facial attributes); (2) phonetic correlation (between phoneme and lip motion). These two correlations together comprise the comple…
Cross-modal representation learning allows to integrate information from different modalities into one representation. At the same time, research on generative models tends to focus on the visual domain with less emphasis on other domains, such as audio or text, potentially missing the benefits of shared representations. Studies successfully linking more than one modality in the generative setting are rare. In this context, we verify the possibility to train variational autoencoders (VAEs) to reconstruct image archetypes from audio data. Specifically, we consider VAEs in an adversarial trainin…
Pay More Attention To Audio: Mitigating Imbalance of Cross-Modal Attention in Large Audio Language Models
1Laboratory of Cognitive Computing；Application, College of Intelligence；Computing, Tianjin University, Tianjin, China 2School of Computer Science, Shanghai Jiao Tong University, Shanghai, China 3School of Electrical \& Electronic Engineering, Nanyang Technological University, Singapore 4Huiyan Technology (Tianjin) Co., Ltd, Tianjin, China
A major challenge in text-video and text-audio retrieval is the lack of large-scale training data. This is unlike image-captioning, where datasets are in the order of millions of samples. To close this gap we propose a new video mining pipeline which involves transferring captions from image captioning datasets to video clips with no additional manual effort. Using this pipeline, we create a new large-scale, weakly labelled audio-video captioning dataset consisting of millions of paired clips and captions. We show that training a multimodal transformed based model on this data achieves competi…
