An objective understanding of media depictions, such as inclusive portrayals of how much someone is heard and seen on screen such as in film and television, requires the machines to discern automatically who, when, how, and where someone is talking, and not. Speaker activity can be automatically discerned from the rich multimodal information present in the media content. This is however a challenging problem due to the vast variety and contextual variability in the media content, and the lack of labeled data. In this work, we present a cross-modal neural network for learning visual representations, which have implicit information pertaining to the spatial location of a speaker in the visual frames. Avoiding the need for manual annotations for active speakers in visual frames, acquiring of which is very expensive, we present a weakly supervised system for the task of localizing active speakers in movie content. We use the learned cross-modal visual representations, and provide weak supervision from movie subtitles acting as a proxy for voice activity, thus requiring no manual annotations. We evaluate the performance of the proposed system on the AVA active speaker dataset and demonstrate the effectiveness of the cross-modal embeddings for localizing active speakers in comparison to fully supervised systems. We also demonstrate state-of-the-art performance for the task of voice activity detection in an audio-visual framework, especially when speech is accompanied by noise and music.
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…
King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）；Adobe Research（奥多比研究院）
Active speaker detection requires a solid integration of multi-modal cues. While individual modalities can approximate a solution, accurate predictions can only be achieved by explicitly fusing the audio and visual features and modeling their temporal progression. Despite its inherent muti-modal nature, current methods still focus on modeling and fusing short-term audiovisual features for individual speakers, often at frame level. In this paper we present a novel approach to active speaker detection that directly addresses the multi-modal nature of the problem, and provides a straightforward s…
In this paper, we show how to use audio to supervise the learning of active speaker detection in video. Voice Activity Detection (VAD) guides the learning of the vision-based classifier in a weakly supervised manner. The classifier uses spatio-temporal features to encode upper body motion - facial expressions and gesticulations associated with speaking. We further improve a generic model for active speaker detection by learning person specific models. Finally, we demonstrate the online adaptation of generic models learnt on one dataset, to previously unseen people in a new dataset, again using…
MoMuSE: Momentum Multi-modal Target Speaker Extraction for Real-time Scenarios with Impaired Visual Cues
The Hong Kong Polytechnic University（香港理工大学）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Key Laboratory of Machine Perception, Peking University, Shenzhen Graduate School（北京大学深圳研究生院机器感知重点实验室）；Computer Vision Lab, ETH Zurich（苏黎世联邦理工学院计算机视觉实验室）
Multi-modal fusion is proven to be an effective method to improve the accuracy and robustness of speaker tracking, especially in complex scenarios. However, how to combine the heterogeneous information and exploit the complementarity of multi-modal signals remains a challenging issue. In this paper, we propose a novel Multi-modal Perception Tracker (MPT) for speaker tracking using both audio and visual modalities. Specifically, a novel acoustic map based on spatial-temporal Global Coherence Field (stGCF) is first constructed for heterogeneous signal fusion, which employs a camera model to map …
Learning Speaker Identity Beyond Language and Modality Constraints: Insights from the POLY-SIM 2026 Challenge
Institute of Computational Perception, Johannes Kepler University（约翰内斯·开普勒大学计算感知研究所）；University of Michigan-Flint（密歇根大学弗林特分校）；BDO DIGITAL Gmbh（BDO数字有限公司）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Fortemedia（富特媒体公司）；College of Computing, Mohammed VI Polytechnic University（穆罕默德六世理工大学计算学院）；IT:U Interdisciplinary Transformation University（IT:U跨学科转型大学）；University of Augsburg（奥格斯堡大学）
We present a cross-modal unsupervised framework for active speaker detection in media content such as TV shows and movies. Machine learning advances have enabled impressive performance in identifying individuals from speech and facial images. We leverage speaker identity information from speech and faces, and formulate active speaker detection as a speech-face assignment task such that the active speaker's face and the underlying speech identify the same person (character). We express the speech segments in terms of their associated speaker identity distances, from all other speech segments, t…
Princeton University（普林斯顿大学）；University of Georgia（佐治亚大学）
For recognizing speakers in video streams, significant research studies have been made to obtain a rich machine learning model by extracting high-level speaker's features such as facial expression, emotion, and gender. However, generating such a model is not feasible by using only single modality feature extractors that exploit either audio signals or image frames, extracted from video streams. In this paper, we address this problem from a different perspective and propose an unprecedented multimodality data fusion framework called DeepMSRF, Deep Multimodal Speaker Recognition with Feature sel…
Though significant progress has been made for speaker-dependent Video-to-Speech (VTS) synthesis, little attention is devoted to multi-speaker VTS that can map silent video to speech, while allowing flexible control of speaker identity, all in a single system. This paper proposes a novel multi-speaker VTS system based on cross-modal knowledge transfer from voice conversion (VC), where vector quantization with contrastive predictive coding (VQCPC) is used for the content encoder of VC to derive discrete phoneme-like acoustic units, which are transferred to a Lip-to-Index (Lip2Ind) network to inf…
POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan
Institute of Computational Perception, Johannes Kepler University Linz, Austria（林茨约翰·开普勒大学计算感知研究所）；University of Michigan-Flint, USA（密歇根大学弗林特分校）；Sapienza University of Rome, Italy（罗马大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Fortemedia Singapore, Singapore（新加坡Fortemedia公司）；IT:U Interdisciplinary Transformation University Austria（奥地利跨学科转型大学）；University of Augsburg, Germany（奥格斯堡大学）；Human-centered AI Group, AI Lab, Linz Institute of Technology, Austria（奥地利林茨理工学院人工智能实验室人本人工智能组）
STNet: Deep Audio-Visual Fusion Network for Robust Speaker Tracking
College of Computer Science and Technology, Taiyuan University of Technology（太原理工大学计算机科学与技术学院）；Peking University（北京大学）；Westlake University（西湖大学）；Westlake Institute for Advanced Study（西湖高等研究院）
In this paper, we propose a multi-speaker face-to-speech waveform generation model that also works for unseen speaker conditions. Using a generative adversarial network (GAN) with linguistic and speaker characteristic features as auxiliary conditions, our method directly converts face images into speech waveforms under an end-to-end training framework. The linguistic features are extracted from lip movements using a lip-reading model, and the speaker characteristic features are predicted from face images using cross-modal learning with a pre-trained acoustic model. Since these two features are…
Speaker diarization is one of the critical components of computational media intelligence as it enables a character-level analysis of story portrayals and media content understanding. Automated audio-based speaker diarization of entertainment media poses challenges due to the diverse acoustic conditions present in media content, be it background music, overlapping speakers, or sound effects. At the same time, speaking faces in the visual modality provide complementary information and not prone to the errors seen in the audio modality. In this paper, we address the problem of speaker diarizatio…
Tianjin University（天津大学）；National Institute of Informatics（国立信息学研究所）
Visual speech (i.e., lip motion) is highly related to auditory speech due to the co-occurrence and synchronization in speech production. This paper investigates this correlation and proposes a cross-modal speech co-learning paradigm. The primary motivation of our cross-modal co-learning method is modeling one modality aided by exploiting knowledge from another modality. Specifically, two cross-modal boosters are introduced based on an audio-visual pseudo-siamese structure to learn the modality-transformed correlation. Inside each booster, a max-feature-map embedded Transformer variant is propo…
EgoAdapt: Enhancing Robustness in Egocentric Interactive Speaker Detection Under Missing Modalities
School of Computer and Communication Enngineering, University of Science and Technology Beijing（北京科技大学计算机与通信工程学院）；MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（民航大学模式分析与机器智能重点实验室，计算机科学与技术学院）；MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, College of Computer Science and Technology, Shenzhen Research Institute, Nanjing University of Aeronautics and Astronautics（民航大学模式分析与机器智能重点实验室，计算机科学与技术学院，深圳研究院）
Hefei University of Technology（合肥工业大学）；Anhui University（安徽大学）
Lipreading refers to understanding and further translating the speech of a speaker in the video into natural language. State-of-the-art lipreading methods excel in interpreting overlap speakers, i.e., speakers appear in both training and inference sets. However, generalizing these methods to unseen speakers incurs catastrophic performance degradation due to the limited number of speakers in training bank and the evident visual variations caused by the shape/color of lips for different speakers. Therefore, merely depending on the visible changes of lips tends to cause model overfitting. To addr…
University of Oxford（牛津大学）；Naver Corporation（Naver公司）
The objective of this paper is to learn representations of speaker identity without access to manually annotated data. To do so, we develop a self-supervised learning objective that exploits the natural cross-modal synchrony between faces and audio in video. The key idea behind our approach is to tease apart--without annotation--the representations of linguistic content and speaker identity. We construct a two-stream architecture which: (1) shares low-level features common to both representations; and (2) provides a natural mechanism for explicitly disentangling these factors, offering the pot…
Istituto Italiano di Tecnologia (IIT)（意大利技术研究院）；University of Insubria（因苏布里亚大学）；University of Engineering and Technology Taxila（塔克西拉工程技术大学）；Information Technology University（信息技术大学）
Recent years have seen a surge in finding association between faces and voices within a cross-modal biometric application along with speaker recognition. Inspired from this, we introduce a challenging task in establishing association between faces and voices across multiple languages spoken by the same set of persons. The aim of this paper is to answer two closely related questions: "Is face-voice association language independent?" and "Can a speaker be recognised irrespective of the spoken language?". These two questions are very important to understand effectiveness and to boost development …
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…
It is now well established from a variety of studies that there is a significant benefit from combining video and audio data in detecting active speakers. However, either of the modalities can potentially mislead audiovisual fusion by inducing unreliable or deceptive information. This paper outlines active speaker detection as a multi-objective learning problem to leverage best of each modalities using a novel self-attention, uncertainty-based multimodal fusion scheme. Results obtained show that the proposed multi-objective learning architecture outperforms traditional approaches in improving …
CoLM-DSR: Leveraging Neural Codec Language Modeling for Multi-Modal Dysarthric Speech Reconstruction
The Chinese University of Hong Kong（香港中文大学）；Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Vocal Engineering Technologies Limited（声动科技有限公司）
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）
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Stanford University（斯坦福大学）；Facebook AI Research（Facebook AI研究院）
We introduce a new approach for audio-visual speech separation. Given a video, the goal is to extract the speech associated with a face in spite of simultaneous background sounds and/or other human speakers. Whereas existing methods focus on learning the alignment between the speaker's lip movements and the sounds they generate, we propose to leverage the speaker's face appearance as an additional prior to isolate the corresponding vocal qualities they are likely to produce. Our approach jointly learns audio-visual speech separation and cross-modal speaker embeddings from unlabeled video. It y…
Tianjin University（天津大学）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；National University of Singapore（新加坡国立大学）；Japan Advanced Institute of Science and Technology（日本北陆先端科学技术大学院大学）
Speaker extraction seeks to extract the target speech in a multi-talker scenario given an auxiliary reference. Such reference can be auditory, i.e., a pre-recorded speech, visual, i.e., lip movements, or contextual, i.e., phonetic sequence. References in different modalities provide distinct and complementary information that could be fused to form top-down attention on the target speaker. Previous studies have introduced visual and contextual modalities in a single model. In this paper, we propose a two-stage time-domain visual-contextual speaker extraction network named VCSE, which incorpora…
University of Coimbra（科英布拉大学）；Institute of Systems and Robotics（系统与机器人研究所）
Human beings have developed fantastic abilities to integrate information from various sensory sources exploring their inherent complementarity. Perceptual capabilities are therefore heightened, enabling, for instance, the well-known "cocktail party" and McGurk effects, i.e., speech disambiguation from a panoply of sound signals. This fusion ability is also key in refining the perception of sound source location, as in distinguishing whose voice is being heard in a group conversation. Furthermore, neuroscience has successfully identified the superior colliculus region in the brain as the one re…
University of Toronto（多伦多大学）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；University of Maryland - Baltimore County（马里兰大学巴尔的摩县分校）
People can recognize scenes across many different modalities beyond natural images. In this paper, we investigate how to learn cross-modal scene representations that transfer across modalities. To study this problem, we introduce a new cross-modal scene dataset. While convolutional neural networks can categorize cross-modal scenes well, they also learn an intermediate representation not aligned across modalities, which is undesirable for cross-modal transfer applications. We present methods to regularize cross-modal convolutional neural networks so that they have a shared representation that i…
University of Oxford（牛津大学）；Naver Corporation（NAVER公司）
Our objective is an audio-visual model for separating a single speaker from a mixture of sounds such as other speakers and background noise. Moreover, we wish to hear the speaker even when the visual cues are temporarily absent due to occlusion. To this end we introduce a deep audio-visual speech enhancement network that is able to separate a speaker's voice by conditioning on both the speaker's lip movements and/or a representation of their voice. The voice representation can be obtained by either (i) enrollment, or (ii) by self-enrollment -- learning the representation on-the-fly given suffi…
Weakly Supervised Visible-Infrared Person Re-Identification via Heterogeneous Expert Collaborative Consistency Learning
Faculty of Information Engineering and Automation, Kunming University of Science and Technology（昆明理工大学信息工程与自动化学院）；School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）
In this paper we address the problem of tracking multiple speakers via the fusion of visual and auditory information. We propose to exploit the complementary nature of these two modalities in order to accurately estimate smooth trajectories of the tracked persons, to deal with the partial or total absence of one of the modalities over short periods of time, and to estimate the acoustic status -- either speaking or silent -- of each tracked person along time. We propose to cast the problem at hand into a generative audio-visual fusion (or association) model formulated as a latent-variable tempo…
Hangzhou Dianzi University（杭州电子科技大学）；Baidu Inc.（百度公司）；Zhejiang International Studies University（浙江外国语学院）
This paper proposes an approach to Dense Video Captioning (DVC) without pairwise event-sentence annotation. First, we adopt the knowledge distilled from relevant and well solved tasks to generate high-quality event proposals. Then we incorporate contrastive loss and cycle-consistency loss typically applied to cross-modal retrieval tasks to build semantic matching between the proposals and sentences, which are eventually used to train the caption generation module. In addition, the parameters of matching module are initialized via pre-training based on annotated images to improve the matching p…
Sun Yat-sen University（中山大学）；Beijing Jiaotong University（北京交通大学）；Alibaba Group（阿里巴巴集团）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Nowadays, customer's demands for E-commerce are more diversified, which introduces more complications to the product retrieval industry. Previous methods are either subject to single-modal input or perform supervised image-level product retrieval, thus fail to accommodate real-life scenarios where enormous weakly annotated multi-modal data are present. In this paper, we investigate a more realistic setting that aims to perform weakly-supervised multi-modal instance-level product retrieval among fine-grained product categories. To promote the study of this challenging task, we contribute Produc…
CmFNet: Cross-modal Fusion Network for Weakly-supervised Segmentation of Medical Images
School of Physics, Peking University（北京大学物理学院）；School of Computer Science, Peking University（北京大学计算机学院）；Department of Radiotherapy, Peking University Cancer Hospital（北京大学肿瘤医院放疗科）；Department of Radiation Oncology, Peking University Third Hospital（北京大学第三医院放疗科）
Nanjing University（南京大学）；SenseTime Research（商汤科技研究院）；CUHK - Sensetime Joint Lab（香港中文大学-商汤联合实验室）；Shanghai AI Laboratory（上海人工智能实验室）
This paper focuses on the weakly-supervised audio-visual video parsing task, which aims to recognize all events belonging to each modality and localize their temporal boundaries. This task is challenging because only overall labels indicating the video events are provided for training. However, an event might be labeled but not appear in one of the modalities, which results in a modality-specific noisy label problem. In this work, we propose a training strategy to identify and remove modality-specific noisy labels dynamically. It is motivated by two key observations: 1) networks tend to learn …
École de Technologie Supérieure（高等技术学院）；Purdue University（普渡大学）
Weakly supervised learning has emerged as an appealing alternative to alleviate the need for large labeled datasets in semantic segmentation. Most current approaches exploit class activation maps (CAMs), which can be generated from image-level annotations. Nevertheless, resulting maps have been demonstrated to be highly discriminant, failing to serve as optimal proxy pixel-level labels. We present a novel learning strategy that leverages self-supervision in a multi-modal image scenario to significantly enhance original CAMs. In particular, the proposed method is based on two observations. Firs…
University of British Columbia（不列颠哥伦比亚大学）；Vector Institute for AI（Vector人工智能研究所）
Multi-modal learning, particularly among imaging and linguistic modalities, has made amazing strides in many high-level fundamental visual understanding problems, ranging from language grounding to dense event captioning. However, much of the research has been limited to approaches that either do not take audio corresponding to video into account at all, or those that model the audio-visual correlations in service of sound or sound source localization. In this paper, we present the evidence, that audio signals can carry surprising amount of information when it comes to high-level visual-lingua…
We propose a new model for speaker naming in movies that leverages visual, textual, and acoustic modalities in an unified optimization framework. To evaluate the performance of our model, we introduce a new dataset consisting of six episodes of the Big Bang Theory TV show and eighteen full movies covering different genres. Our experiments show that our multimodal model significantly outperforms several competitive baselines on the average weighted F-score metric. To demonstrate the effectiveness of our framework, we design an end-to-end memory network model that leverages our speaker naming mo…
Sun Yat-sen University（中山大学）；Peng Cheng Laboratory（鹏城实验室）；Tencent PCG（腾讯平台与内容事业群）；HKUST（香港科技大学）；Pazhou Lab（琶洲实验室）
Weakly supervised temporal action localization (WS-TAL) is a challenging task that aims to localize action instances in the given video with video-level categorical supervision. Both appearance and motion features are used in previous works, while they do not utilize them in a proper way but apply simple concatenation or score-level fusion. In this work, we argue that the features extracted from the pretrained extractor, e.g., I3D, are not the WS-TALtask-specific features, thus the feature re-calibration is needed for reducing the task-irrelevant information redundancy. Therefore, we propose a…
Person identification in the wild is very challenging due to great variation in poses, face quality, clothes, makeup and so on. Traditional research, such as face recognition, person re-identification, and speaker recognition, often focuses on a single modal of information, which is inadequate to handle all the situations in practice. Multi-modal person identification is a more promising way that we can jointly utilize face, head, body, audio features, and so on. In this paper, we introduce iQIYI-VID, the largest video dataset for multi-modal person identification. It is composed of 600K video…
University of Amsterdam（阿姆斯特丹大学）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）
When speakers describe an image, they tend to look at objects before mentioning them. In this paper, we investigate such sequential cross-modal alignment by modelling the image description generation process computationally. We take as our starting point a state-of-the-art image captioning system and develop several model variants that exploit information from human gaze patterns recorded during language production. In particular, we propose the first approach to image description generation where visual processing is modelled $\textit{sequentially}$. Our experiments and analyses confirm that …
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）；Renmin University of China（中国人民大学）；CEBSIT, Chinese Academy of Sciences（中国科学院CEBSIT）
Multispectral pedestrian detection has shown great advantages under poor illumination conditions, since the thermal modality provides complementary information for the color image. However, real multispectral data suffers from the position shift problem, i.e. the color-thermal image pairs are not strictly aligned, making one object has different positions in different modalities. In deep learning based methods, this problem makes it difficult to fuse the feature maps from both modalities and puzzles the CNN training. In this paper, we propose a novel Aligned Region CNN (AR-CNN) to handle the w…
LAAS-CNRS（法国国家科学研究中心LAAS实验室）；UT3（图卢兹第三大学）；IRIT（图卢兹计算机科学研究所）；Université de Toulouse（图卢兹大学）；CNRS（法国国家科学研究中心）；INP Toulouse（图卢兹国立理工学院）
Meetings are a common activity in professional contexts, and it remains challenging to endow vocal assistants with advanced functionalities to facilitate meeting management. In this context, a task like active speaker detection can provide useful insights to model interaction between meeting participants. Motivated by our application context related to advanced meeting assistant, we want to combine audio and visual information to achieve the best possible performance. In this paper, we propose two different types of fusion for the detection of the active speaker, combining two visual modalitie…
