Self-supervised landmark estimation is a challenging task that demands the formation of locally distinct feature representations to identify sparse facial landmarks in the absence of annotated data. To tackle this task, existing state-of-the-art (SOTA) methods (1) extract coarse features from backbones that are trained with instance-level self-supervised learning (SSL) paradigms, which neglect the dense prediction nature of the task, (2) aggregate them into memory-intensive hypercolumn formations, and (3) supervise lightweight projector networks to naively establish full local correspondences among all pairs of spatial features. In this paper, we introduce SCE-MAE, a framework that (1) leverages the MAE, a region-level SSL method that naturally better suits the landmark prediction task, (2) operates on the vanilla feature map instead of on expensive hypercolumns, and (3) employs a Correspondence Approximation and Refinement Block (CARB) that utilizes a simple density peak clustering algorithm and our proposed Locality-Constrained Repellence Loss to directly hone only select local correspondences. We demonstrate through extensive experiments that SCE-MAE is highly effective and robust, outperforming existing SOTA methods by large margins of approximately 20%-44% on the landmark matching and approximately 9%-15% on the landmark detection tasks.
Scene graph generation (SGG) is a sophisticated task that suffers from both complex visual features and dataset long-tail problem. Recently, various unbiased strategies have been proposed by designing novel loss functions and data balancing strategies. Unfortunately, these unbiased methods fail to emphasize language priors in feature refinement perspective. Inspired by the fact that predicates are highly correlated with semantics hidden in subject-object pair and global context, we propose LANDMARK (LANguage-guiDed representationenhanceMent frAmewoRK) that learns predicate-relevant representat…
University of Amsterdam（阿姆斯特丹大学）；Xiaohongshu Inc（小红书公司）
Person re-identification aims to retrieve persons in highly varying settings across different cameras and scenarios, in which robust and discriminative representation learning is crucial. Most research considers learning representations from single images, ignoring any potential interactions between them. However, due to the high intra-identity variations, ignoring such interactions typically leads to outlier features. To tackle this issue, we propose a Neighbor Transformer Network, or NFormer, which explicitly models interactions across all input images, thus suppressing outlier features and …
SLD: Segmentation-Based Landmark Detection for Spinal Ligaments
Institute for Computational Visualistics, University of Koblenz, Germany（计算视觉研究所，科伦茨大学，德国）；University Sports, University of Koblenz, Germany（大学体育，科伦茨大学，德国）；Institute of Anatomy, University Medical Center of Johannes Gutenberg University Mainz, Germany（解剖研究所，吉森大学医学中心，德国）
Representation Learning of Lab Values via Masked AutoEncoders
Massachusetts Institute of Technology (MIT)（麻省理工学院）；Université Paris-Saclay（巴黎-萨克雷大学）；University of Michigan（密歇根大学）；Northeastern University（东北大学）；Harvard Medical School（哈佛医学院）；Brigham and Women’s Hospital/Dana-Farber Cancer Institute（哈佛医学院-布里特医院/达纳-法伯癌症研究所）；Beth Israel Deaconess Medical Center（贝斯以色列医疗中心）
Landmark-based robot self-localization has recently garnered interest as a highly-compressive domain-invariant approach for performing visual place recognition (VPR) across domains (e.g., time of day, weather, and season). However, landmark-based self-localization can be an ill-posed problem for a passive observer (e.g., manual robot control), as many viewpoints may not provide an effective landmark view. In this study, we consider an active self-localization task by an active observer and present a novel reinforcement learning (RL)-based next-best-view (NBV) planner. Our contributions are as …
Depression is a major debilitating disorder which can affect people from all ages. With a continuous increase in the number of annual cases of depression, there is a need to develop automatic techniques for the detection of the presence and extent of depression. In this AVEC challenge we explore different modalities (speech, language and visual features extracted from face) to design and develop automatic methods for the detection of depression. In psychology literature, the PHQ-8 questionnaire is well established as a tool for measuring the severity of depression. In this paper we aim to auto…
FacialPulse: An Efficient RNN-based Depression Detection via Temporal Facial Landmarks
Hefei University of Technology（合肥工业大学）；CFAR（计算科学与工程中心）；IHPC（高性能计算研究所）；A*STAR（新加坡科技研究局）；University of Science and Technology of China（中国科学技术大学）；The University of Electro-Communications（东京电机大学）
FM-OSD: Foundation Model-Enabled One-Shot Detection of Anatomical Landmarks
The Chinese University of Hong Kong（香港中文大学）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Massachusetts General Brigham（麻省总医院布里格姆医疗系统）；Institute of Medical Intelligence and XR, The Chinese University of Hong Kong（香港中文大学医学智能与XR研究所）
This paper presents a new approach for integrating semantic information for vision-based vehicle navigation. Although vision-based vehicle navigation systems using pre-mapped visual landmarks are capable of achieving submeter level accuracy in large-scale urban environment, a typical error source in this type of systems comes from the presence of visual landmarks or features from temporal objects in the environment, such as cars and pedestrians. We propose a gated factor graph framework to use semantic information associated with visual features to make decisions on outlier/ inlier computation…
Mask 2D-3D: Adaptive Dual-Masked Autoencoder Network for Image-to-Point Cloud Registration
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）；Institute of Advanced Technology, University of Science and Technology of China（中国科学技术大学先进技术研究院）
A recent trend to recognize facial expressions in the real-world scenario is to deploy attention based convolutional neural networks (CNNs) locally to signify the importance of facial regions and, combine it with global facial features and/or other complementary context information for performance gain. However, in the presence of occlusions and pose variations, different channels respond differently, and further that the response intensity of a channel differ across spatial locations. Also, modern facial expression recognition(FER) architectures rely on external sources like landmark detector…
Shenzhen University（深圳大学）；Hanshan Normal University（韩山师范学院）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）
Recently, convolutional neural networks (CNNs)-based facial landmark detection methods have achieved great success. However, most of existing CNN-based facial landmark detection methods have not attempted to activate multiple correlated facial parts and learn different semantic features from them that they can not accurately model the relationships among the local details and can not fully explore more discriminative and fine semantic features, thus they suffer from partial occlusions and large pose variations. To address these problems, we propose a cross-order cross-semantic deep network (CC…
Compared to abstract features, significant objects, so-called landmarks, are a more natural means for vehicle localization and navigation, especially in challenging unstructured environments. The major challenge is to recognize landmarks in various lighting conditions and changing environment (growing vegetation) while only having few training samples available. We propose a new method which leverages Deep Learning as well as model-based methods to overcome the need of a large data set. Using RGB images and light detection and ranging (LiDAR) point clouds, our approach combines state-of-the-ar…
CITIC-Research Center of Information and Communication Technologies, University of A Coruña（科蒂克信息与通信技术研究中心，拉科鲁尼亚大学）；Department of Computer Science, University of A Coruña（拉科鲁尼亚大学计算机科学系）；University of A Coruña（拉科鲁尼亚大学）；CITIC-Research Center of Information and Communication Technologies（科蒂克信息与通信技术研究中心）
The analysis of different image modalities is frequently performed in ophthalmology as it provides complementary information for the diagnosis and follow-up of relevant diseases, like hypertension or diabetes. This work presents a hybrid method for the multimodal registration of color fundus retinography and fluorescein angiography. The proposed method combines a feature-based approach, using domain-specific landmarks, with an intensity-based approach that employs a domain-adapted similarity metric. The methodology is tested on a dataset of 59 image pairs containing both healthy and pathologic…
We address the problem of vehicle self-localization from multi-modal sensor information and a reference map. The map is generated off-line by extracting landmarks from the vehicle's field of view, while the measurements are collected similarly on the fly. Our goal is to determine the autonomous vehicle's pose from the landmark measurements and map landmarks. To learn this mapping, we propose DeepLocalization, a deep neural network that regresses the vehicle's translation and rotation parameters from unordered and dynamic input landmarks. The proposed network architecture is robust to changes o…
Zhongnan University of Economics and Law（中南财经政法大学）；Shenzhen University（深圳大学）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）；University of Alberta（阿尔伯塔大学）；Systems Research Institute, Polish Academy of Sciences（波兰科学院系统研究所）；China Three Gorges University（三峡大学）
Current fully-supervised facial landmark detection methods have progressed rapidly and achieved remarkable performance. However, they still suffer when coping with faces under large poses and heavy occlusions for inaccurate facial shape constraints and insufficient labeled training samples. In this paper, we propose a semi-supervised framework, i.e., a Self-Calibrated Pose Attention Network (SCPAN) to achieve more robust and precise facial landmark detection in challenging scenarios. To be specific, a Boundary-Aware Landmark Intensity (BALI) field is proposed to model more effective facial sha…
H3DE-Net: Efficient and Accurate 3D Landmark Detection in Medical Imaging
School of Computer Science USTC（计算机科学学院 中国科学技术大学）；School of Computer Science（计算机科学学院）；Shanghai Jiao Tong University（上海交通大学）；ShanghaiTech University（上海科技大学）；Sciences College（科学学院）；School of Information Science, NENU（信息科学学院 南京师范大学）；Technical University of Munich (TUM)（慕尼黑技术大学）；Stanford University（斯坦福大学）
Tsinghua University（清华大学）；Huazhong University of Science and Technology（华中科技大学）
Unsupervised visual anomaly detection conveys practical significance in many scenarios and is a challenging task due to the unbounded definition of anomalies. Moreover, most previous methods are application-specific, and establishing a unified model for anomalies across application scenarios remains unsolved. This paper proposes a novel hybrid framework termed Siamese Transition Masked Autoencoders(ST-MAE) to handle various visual anomaly detection tasks uniformly via deep feature transition. Concretely, the proposed method first extracts hierarchical semantics features from a pre-trained deep…
Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）
In this paper, we propose a self-supervised learningmethod for multi-object pose estimation. 3D object under-standing from 2D image is a challenging task that infers ad-ditional dimension from reduced-dimensional information.In particular, the estimation of the 3D localization or orien-tation of an object requires precise reasoning, unlike othersimple clustering tasks such as object classification. There-fore, the scale of the training dataset becomes more cru-cial. However, it is challenging to obtain large amount of3D dataset since achieving 3D annotation is expensive andtime-consuming. If t…
We address the challenging problem of RGB image-based head pose estimation. We first reformulate head pose representation learning to constrain it to a bounded space. Head pose represented as vector projection or vector angles shows helpful to improving performance. Further, a ranking loss combined with MSE regression loss is proposed. The ranking loss supervises a neural network with paired samples of the same person and penalises incorrect ordering of pose prediction. Analysis on this new loss function suggests it contributes to a better local feature extractor, where features are generalise…
University of Oxford（牛津大学）；KTH Royal Institute of Technology（KTH皇家理工学院）；Scania AB（斯堪尼亚公司）
We present an efficient multi-sensor odometry system for mobile platforms that jointly optimizes visual, lidar, and inertial information within a single integrated factor graph. This runs in real-time at full framerate using fixed lag smoothing. To perform such tight integration, a new method to extract 3D line and planar primitives from lidar point clouds is presented. This approach overcomes the suboptimality of typical frame-to-frame tracking methods by treating the primitives as landmarks and tracking them over multiple scans. True integration of lidar features with standard visual feature…
The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）
Understanding fashion images has been advanced by benchmarks with rich annotations such as DeepFashion, whose labels include clothing categories, landmarks, and consumer-commercial image pairs. However, DeepFashion has nonnegligible issues such as single clothing-item per image, sparse landmarks (4~8 only), and no per-pixel masks, making it had significant gap from real-world scenarios. We fill in the gap by presenting DeepFashion2 to address these issues. It is a versatile benchmark of four tasks including clothes detection, pose estimation, segmentation, and retrieval. It has 801K clothing i…
Chalmers University of Technology（查尔姆斯理工大学）；Zenseact
Masked autoencoding has become a successful pretraining paradigm for Transformer models for text, images, and, recently, point clouds. Raw automotive datasets are suitable candidates for self-supervised pre-training as they generally are cheap to collect compared to annotations for tasks like 3D object detection (OD). However, the development of masked autoencoders for point clouds has focused solely on synthetic and indoor data. Consequently, existing methods have tailored their representations and models toward small and dense point clouds with homogeneous point densities. In this work, we s…
