Associating sound and its producer in complex audiovisual scene is a challenging task, especially when we are lack of annotated training data. In this paper, we present a flexible audiovisual model that introduces a soft-clustering module as the audio and visual content detector, and regards the pervasive property of audiovisual concurrency as the latent supervision for inferring the correlation among detected contents. To ease the difficulty of audiovisual learning, we propose a novel curriculum learning strategy that trains the model from simple to complex scene. We show that such ordered learning procedure rewards the model the merits of easy training and fast convergence. Meanwhile, our audiovisual model can also provide effective unimodal representation and cross-modal alignment performance. We further deploy the well-trained model into practical audiovisual sound localization and separation task. We show that our localization model significantly outperforms existing methods, based on which we show comparable performance in sound separation without referring external visual supervision. Our video demo can be found at https://youtu.be/kuClfGG0cFU.
Imperial College London（帝国理工学院）；Samsung AI Centre, Cambridge（三星人工智能中心（剑桥））；Facebook London（Facebook（伦敦））
The intuitive interaction between the audio and visual modalities is valuable for cross-modal self-supervised learning. This concept has been demonstrated for generic audiovisual tasks like video action recognition and acoustic scene classification. However, self-supervision remains under-explored for audiovisual speech. We propose a method to learn self-supervised speech representations from the raw audio waveform. We train a raw audio encoder by combining audio-only self-supervision (by predicting informative audio attributes) with visual self-supervision (by generating talking faces from au…
We tackle the problem of audiovisual scene analysis for weakly-labeled data. To this end, we build upon our previous audiovisual representation learning framework to perform object classification in noisy acoustic environments and integrate audio source enhancement capability. This is made possible by a novel use of non-negative matrix factorization for the audio modality. Our approach is founded on the multiple instance learning paradigm. Its effectiveness is established through experiments over a challenging dataset of music instrument performance videos. We also show encouraging visual obje…
We present an introspection of an audiovisual speech enhancement model. In particular, we focus on interpreting how a neural audiovisual speech enhancement model uses visual cues to improve the quality of the target speech signal. We show that visual cues provide not only high-level information about speech activity, i.e., speech/silence, but also fine-grained visual information about the place of articulation. One byproduct of this finding is that the learned visual embeddings can be used as features for other visual speech applications. We demonstrate the effectiveness of the learned visual …
Imperial College London（伦敦帝国理工学院）；Facebook London（脸书伦敦）；University of Augsburg（奥格斯堡大学）
The large amount of audiovisual content being shared online today has drawn substantial attention to the prospect of audiovisual self-supervised learning. Recent works have focused on each of these modalities separately, while others have attempted to model both simultaneously in a cross-modal fashion. However, comparatively little attention has been given to leveraging one modality as a training objective to learn from the other. In this work, we propose Learning visual speech Representations from Audio via self-supervision (LiRA). Specifically, we train a ResNet+Conformer model to predict ac…
CurriFlow: Curriculum-Guided Depth Fusion with Optical Flow-Based Temporal Alignment for 3D Semantic Scene Completion
School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院）；Ministry of Education（教育部）；Shandong Computer Science Center (National Supercomputer Center in Jinan)（山东省计算机科学中心（济南国家超算中心））；Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东省科学院））；Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing（山东省计算电力互联网与服务计算重点实验室）；Shandong Fundamental Research Center for Computer Science（山东省计算机科学基础研究中心）
CASA-SDF: Curriculum-Aware Spatial Adaptation with Curvature-Guided Density for Neural Implicit Surface Reconstruction
School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；School of Automation, Nanjing University of Science and Technology（南京理工大学自动化学院）
University of Southern California（南加州大学）；Google, Inc.（谷歌公司）
When supervising an object detector with weakly labeled data, most existing approaches are prone to trapping in the discriminative object parts, e.g., finding the face of a cat instead of the full body, due to lacking the supervision on the extent of full objects. To address this challenge, we incorporate object segmentation into the detector training, which guides the model to correctly localize the full objects. We propose the multiple instance curriculum learning (MICL) method, which injects curriculum learning (CL) into the multiple instance learning (MIL) framework. The MICL method starts…
School of Automation, Northwestern Polytechnical University（西北工业大学自动化学院）
Weakly-supervised object detection (WOD) is a challenging problems in computer vision. The key problem is to simultaneously infer the exact object locations in the training images and train the object detectors, given only the training images with weak image-level labels. Intuitively, by simulating the selective attention mechanism of human visual system, saliency detection technique can select attractive objects in scenes and thus is a potential way to provide useful priors for WOD. However, the way to adopt saliency detection in WOD is not trivial since the detected saliency region might be …
Audiovisual automatic speech recognition (AV-ASR) aims to improve the robustness of a speech recognition system by incorporating visual information. Training fully supervised multimodal models for this task from scratch, however is limited by the need for large labelled audiovisual datasets (in each downstream domain of interest). We present AVFormer, a simple method for augmenting audio-only models with visual information, at the same time performing lightweight domain adaptation. We do this by (i) injecting visual embeddings into a frozen ASR model using lightweight trainable adaptors. We sh…
Prototype-Guided Curriculum Learning for Zero-Shot Learning
School of Electronic Information and Communications, Huazhong University of Science and Technology（电子信息与通信学院，华中科技大学）；Mohamed bin Zayed University of AI（马尔代夫人工智能大学）；School of Computer Science and Engineering, Nanjing University of Science and Technology（计算机科学与工程学院，南京理工大学）；School of Computer Science, The University of Sydney（计算机科学学院，悉尼大学）
VideoTG-R1: Boosting Video Temporal Grounding via Curriculum Reinforcement Learning on Reflected Boundary Annotations
University of Science and Technology of China（中国科学技术大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Beihang University（北京航空航天大学）；Shanghai Jiao Tong University（上海交通大学）；Zhejiang University（浙江大学）；State Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所）
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；IIIS, Tsinghua University（清华大学交叉信息研究院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；Deepmind（深度思考）；MIT BCS（麻省理工学院脑与认知科学系）；CBMM（脑、心智与机器中心）
We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that learns visual concepts, words, and semantic parsing of sentences without explicit supervision on any of them; instead, our model learns by simply looking at images and reading paired questions and answers. Our model builds an object-based scene representation and translates sentences into executable, symbolic programs. To bridge the learning of two modules, we use a neuro-symbolic reasoning module that executes these programs on the latent scene representation. Analogical to human concept learning, the perception module learns…
OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?
University of California, Berkeley（加州大学伯克利分校）；Duke University（杜克大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Washington（华盛顿大学）；Elorian；Impossible Research
