Dance experts often view dance as a hierarchy of information, spanning low-level (raw images, image sequences), mid-levels (human poses and bodypart movements), and high-level (dance genre). We propose a Hierarchical Dance Video Recognition framework (HDVR). HDVR estimates 2D pose sequences, tracks dancers, and then simultaneously estimates corresponding 3D poses and 3D-to-2D imaging parameters, without requiring ground truth for 3D poses. Unlike most methods that work on a single person, our tracking works on multiple dancers, under occlusions. From the estimated 3D pose sequence, HDVR extracts body part movements, and therefrom dance genre. The resulting hierarchical dance representation is explainable to experts. To overcome noise and interframe correspondence ambiguities, we enforce spatial and temporal motion smoothness and photometric continuity over time. We use an LSTM network to extract 3D movement subsequences from which we recognize the dance genre. For experiments, we have identified 154 movement types, of 16 body parts, and assembled a new University of Illinois Dance (UID) Dataset, containing 1143 video clips of 9 genres covering 30 hours, annotated with movement and genre labels. Our experimental results demonstrate that our algorithms outperform the state-of-the-art 3D pose estimation methods, which also enhances our dance recognition performance.
BeatDance: Generating Beat-Consistent 3D Dance with Hierarchical Spatial-Temporal Modeling
College of Software, Jilin University（吉林大学软件学院）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；ReLER, AAII, University of Technology Sydney（悉尼科技大学AAII ReLER实验室）；College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；School of Computer Science and Technology, Zhejiang Normal University（浙江师范大学计算机科学与技术学院）；School of Information and Communication Engineering, Dalian University of Technology（大连理工大学信息与通信工程学院）；School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University（深圳大学医学部生物医学工程学院）；School of Computer Science and Informatics, Cardiff University（卡迪夫大学计算机科学与信息学院）
Tempo as the Stable Cue: Hierarchical Mixture of Tempo and Beat Experts for Music to 3D Dance Generation
School of Electronic Engineering, Xidian University（西安电子科技大学电子工程学院）；Hohai university（河海大学）；School of Computer Science and Technology, Xidian University（西安电子科技大学计算机科学与技术学院）；Institute for Infocomm Research (I 2 R), A*STAR（新加坡科技研究局信息与通信研究所）
Nokia Bell Labs（诺基亚贝尔实验室）；New York University（纽约大学）
One of the key criticisms of deep learning is that large amounts of expensive and difficult-to-acquire training data are required in order to train models with high performance and good generalization capabilities. Focusing on the task of monocular camera pose estimation via scene coordinate regression (SCR), we describe a novel method, Domain Adaptation of Networks for Camera pose Estimation (DANCE), which enables the training of models without access to any labels on the target task. DANCE requires unlabeled images (without known poses, ordering, or scene coordinate labels) and a 3D represen…
Dance challenges are going viral in video communities like TikTok nowadays. Once a challenge becomes popular, thousands of short-form videos will be uploaded in merely a couple of days. Therefore, virality prediction from dance challenges is of great commercial value and has a wide range of applications, such as smart recommendation and popularity promotion. In this paper, a novel multi-modal framework which integrates skeletal, holistic appearance, facial and scenic cues is proposed for comprehensive dance virality prediction. To model body movements, we propose a pyramidal skeleton graph con…
Driving 3D characters to dance following a piece of music is highly challenging due to the spatial constraints applied to poses by choreography norms. In addition, the generated dance sequence also needs to maintain temporal coherency with different music genres. To tackle these challenges, we propose a novel music-to-dance framework, Bailando, with two powerful components: 1) a choreographic memory that learns to summarize meaningful dancing units from 3D pose sequence to a quantized codebook, 2) an actor-critic Generative Pre-trained Transformer (GPT) that composes these units to a fluent da…
Tsinghua University（清华大学）；Wayne State University（韦恩州立大学）；University of Maryland（马里兰大学）
Unsupervised learning of global features for 3D shape analysis is an important research challenge because it avoids manual effort for supervised information collection. In this paper, we propose a view-based deep learning model called Hierarchical View Predictor (HVP) to learn 3D shape features from unordered views in an unsupervised manner. To mine highly discriminative information from unordered views, HVP performs a novel hierarchical view prediction over a view pair, and aggregates the knowledge learned from the predictions in all view pairs into a global feature. In a view pair, we pose h…
Segmenting an image into its parts is a frequent preprocess for high-level vision tasks such as image editing. However, annotating masks for supervised training is expensive. Weakly-supervised and unsupervised methods exist, but they depend on the comparison of pairs of images, such as from multi-views, frames of videos, and image augmentation, which limits their applicability. To address this, we propose a GAN-based approach that generates images conditioned on latent masks, thereby alleviating full or weak annotations required in previous approaches. We show that such mask-conditioned image …
The formation of connections between neural cells is emerging essentially from an unsupervised learning process. For instance, during the development of the primary visual cortex of mammals (V1), we observe the emergence of cells selective to localized and oriented features. This leads to the development of a rough contour-based representation of the retinal image in area V1. We propose a biological model of the formation of this representation along the thalamo-cortical pathway. To achieve this goal, we replicated the Multi-Layer Convolutional Sparse Coding (ML-CSC) algorithm developed by Mic…
Instance segmentation is an active topic in computer vision that is usually solved by using supervised learning approaches over very large datasets composed of object level masks. Obtaining such a dataset for any new domain can be very expensive and time-consuming. In addition, models trained on certain annotated categories do not generalize well to unseen objects. The goal of this paper is to propose a method that can perform unsupervised discovery of long-tail categories in instance segmentation, through learning instance embeddings of masked regions. Leveraging rich relationship and hierarc…
College of Computer Science and Technology, Zhejiang Gongshang University（浙江工商大学计算机科学与技术学院）；Zhejiang Key Lab of E-Commerce（浙江省电子商务重点实验室）
This paper targets unsupervised skeleton-based action representation learning and proposes a new Hierarchical Contrast (HiCo) framework. Different from the existing contrastive-based solutions that typically represent an input skeleton sequence into instance-level features and perform contrast holistically, our proposed HiCo represents the input into multiple-level features and performs contrast in a hierarchical manner. Specifically, given a human skeleton sequence, we represent it into multiple feature vectors of different granularities from both temporal and spatial domains via sequence-to-…
National University of Defense Technology（国防科技大学）；Shandong University（山东大学）；Simon Fraser University（西蒙弗雷泽大学）
We introduce RIM-Net, a neural network which learns recursive implicit fields for unsupervised inference of hierarchical shape structures. Our network recursively decomposes an input 3D shape into two parts, resulting in a binary tree hierarchy. Each level of the tree corresponds to an assembly of shape parts, represented as implicit functions, to reconstruct the input shape. At each node of the tree, simultaneous feature decoding and shape decomposition are carried out by their respective feature and part decoders, with weight sharing across the same hierarchy level. As an implicit field deco…
Shanghai Jiao Tong University（上海交通大学）；University of Cambridge（剑桥大学）
Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video. A novel unsupervised training framework is proposed with 3D hierarchical refinement and augmentation using explicit 3D geometry. In this framework, the depth and pose estimations are hierarchically and mutually coupled to refine the estimated pose layer by layer. The intermediate view image is proposed and synthesized by warping the pixels in an image with t…
Interpretable Single-View 3D Gaussian Splatting using Unsupervised Hierarchical Disentangled Representation Learning
Shanghai Jiao Tong University（上海交通大学）；Ningbo Institute of Digital Twin, Eastern Institute of Technology（东方理工大学宁波数字孪生研究院）；Hong Kong Polytechnic University（香港理工大学）
Nanjing University of Science and Technology（南京理工大学）；University of Electronic Science and Technology of China（电子科技大学）
Optical flow is an easily conceived and precious cue for advancing unsupervised video object segmentation (UVOS). Most of the previous methods directly extract and fuse the motion and appearance features for segmenting target objects in the UVOS setting. However, optical flow is intrinsically an instantaneous velocity of all pixels among consecutive frames, thus making the motion features not aligned well with the primary objects among the corresponding frames. To solve the above challenge, we propose a concise, practical, and efficient architecture for appearance and motion feature alignment,…
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）
Capsule networks are designed to present the objects by a set of parts and their relationships, which provide an insight into the procedure of visual perception. Although recent works have shown the success of capsule networks on simple objects like digits, the human faces with homologous structures, which are suitable for capsules to describe, have not been explored. In this paper, we propose a Hierarchical Parsing Capsule Network (HP-Capsule) for unsupervised face subpart-part discovery. When browsing large-scale face images without labels, the network first encodes the frequently observed p…
National Key Laboratory of Science and Technology on Multispectral Information Processing, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院多谱信息处理技术国家级重点实验室）；School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）
Optical flow estimation has made great progress, but usually suffers from degradation under adverse weather. Although semi/full-supervised methods have made good attempts, the domain shift between the synthetic and real adverse weather images would deteriorate their performance. To alleviate this issue, our start point is to unsupervisedly transfer the knowledge from source clean domain to target degraded domain. Our key insight is that adverse weather does not change the intrinsic optical flow of the scene, but causes a significant difference for the warp error between clean and degraded imag…
The combination of spiking neural networks and event-based vision sensors holds the potential of highly efficient and high-bandwidth optical flow estimation. This paper presents the first hierarchical spiking architecture in which motion (direction and speed) selectivity emerges in an unsupervised fashion from the raw stimuli generated with an event-based camera. A novel adaptive neuron model and stable spike-timing-dependent plasticity formulation are at the core of this neural network governing its spike-based processing and learning, respectively. After convergence, the neural architecture …
Temporal Prototyping and Hierarchical Alignment for Unsupervised Video-based Visible-Infrared Person Re-Identification
College of Control Science and Engineering, Zhejiang University（控制科学与工程学院，浙江大学）；School of Computer Science and Technology, Zhejiang University of Water Resources and Electric Power（计算机科学与技术学院，浙江水利电力大学）
Unsupervised semantic segmentation aims to discover groupings within and across images that capture object and view-invariance of a category without external supervision. Grouping naturally has levels of granularity, creating ambiguity in unsupervised segmentation. Existing methods avoid this ambiguity and treat it as a factor outside modeling, whereas we embrace it and desire hierarchical grouping consistency for unsupervised segmentation. We approach unsupervised segmentation as a pixel-wise feature learning problem. Our idea is that a good representation shall reveal not just a particular l…
Unsupervised Monocular Depth Estimation Based on Hierarchical Feature-Guided Diffusion
School of Information Science and Technology, ShanghaiTech University（信息科学与技术学院，上海科技大学）；Bionic Vision System Laboratory, State Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences（生物视觉系统实验室，传感技术国家重点实验室，微系统与信息工程研究所，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Xiongan Institute of Innovation（雄安创新研究院）；University of Science and Technology of China（中国科学技术大学）
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；ETH Zürich（苏黎世联邦理工学院）；KU Leuven（鲁汶大学）；University of Tübingen（图宾根大学）
Humans perceive the 3D world as a set of distinct objects that are characterized by various low-level (geometry, reflectance) and high-level (connectivity, adjacency, symmetry) properties. Recent methods based on convolutional neural networks (CNNs) demonstrated impressive progress in 3D reconstruction, even when using a single 2D image as input. However, the majority of these methods focuses on recovering the local 3D geometry of an object without considering its part-based decomposition or relations between parts. We address this challenging problem by proposing a novel formulation that allo…
University of Washington（华盛顿大学）；Electronics and Telecommunications Research Institute（电子与电信研究所）
The Alberta Infant Motor Scale (AIMS) is a well-known assessment scheme that evaluates the gross motor development of infants by recording the number of specific poses achieved. With the aid of the image-based pose recognition model, the AIMS evaluation procedure can be shortened and automated, providing early diagnosis or indicator of potential developmental disorder. Due to limited public infant-related datasets, many works use the SMIL-based method to generate synthetic infant images for training. However, this domain mismatch between real and synthetic training samples often leads to perfo…
For most unsupervised person re-identification (re-ID), people often adopt unsupervised domain adaptation (UDA) method. UDA often train on the labeled source dataset and evaluate on the target dataset, which often focuses on learning differences between the source dataset and the target dataset to improve the generalization of the model. Base on these, we explore how to make use of the similarity of samples to conduct a fully unsupervised method which just trains on the unlabeled target dataset. Concretely, we propose a hierarchical clustering-guided re-ID (HCR) method. We use hierarchical clu…
Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement
College of Electronic Science and Technology, National University of Defense Technology（电子科学与技术学院，国防科技大学）；College of Electronic and Information Engineering, Beihang University（电子与信息工程学院，北航）
National University of Defense Technology（中国人民解放军国防科技大学）
Due to the high cost of data annotation in supervised learning for person re-identification (Re-ID) methods, unsupervised learning becomes more attractive in the real world. The Bottom-up Clustering (BUC) approach based on hierarchical clustering serves as one promising unsupervised clustering method. One key factor of BUC is the distance measurement strategy. Ideally, the distance measurement should consider both inter-cluster and intra-cluster distance of all samples. However, BUC uses the minimum distance, only considers a pair of the nearest sample between two clusters and ignores the dive…
In this paper, we propose a novel approach for unsupervised domain adaptation, that relates notions of optimal transport, learning probability measures and unsupervised learning. The proposed approach, HOT-DA, is based on a hierarchical formulation of optimal transport, that leverages beyond the geometrical information captured by the ground metric, richer structural information in the source and target domains. The additional information in the labeled source domain is formed instinctively by grouping samples into structures according to their class labels. While exploring hidden structures i…
University of Southern California（南加州大学）；Tencent America（腾讯美国）；Tencent Media Lab（腾讯媒体实验室）
Inspired by the recent PointHop classification method, an unsupervised 3D point cloud registration method, called R-PointHop, is proposed in this work. R-PointHop first determines a local reference frame (LRF) for every point using its nearest neighbors and finds local attributes. Next, R-PointHop obtains local-to-global hierarchical features by point downsampling, neighborhood expansion, attribute construction and dimensionality reduction steps. Thus, point correspondences are built in hierarchical feature space using the nearest neighbor rule. Afterwards, a subset of salient points with good…
STMicrolectronics, ADG Central R&D, Catania, Italy（意法半导体，ADG中央研发部，卡塔尼亚，意大利）；PeRCeiVe Lab - University of Catania（PeRCeiVe实验室 - 卡塔尼亚大学）
In this work, we propose a 3D fully convolutional architecture for video saliency prediction that employs hierarchical supervision on intermediate maps (referred to as conspicuity maps) generated using features extracted at different abstraction levels. We provide the base hierarchical learning mechanism with two techniques for domain adaptation and domain-specific learning. For the former, we encourage the model to unsupervisedly learn hierarchical general features using gradient reversal at multiple scales, to enhance generalization capabilities on datasets for which no annotations are provi…
We propose FineGAN, a novel unsupervised GAN framework, which disentangles the background, object shape, and object appearance to hierarchically generate images of fine-grained object categories. To disentangle the factors without supervision, our key idea is to use information theory to associate each factor to a latent code, and to condition the relationships between the codes in a specific way to induce the desired hierarchy. Through extensive experiments, we show that FineGAN achieves the desired disentanglement to generate realistic and diverse images belonging to fine-grained classes of …
We address the task of domain generalization, where the goal is to train a predictive model such that it is able to generalize to a new, previously unseen domain. We choose a hierarchical generative approach within the framework of variational autoencoders and propose a domain-unsupervised algorithm that is able to generalize to new domains without domain supervision. We show that our method is able to learn representations that disentangle domain-specific information from class-label specific information even in complex settings where domain structure is not observed during training. Our inte…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Daimler TSS（戴姆勒TSS公司）；Facebook AI Research（脸书人工智能研究实验室）；MIT（麻省理工学院）；Harvard Medical School（哈佛医学院）；KU Leuven（鲁汶大学）；ETH Zurich（苏黎世联邦理工学院）
Action segmentation refers to inferring boundaries of semantically consistent visual concepts in videos and is an important requirement for many video understanding tasks. For this and other video understanding tasks, supervised approaches have achieved encouraging performance but require a high volume of detailed frame-level annotations. We present a fully automatic and unsupervised approach for segmenting actions in a video that does not require any training. Our proposal is an effective temporally-weighted hierarchical clustering algorithm that can group semantically consistent frames of th…
Imperial College London（帝国理工学院）；Microsoft Research（微软研究院）；Microsoft Research Cambridge（微软剑桥研究院）
Current face recognition systems typically operate via classification into known identities obtained from supervised identity annotations. There are two problems with this paradigm: (1) current systems are unable to benefit from often abundant unlabelled data; and (2) they equate successful recognition with labelling a given input image. Humans, on the other hand, regularly perform identification of individuals completely unsupervised, recognising the identity of someone they have seen before even without being able to name that individual. How can we go beyond the current classification parad…
Deep learning models have been shown to learn spurious correlations from data that sometimes lead to systematic failures for certain subpopulations. Prior work has typically diagnosed this by crowdsourcing annotations for various protected attributes and measuring performance, which is both expensive to acquire and difficult to scale. In this work, we propose UDIS, an unsupervised algorithm for surfacing and analyzing such failure modes. UDIS identifies subpopulations via hierarchical clustering of dataset embeddings and surfaces systematic failure modes by visualizing low performing clusters …
The present phase of Machine Learning is characterized by supervised learning algorithms relying on large sets of labeled examples ($n \to \infty$). The next phase is likely to focus on algorithms capable of learning from very few labeled examples ($n \to 1$), like humans seem able to do. We propose an approach to this problem and describe the underlying theory, based on the unsupervised, automatic learning of a ``good'' representation for supervised learning, characterized by small sample complexity ($n$). We consider the case of visual object recognition though the theory applies to other do…
University of Electronic Science and Technology of China（电子科技大学）；Nanyang University of Technology（南洋理工大学）；Hefei University of Technology（合肥工业大学）
Existing video hash functions are built on three isolated stages: frame pooling, relaxed learning, and binarization, which have not adequately explored the temporal order of video frames in a joint binary optimization model, resulting in severe information loss. In this paper, we propose a novel unsupervised video hashing framework dubbed Self-Supervised Video Hashing (SSVH), that is able to capture the temporal nature of videos in an end-to-end learning-to-hash fashion. We specifically address two central problems: 1) how to design an encoder-decoder architecture to generate binary codes for …
Laboratoire de Physique, UMR 5672（物理实验室，联合研究单位5672）；CNRS, ENS de Lyon, UCB Lyon 1（法国国家科学研究中心，里昂高等师范学院，里昂第一大学）；UMPA UMR 5669（纯数学与应用数学联合研究单位5669）；LIP UMR 5668（计算机科学并行计算实验室，联合研究单位5668）；Laboratoire Hubert Curien, UMR 5516（于贝尔·居里安实验室，联合研究单位5516）；CNRS, University of Lyon, UJM-Saint-Etienne（法国国家科学研究中心，里昂大学，圣艾蒂安让·莫内大学）
We propose a novel algorithm for unsupervised graph representation learning with attributed graphs. It combines three advantages addressing some current limitations of the literature: i) The model is inductive: it can embed new graphs without re-training in the presence of new data; ii) The method takes into account both micro-structures and macro-structures by looking at the attributed graphs at different scales; iii) The model is end-to-end differentiable: it is a building block that can be plugged into deep learning pipelines and allows for back-propagation. We show that combining a coarsen…
SHAPE: Structure-aware Hierarchical Unsupervised Domain Adaptation with Plausibility Evaluation for Medical Image Segmentation
School of Software, Northwestern Polytechnical University（西北工业大学软件学院）；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）；School of Software Engineering, USTC（USTC软件工程学院）；Australian Institute of Health Innovation, Macquarie University（麦考瑞大学健康创新研究所）；Faculty of Applied Science, Macao Polytechnic University（澳门理工学院应用科学学院）；School of Computer Software, Tianjin University（天津大学计算机软件学院）
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；Google Research（谷歌研究院）
Humans easily recognize object parts and their hierarchical structure by watching how they move; they can then predict how each part moves in the future. In this paper, we propose a novel formulation that simultaneously learns a hierarchical, disentangled object representation and a dynamics model for object parts from unlabeled videos. Our Parts, Structure, and Dynamics (PSD) model learns to, first, recognize the object parts via a layered image representation; second, predict hierarchy via a structural descriptor that composes low-level concepts into a hierarchical structure; and third, mode…
Recognizing actions from still images is popularly studied recently. In this paper, we model an action class as a flexible number of spatial configurations of body parts by proposing a new spatial SPN (Sum-Product Networks). First, we discover a set of parts in image collections via unsupervised learning. Then, our new spatial SPN is applied to model the spatial relationship and also the high-order correlations of parts. To learn robust networks, we further develop a hierarchical spatial SPN method, which models pairwise spatial relationship between parts inside sub-images and models the corre…
SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection
Institute of Artificial Intelligence, University of Engineering and Technology, Vietnam National University（越南国立大学工程技术大学人工智能研究所）；Human-Machine Interaction Laboratory, University of Engineering and Technology, Vietnam National University（越南国立大学工程技术大学人机交互实验室）；Applied AI Lab, Phenikaa School of Computing, Phenikaa University（费尼卡大学计算学院应用人工智能实验室）
Hierarchical Identity Learning for Unsupervised Visible-Infrared Person Re-Identification
IEEE Publication Technology Department（IEEE出版技术部门）；State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University（信息服务网络国家重点实验室，电信工程学院，西安电子科技大学）；Department of Computer Science and Technology, Tongji University（计算机科学与技术系，同济大学）
University of Twente（特文特大学）；Leibniz University Hannover（汉诺威莱布尼茨大学）；Zhejiang University（浙江大学）
In this paper, we present an unsupervised learning framework for analyzing activities and interactions in surveillance videos. In our framework, three levels of video events are connected by Hierarchical Dirichlet Process (HDP) model: low-level visual features, simple atomic activities, and multi-agent interactions. Atomic activities are represented as distribution of low-level features, while complicated interactions are represented as distribution of atomic activities. This learning process is unsupervised. Given a training video sequence, low-level visual features are extracted based on opt…
The main challenges of image-to-image (I2I) translation are to make the translated image realistic and retain as much information from the source domain as possible. To address this issue, we propose a novel architecture, termed as IEGAN, which removes the encoder of each network and introduces an encoder that is independent of other networks. Compared with previous models, it embodies three advantages of our model: Firstly, it is more directly and comprehensively to grasp image information since the encoder no longer receives loss from generator and discriminator. Secondly, the independent en…
Shallow Features Matter: Hierarchical Memory with Heterogeneous Interaction for Unsupervised Video Object Segmentation
Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University（上海智能信息处理重点实验室，计算机科学与人工智能学院，复旦大学）；The School of Computer Engineering and Science, Shanghai University（上海大学计算机工程与科学学院）
