Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT) pipelines. Unfortunately, they lack two key properties: objects are often split into parts and are not consistently tracked over time. In fact, state-of-the-art models achieve pixel-level accuracy and temporal consistency by relying on supervised object detection with additional ID labels for the association through time. This paper proposes a video object-centric model for MOT. It consists of an index-merge module that adapts the object-centric slots into detection outputs and an object memory module that builds complete object prototypes to handle occlusions. Benefited from object-centric learning, we only require sparse detection labels (0%-6.25%) for object localization and feature binding. Relying on our self-supervised Expectation-Maximization-inspired loss for object association, our approach requires no ID labels. Our experiments significantly narrow the gap between the existing object-centric model and the fully supervised state-of-the-art and outperform several unsupervised trackers.
Westlake University（西湖大学）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；The future network of intelligence institute (FNII)（未来网络智能研究院）；Shenzhen Research Institute of Big Data（深圳大数据研究院）
3D single object tracking (3D SOT) in LiDAR point clouds plays a crucial role in autonomous driving. Current approaches all follow the Siamese paradigm based on appearance matching. However, LiDAR point clouds are usually textureless and incomplete, which hinders effective appearance matching. Besides, previous methods greatly overlook the critical motion clues among targets. In this work, beyond 3D Siamese tracking, we introduce a motion-centric paradigm to handle 3D SOT from a new perspective. Following this paradigm, we propose a matching-free two-stage tracker M^2-Track. At the 1^st-stage,…
University of Washington（华盛顿大学）；Electronics and Telecommunications Research Institute（韩国电子通信研究院）
Multi-Object Tracking over humans has improved rapidly with the development of object detection and re-identification. However, multi-actor tracking over humans with similar appearance and nonlinear movement can still be very challenging even for the state-of-the-art tracking algorithm. Current motion-based tracking algorithms often use Kalman Filter to predict the motion of an object, however, its linear movement assumption can cause failure in tracking when the target is not moving linearly. And for multi-players tracking over the sports field, because the players in the same team are usuall…
Carnegie Mellon University（卡内基梅隆大学）；Shanghai AI Laboratory（上海人工智能实验室）；Nvidia（英伟达）
Kalman filter (KF) based methods for multi-object tracking (MOT) make an assumption that objects move linearly. While this assumption is acceptable for very short periods of occlusion, linear estimates of motion for prolonged time can be highly inaccurate. Moreover, when there is no measurement available to update Kalman filter parameters, the standard convention is to trust the priori state estimations for posteriori update. This leads to the accumulation of errors during a period of occlusion. The error causes significant motion direction variance in practice. In this work, we show that a ba…
View-Centric Multi-Object Tracking with Homographic Matching in Moving UAV
MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China（脑启发智能感知与认知教育部重点实验室，中国科学技术大学）；Singapore University of Technology and Design（新加坡科技设计大学）；Alibaba Group（阿里巴巴集团）；Department of Computer Science and Engineering, Shanghai Jiao Tong University（上海交通大学计算机科学与工程系）
Estimating the target extent poses a fundamental challenge in visual object tracking. Typically, trackers are box-centric and fully rely on a bounding box to define the target in the scene. In practice, objects often have complex shapes and are not aligned with the image axis. In these cases, bounding boxes do not provide an accurate description of the target and often contain a majority of background pixels. We propose a segmentation-centric tracking pipeline that not only produces a highly accurate segmentation mask, but also internally works with segmentation masks instead of bounding boxes…
VOVTrack: Exploring the Potentiality in Videos for Open-Vocabulary Object Tracking
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；City University of Hong Kong（香港城市大学）
The Ohio State University（俄亥俄州立大学）；Google Research（谷歌研究院）；University of Southern California（南加州大学）
Many objects do not appear frequently enough in complex scenes (e.g., certain handbags in living rooms) for training an accurate object detector, but are often found frequently by themselves (e.g., in product images). Yet, these object-centric images are not effectively leveraged for improving object detection in scene-centric images. In this paper, we propose Mosaic of Object-centric images as Scene-centric images (MosaicOS), a simple and novel framework that is surprisingly effective at tackling the challenges of long-tailed object detection. Keys to our approach are three-fold: (i) pseudo s…
The objective of this work is to learn an object-centric video representation, with the aim of improving transferability to novel tasks, i.e., tasks different from the pre-training task of action classification. To this end, we introduce a new object-centric video recognition model based on a transformer architecture. The model learns a set of object-centric summary vectors for the video, and uses these vectors to fuse the visual and spatio-temporal trajectory 'modalities' of the video clip. We also introduce a novel trajectory contrast loss to further enhance objectness in these summary vecto…
Top-Down Guidance for Learning Object-Centric Representations
MAIS, Institute of Automation, Chinese Academy of Sciences（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）；CAIR, HKSIS, Chinese Academy of Sciences（中国科学院计算机研究所）；School of Computer Science and Engineering, the Faculty of Innovation Engineering, M.U.S.T（澳门科技大学计算机科学与工程学院）
University of Göttingen（哥廷根大学）；University of Tübingen（蒂宾根大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Bernstein Center for Computational Neuroscience（伯恩斯坦计算神经科学中心）；Campus Institute Data Science（校园数据科学研究所）；Max Planck Institute for Dynamics and Self-Organization（马克斯·普朗克动力学与自组织研究所）
Perceiving the world in terms of objects and tracking them through time is a crucial prerequisite for reasoning and scene understanding. Recently, several methods have been proposed for unsupervised learning of object-centric representations. However, since these models were evaluated on different downstream tasks, it remains unclear how they compare in terms of basic perceptual abilities such as detection, figure-ground segmentation and tracking of objects. To close this gap, we design a benchmark with four data sets of varying complexity and seven additional test sets featuring challenging t…
Reconstructing 3D objects is an important computer vision task that has wide application in AR/VR. Deep learning algorithm developed for this task usually relies on an unrealistic synthetic dataset, such as ShapeNet and Things3D. On the other hand, existing real-captured object-centric datasets usually do not have enough annotation to enable supervised training or reliable evaluation. In this technical report, we present a photo-realistic object-centric dataset HM3D-ABO. It is constructed by composing realistic indoor scene and realistic object. For each configuration, we provide multi-view RG…
Object-Centric Data Synthesis for Category-level Object Detection
University of Richmond（里士满大学）；University of California, Los Angeles（加州大学洛杉矶分校）；University of California, Berkeley（加州大学伯克利分校）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Analog Devices, Inc（安森科技公司）
3D object detection has recently become popular due to many applications in robotics, augmented reality, autonomy, and image retrieval. We introduce the Objectron dataset to advance the state of the art in 3D object detection and foster new research and applications, such as 3D object tracking, view synthesis, and improved 3D shape representation. The dataset contains object-centric short videos with pose annotations for nine categories and includes 4 million annotated images in 14,819 annotated videos. We also propose a new evaluation metric, 3D Intersection over Union, for 3D object detectio…
Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；School of Electronic Engineering, Xidian University（西安电子科技大学电子工程学院）；Peng Cheng Laboratory（鹏城实验室）
Hand-Centric Motion Refinement for 3D Hand-Object Interaction via Hierarchical Spatial-Temporal Modeling
Zhejiang University（浙江大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东省科学院）山东省人工智能研究院）
We tackle the problem of object-centric learning on point clouds, which is crucial for high-level relational reasoning and scalable machine intelligence. In particular, we introduce a framework, SPAIR3D, to factorize a 3D point cloud into a spatial mixture model where each component corresponds to one object. To model the spatial mixture model on point clouds, we derive the Chamfer Mixture Loss, which fits naturally into our variational training pipeline. Moreover, we adopt an object-specification scheme that describes each object's location relative to its local voxel grid cell. Such a scheme…
University of Adelaide（阿德莱德大学）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）；Monash University（莫纳什大学）
Semantic aware reconstruction is more advantageous than geometric-only reconstruction for future robotic and AR/VR applications because it represents not only where things are, but also what things are. Object-centric mapping is a task to build an object-level reconstruction where objects are separate and meaningful entities that convey both geometry and semantic information. In this paper, we present MOLTR, a solution to object-centric mapping using only monocular image sequences and camera poses. It is able to localise, track, and reconstruct multiple objects in an online fashion when an RGB…
Self-supervision allows learning meaningful representations of natural images, which usually contain one central object. How well does it transfer to multi-entity scenes? We discuss key aspects of learning structured object-centric representations with self-supervision and validate our insights through several experiments on the CLEVR dataset. Regarding the architecture, we confirm the importance of competition for attention-based object discovery, where each image patch is exclusively attended by one object. For training, we show that contrastive losses equipped with matching can be applied d…
Samsung Advanced Institute of Technology（三星先进技术研究院）
Human is one of the most essential classes in visual recognition tasks such as detection, segmentation, and pose estimation. Although much effort has been put into individual tasks, multi-task learning for these three tasks has been rarely studied. In this paper, we explore a compact multi-task network architecture that maximally shares the parameters of the multiple tasks via object-centric learning. To this end, we propose a novel query design to encode the human instance information effectively, called human-centric query (HCQ). HCQ enables for the query to learn explicit and structural inf…
We present an approach for aggregating a sparse set of views of an object in order to compute a semi-implicit 3D representation in the form of a volumetric feature grid. Key to our approach is an object-centric canonical 3D coordinate system into which views can be lifted, without explicit camera pose estimation, and then combined -- in a manner that can accommodate a variable number of views and is view order independent. We show that computing a symmetry-aware mapping from pixels to the canonical coordinate system allows us to better propagate information to unseen regions, as well as to rob…
In this work, we present Patch-based Object-centric Video Transformer (POVT), a novel region-based video generation architecture that leverages object-centric information to efficiently model temporal dynamics in videos. We build upon prior work in video prediction via an autoregressive transformer over the discrete latent space of compressed videos, with an added modification to model object-centric information via bounding boxes. Due to better compressibility of object-centric representations, we can improve training efficiency by allowing the model to only access object information for long…
