In this paper, we introduce a new problem, named audio-visual video parsing, which aims to parse a video into temporal event segments and label them as either audible, visible, or both. Such a problem is essential for a complete understanding of the scene depicted inside a video. To facilitate exploration, we collect a Look, Listen, and Parse (LLP) dataset to investigate audio-visual video parsing in a weakly-supervised manner. This task can be naturally formulated as a Multimodal Multiple Instance Learning (MMIL) problem. Concretely, we propose a novel hybrid attention network to explore unimodal and cross-modal temporal contexts simultaneously. We develop an attentive MMIL pooling method to adaptively explore useful audio and visual content from different temporal extent and modalities. Furthermore, we discover and mitigate modality bias and noisy label issues with an individual-guided learning mechanism and label smoothing technique, respectively. Experimental results show that the challenging audio-visual video parsing can be achieved even with only video-level weak labels. Our proposed framework can effectively leverage unimodal and cross-modal temporal contexts and alleviate modality bias and noisy labels problems.
The thud of a bouncing ball, the onset of speech as lips open -- when visual and audio events occur together, it suggests that there might be a common, underlying event that produced both signals. In this paper, we argue that the visual and audio components of a video signal should be modeled jointly using a fused multisensory representation. We propose to learn such a representation in a self-supervised way, by training a neural network to predict whether video frames and audio are temporally aligned. We use this learned representation for three applications: (a) sound source localization, i.…
Department of Electrical and Computer Engineering, Johns Hopkins University（约翰霍普金斯大学电气与计算机工程系）
Natural environment and our interaction with it is essentially multisensory, where we may deploy visual, tactile and/or auditory senses to perceive, learn and interact with our environment. Our objective in this study is to develop a scene analysis algorithm using multisensory information, specifically vision and audio. We develop a proto-object based audiovisual saliency map (AVSM) for the analysis of dynamic natural scenes. A specialized audiovisual camera with $360 \degree$ Field of View, capable of locating sound direction, is used to collect spatiotemporally aligned audiovisual data. We d…
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…
Indian Institute of Techonology, Bombay（印度理工学院孟买分校）
In this paper, we present a novel approach to the audio-visual video parsing (AVVP) task that demarcates events from a video separately for audio and visual modalities. The proposed parsing approach simultaneously detects the temporal boundaries in terms of start and end times of such events. We show how AVVP can benefit from the following techniques geared towards effective cross-modal learning: (i) adversarial training and skip connections (ii) global context aware attention and, (iii) self-supervised pretraining using an audio-video grounding objective to obtain cross-modal audio-video repr…
UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing
Graduate Institute of Communication Engineering, National Taiwan University（国立台湾大学通信工程研究所）；NVIDIA, Taiwan（台湾NVIDIA公司）；Mitsubishi Electric Research Labs (MERL)（三菱电机研究实验室）
University of Rochester（罗切斯特大学）；Meta Reality Labs Research（Meta现实实验室）
Humans naturally perceive surrounding scenes by unifying sound and sight in a first-person view. Likewise, machines are advanced to approach human intelligence by learning with multisensory inputs from an egocentric perspective. In this paper, we explore the challenging egocentric audio-visual object localization task and observe that 1) egomotion commonly exists in first-person recordings, even within a short duration; 2) The out-of-view sound components can be created while wearers shift their attention. To address the first problem, we propose a geometry-aware temporal aggregation module to…
In this paper, we propose to make a systematic study on machines multisensory perception under attacks. We use the audio-visual event recognition task against multimodal adversarial attacks as a proxy to investigate the robustness of audio-visual learning. We attack audio, visual, and both modalities to explore whether audio-visual integration still strengthens perception and how different fusion mechanisms affect the robustness of audio-visual models. For interpreting the multimodal interactions under attacks, we learn a weakly-supervised sound source visual localization model to localize sou…
DeepFake based digital facial forgery is threatening the public media security, especially when lip manipulation has been used in talking face generation, the difficulty of fake video detection is further improved. By only changing lip shape to match the given speech, the facial features of identity is hard to be discriminated in such fake talking face videos. Together with the lack of attention on audio stream as the prior knowledge, the detection failure of fake talking face generation also becomes inevitable. Inspired by the decision-making mechanism of human multisensory perception system,…
UT Austin（德克萨斯大学奥斯汀分校）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；Facebook Reality Labs（Facebook 现实实验室）；Facebook AI Research（Facebook 人工智能研究院）
Moving around in the world is naturally a multisensory experience, but today's embodied agents are deaf---restricted to solely their visual perception of the environment. We introduce audio-visual navigation for complex, acoustically and visually realistic 3D environments. By both seeing and hearing, the agent must learn to navigate to a sounding object. We propose a multi-modal deep reinforcement learning approach to train navigation policies end-to-end from a stream of egocentric audio-visual observations, allowing the agent to (1) discover elements of the geometry of the physical space indi…
AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection
Social Networks and Human-Centered Computing Program, Taiwan International Graduate Program, Academia Sinica（社会网络与以人为本计算计划、台湾国际研究生计划、中国科学院）；Institute of Information Systems and Applications, National Tsing Hua University（信息系统与应用研究所、国立清华大学）；Department of Computer Science, National Chengchi University（计算机科学系、国立成功大学）；Research Center for Information Technology Innovation, Academia Sinica（信息技术创新研究中心、中国科学院）；Institute of Information Science, Academia Sinica（信息科学研究所、中国科学院）
UniSync: A Unified Framework for Audio-Visual Synchronization
Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东省人工智能与数字经济实验室（深圳））；Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
University of Birmingham（伯明翰大学）；Waseda University（早稻田大学）
The hype about sensorimotor learning is currently reaching high fever, thanks to the latest advancement in deep learning. In this paper, we present an open-source framework for collecting large-scale, time-synchronised synthetic data from highly disparate sensory modalities, such as audio, video, and proprioception, for learning robot manipulation tasks. We demonstrate the learning of non-linear sensorimotor mappings for a humanoid drumming robot that generates novel motion sequences from desired audio data using cross-modal correspondences. We evaluate our system through the quality of its cr…
Predicting future sensory states is crucial for learning agents such as robots, drones, and autonomous vehicles. In this paper, we couple multiple sensory modalities with exploratory actions and propose a predictive neural network architecture to address this problem. Most existing approaches rely on large, manually annotated datasets, or only use visual data as a single modality. In contrast, the unsupervised method presented here uses multi-modal perceptions for predicting future visual frames. As a result, the proposed model is more comprehensive and can better capture the spatio-temporal d…
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）
Human brain is continuously inundated with the multisensory information and their complex interactions coming from the outside world at any given moment. Such information is automatically analyzed by binding or segregating in our brain. While this task might seem effortless for human brains, it is extremely challenging to build a machine that can perform similar tasks since complex interactions cannot be dealt with single type of integration but requires more sophisticated approaches. In this paper, we propose a new model to address the multisensory integration problem with individual event-sp…
Reinforced Label Denoising for Weakly-Supervised Audio-Visual Video Parsing
Shandong University（山东大学）；Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东省科学院））；Shandong Computer Science Center (National Supercomputer Center in Jinan)（山东省计算中心（国家超级计算济南中心））
Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-wise Pseudo Labeling
Hefei University of Technology（合肥工业大学）；Shanghai AI Laboratory（上海人工智能实验室）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）；Anhui Zhonghuitong Technology Co., Ltd.（安徽中汇通科技有限公司）
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）；Shanghai AI Lab（上海人工智能实验室）
Audio-Visual Video Parsing is a task to predict the events that occur in video segments for each modality. It often performs in a weakly supervised manner, where only video event labels are provided, i.e., the modalities and the timestamps of the labels are unknown. Due to the lack of densely annotated labels, recent work attempts to leverage pseudo labels to enrich the supervision. A commonly used strategy is to generate pseudo labels by categorizing the known event labels for each modality. However, the labels are still limited to the video level, and the temporal boundaries of event timesta…
Label-anticipated Event Disentanglement for Audio-Visual Video Parsing
Hefei University of Technology（合肥工业大学）；Anhui Zhonghuitong Technology Co., Ltd.（安徽中汇通科技有限公司）；University of Science and Technology of China（中国科学技术大学）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）；Northwestern Polytechnical University（西北工业大学）；Shanghai AI Laboratory（上海人工智能实验室）
Recognizing and localizing events in videos is a fundamental task for video understanding. Since events may occur in auditory and visual modalities, multimodal detailed perception is essential for complete scene comprehension. Most previous works attempted to analyze videos from a holistic perspective. However, they do not consider semantic information at multiple scales, which makes the model difficult to localize events in different lengths. In this paper, we present a Multimodal Pyramid Attentional Network (\textbf{MM-Pyramid}) for event localization. Specifically, we first propose the atte…
Multimodal Imbalance-Aware Gradient Modulation for Weakly-supervised Audio-Visual Video Parsing
Zhengzhou University（郑州大学）；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）；Peng Cheng Laboratory（鹏城实验室）
TEn-CATG:Text-Enriched Audio-Visual Video Parsing with Multi-Scale Category-Aware Temporal Graph
Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey（视觉、语音和信号处理中心（CVSSP），萨里大学）；School of Computer Science and Artificial Intelligence, Wuhan University of Technology（计算机科学与人工智能学院，武汉理工大学）；National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University（通用人工智能国家重点实验室，北京大学智能科学与技术学院）；College of Information and Electrical Engineering, China Agricultural University（信息与电子工程学院，中国农业大学）
Beijing University of Posts and Telecommunications（北京邮电大学）；University of Technology Sydney（悉尼科技大学）；Australian AI Institute（澳大利亚人工智能研究所）
For multimodal tasks, a good feature extraction network should extract information as much as possible and ensure that the extracted feature embedding and other modal feature embedding have an excellent mutual understanding. The latter is often more critical in feature fusion than the former. Therefore, selecting the optimal feature extraction network collocation is a very important subproblem in multimodal tasks. Most of the existing studies ignore this problem or adopt an ergodic approach. This problem is modeled as an optimization problem in this paper. A novel method is proposed to convert…
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 …
Renmin University of China（中国人民大学）；University of Rochester（罗切斯特大学）
In this paper, we focus on the Audio-Visual Question Answering (AVQA) task, which aims to answer questions regarding different visual objects, sounds, and their associations in videos. The problem requires comprehensive multimodal understanding and spatio-temporal reasoning over audio-visual scenes. To benchmark this task and facilitate our study, we introduce a large-scale MUSIC-AVQA dataset, which contains more than 45K question-answer pairs covering 33 different question templates spanning over different modalities and question types. We develop several baselines and introduce a spatio-temp…
The Chinese University of Hong Kong（香港中文大学）；Monash University（莫纳什大学）；SenseTime Research（商汤科技研究院）；Sensetime（商汤科技（此处原英文为“sensetime”，结合上下文“wuwenyan@sensetime.com”推测为“商汤科技”，但严格按“机构粒度”提取，原文本中“SenseTime Research”已单独列出，此处“sensetime”视为同一机构））
Animating high-fidelity video portrait with speech audio is crucial for virtual reality and digital entertainment. While most previous studies rely on accurate explicit structural information, recent works explore the implicit scene representation of Neural Radiance Fields (NeRF) for realistic generation. In order to capture the inconsistent motions as well as the semantic difference between human head and torso, some work models them via two individual sets of NeRF, leading to unnatural results. In this work, we propose Semantic-aware Speaking Portrait NeRF (SSP-NeRF), which creates delicate …
Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation
MBZUAI；Hefei University of Technology（合肥工业大学）；University of Science and Technology of China（中国科学技术大学）；National University of Singapore（新加坡国立大学）；Peking University（北京大学）；Tsinghua University（清华大学）；OpenNLP Lab（OpenNLP实验室）
AV-Unified: A Unified Framework for Audio-visual Scene Understanding
Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation
Shanghai Jiao Tong University（上海交通大学）；University of Electronic Science and Technology of China（电子科技大学）；Zhejiang University（浙江大学）；The University of Tokyo（东京大学）；Nanyang Technological University（南洋理工大学）
