In this technical report, we present our solution to localize a spatio-temporal person in an untrimmed video based on a sentence. We achieve the second vIOU(0.30025) in the HC-STVG track of the 3rd Person in Context(PIC) Challenge. Our solution contains three parts: 1) human attributes information is extracted from the sentence, it is helpful to filter out tube proposals in the testing phase and supervise our classifier to learn appearance information in the training phase. 2) we detect humans with YoloV5 and track humans based on the DeepSort framework but replace the original ReID network with FastReID. 3) a visual transformer is used to extract cross-modal representations for localizing a spatio-temporal tube of the target person.
Sun Yat-sen University（中山大学）；Tencent（腾讯）；Guangdong Province Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）
In this technical report, we introduce our solution to human-centric spatio-temporal video grounding task. We propose a concise and effective framework named STVGFormer, which models spatiotemporal visual-linguistic dependencies with a static branch and a dynamic branch. The static branch performs cross-modal understanding in a single frame and learns to localize the target object spatially according to intra-frame visual cues like object appearances. The dynamic branch performs cross-modal understanding across multiple frames. It learns to predict the starting and ending time of the target mo…
Beihang University（北京航空航天大学）；Sun Yat-sen University（中山大学）；Pazhou Lab（琶洲实验室）；ByteDance AI Lab（字节跳动人工智能实验室）；University of Sydney（悉尼大学）
In this work, we introduce a novel task - Humancentric Spatio-Temporal Video Grounding (HC-STVG). Unlike the existing referring expression tasks in images or videos, by focusing on humans, HC-STVG aims to localize a spatiotemporal tube of the target person from an untrimmed video based on a given textural description. This task is useful, especially for healthcare and security-related applications, where the surveillance videos can be extremely long but only a specific person during a specific period of time is concerned. HC-STVG is a video grounding task that requires both spatial (where) and…
University of Science and Technology of China（中国科学技术大学）；Huawei Cloud EI Product Department（华为云EI产品部）；Huawei Noah’s Ark Laboratory（华为诺亚方舟实验室）
Existing methods for person re-identification (Re-ID) are mostly based on supervised learning which requires numerous manually labeled samples across all camera views for training. Such a paradigm suffers the scalability issue since in real-world Re-ID application, it is difficult to exhaustively label abundant identities over multiple disjoint camera views. To this end, we propose a progressive deep learning method for unsupervised person Re-ID in the wild by Tracklet Association with Spatio-Temporal Regularization (TASTR). In our approach, we first collect tracklet data within each camera by…
Robust online multi-person tracking requires the correct associations of online detection responses with existing trajectories. We address this problem by developing a novel appearance modeling approach to provide accurate appearance affinities to guide data association. In contrast to most existing algorithms that only consider the spatial structure of human appearances, we exploit the temporal dynamic characteristics within temporal appearance sequences to discriminate different persons. The temporal dynamic makes a sufficient complement to the spatial structure of varying appearances in the…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；Osaka University（大阪大学）；Kyoto University（京都大学）；RIKEN, Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）
3D panoramic multi-person localization and tracking are prominent in many applications, however, conventional methods using LiDAR equipment could be economically expensive and also computationally inefficient due to the processing of point cloud data. In this work, we propose an effective and efficient approach at a low cost. First, we obtain panoramic videos with four normal cameras. Then, we transform human locations from a 2D panoramic image coordinate to a 3D panoramic camera coordinate using camera geometry and human bio-metric property (i.e., height). Finally, we generate 3D tracklets by…
In this work we propose an online multi person pose tracking approach which works on two consecutive frames $I_{t-1}$ and $I_t$. The general formulation of our temporal network allows to rely on any multi person pose estimation approach as spatial network. From the spatial network we extract image features and pose features for both frames. These features serve as input for our temporal model that predicts Temporal Flow Fields (TFF). These TFF are vector fields which indicate the direction in which each body joint is going to move from frame $I_{t-1}$ to frame $I_t$. This novel representation …
Online multi-object tracking is a fundamental problem in time-critical video analysis applications. A major challenge in the popular tracking-by-detection framework is how to associate unreliable detection results with existing tracks. In this paper, we propose to handle unreliable detection by collecting candidates from outputs of both detection and tracking. The intuition behind generating redundant candidates is that detection and tracks can complement each other in different scenarios. Detection results of high confidence prevent tracking drifts in the long term, and predictions of tracks …
Sunmi US Inc.（商米美国公司）；Shanghai Sunmi Technology Co., Ltd（上海商米科技有限公司）
Computer vision algorithms are being implemented across a breadth of industries to enable technological innovations. In this paper, we study the problem of computer vision based customer tracking in retail industry. To this end, we introduce a dataset collected from a camera in an office environment where participants mimic various behaviors of customers in a supermarket. In addition, we describe an illustrative example of the use of this dataset for tracking participants based on a head tracking model in an effort to minimize errors due to occlusion. Furthermore, we propose a model for recogn…
The automatization of Multi-Object Tracking becomes a demanding task in real unconstrained scenarios, where the algorithms have to deal with crowds, crossing people, occlusions, disappearances and the presence of visually similar individuals. In those circumstances, the data association between the incoming detections and their corresponding identities could miss some tracks or produce identity switches. In order to reduce these tracking errors, and even their propagation in further frames, this article presents a Deep Multi-Shot neural model for measuring the Degree of Appearance Similarity (…
Multi-person human pose estimation and tracking in the wild is important and challenging. For training a powerful model, large-scale training data are crucial. While there are several datasets for human pose estimation, the best practice for training on multi-dataset has not been investigated. In this paper, we present a simple network called Multi-Domain Pose Network (MDPN) to address this problem. By treating the task as multi-domain learning, our methods can learn a better representation for pose prediction. Together with prediction heads fine-tuning and multi-branch combination, it shows s…
Fraunhofer Center Machine Learning（弗劳恩霍夫机器学习中心）；Fraunhofer ITWM（弗劳恩霍夫工业数学研究所）；Institute for Machine Learning and Analytics (IMLA) Offenburg University（奥芬堡大学机器学习与分析研究所（IMLA））；University of Mannheim（曼海姆大学）
Multiple Object Tracking (MOT) is a long-standing task in computer vision. Current approaches based on the tracking by detection paradigm either require some sort of domain knowledge or supervision to associate data correctly into tracks. In this work, we present an unsupervised multiple object tracking approach based on visual features and minimum cost lifted multicuts. Our method is based on straight-forward spatio-temporal cues that can be extracted from neighboring frames in an image sequences without superivison. Clustering based on these cues enables us to learn the required appearance i…
SenseTime Research（商汤科技研究院）；The University of Sydney（悉尼大学）；SenseTime Computer Vision Research Group（商汤科技计算机视觉研究组）
We propose a unified framework for multi-person pose estimation and tracking. Our framework consists of two main components,~\ie~SpatialNet and TemporalNet. The SpatialNet accomplishes body part detection and part-level data association in a single frame, while the TemporalNet groups human instances in consecutive frames into trajectories. Specifically, besides body part detection heatmaps, SpatialNet also predicts the Keypoint Embedding (KE) and Spatial Instance Embedding (SIE) for body part association. We model the grouping procedure into a differentiable Pose-Guided Grouping (PGG) module t…
Current datasets for video-based person re-identification (re-ID) do not include structural knowledge in form of human pose annotations for the persons of interest. Nonetheless, pose information is very helpful to disentangle useful feature information from background or occlusion noise. Especially real-world scenarios, such as surveillance, contain a lot of occlusions in human crowds or by obstacles. On the other hand, video-based person re-ID can benefit other tasks such as multi-person pose tracking in terms of robust feature matching. For that reason, we present PoseTrackReID, a large-scal…
We propose a novel top-down approach that tackles the problem of multi-person human pose estimation and tracking in videos. In contrast to existing top-down approaches, our method is not limited by the performance of its person detector and can predict the poses of person instances not localized. It achieves this capability by propagating known person locations forward and backward in time and searching for poses in those regions. Our approach consists of three components: (i) a Clip Tracking Network that performs body joint detection and tracking simultaneously on small video clips; (ii) a Vi…
Microsoft Research Asia（微软亚洲研究院）；Huazhong University of Science and Technology（华中科技大学）
We present VoxelTrack for multi-person 3D pose estimation and tracking from a few cameras which are separated by wide baselines. It employs a multi-branch network to jointly estimate 3D poses and re-identification (Re-ID) features for all people in the environment. In contrast to previous efforts which require to establish cross-view correspondence based on noisy 2D pose estimates, it directly estimates and tracks 3D poses from a 3D voxel-based representation constructed from multi-view images. We first discretize the 3D space by regular voxels and compute a feature vector for each voxel by av…
A video can be represented as a sequence of tracklets, each spanning 10-20 frames, and associated with one entity (eg. a person). The task of \emph{Entity Discovery} in videos can be naturally posed as tracklet clustering. We approach this task by leveraging \emph{Temporal Coherence}(TC): the fundamental property of videos that each tracklet is likely to be associated with the same entity as its temporal neighbors. Our major contributions are the first Bayesian nonparametric models for TC at tracklet-level. We extend Chinese Restaurant Process (CRP) to propose TC-CRP, and further to Temporally…
Accurate whole-body multi-person pose estimation and tracking is an important yet challenging topic in computer vision. To capture the subtle actions of humans for complex behavior analysis, whole-body pose estimation including the face, body, hand and foot is essential over conventional body-only pose estimation. In this paper, we present AlphaPose, a system that can perform accurate whole-body pose estimation and tracking jointly while running in realtime. To this end, we propose several new techniques: Symmetric Integral Keypoint Regression (SIKR) for fast and fine localization, Parametric …
In this paper, we propose a novel effective light-weight framework, called LightTrack, for online human pose tracking. The proposed framework is designed to be generic for top-down pose tracking and is faster than existing online and offline methods. Single-person Pose Tracking (SPT) and Visual Object Tracking (VOT) are incorporated into one unified functioning entity, easily implemented by a replaceable single-person pose estimation module. Our framework unifies single-person pose tracking with multi-person identity association and sheds first light upon bridging keypoint tracking with object…
We present an online approach to efficiently and simultaneously detect and track the 2D pose of multiple people in a video sequence. We build upon Part Affinity Field (PAF) representation designed for static images, and propose an architecture that can encode and predict Spatio-Temporal Affinity Fields (STAF) across a video sequence. In particular, we propose a novel temporal topology cross-linked across limbs which can consistently handle body motions of a wide range of magnitudes. Additionally, we make the overall approach recurrent in nature, where the network ingests STAF heatmaps from pre…
University of Oxford（牛津大学）；École Polytechnique（巴黎综合理工学院）；CNRS（法国国家科学研究中心）；IP Paris（巴黎理工学院）
The objective of this work is person-clustering in videos -- grouping characters according to their identity. Previous methods focus on the narrower task of face-clustering, and for the most part ignore other cues such as the person's voice, their overall appearance (hair, clothes, posture), and the editing structure of the videos. Similarly, most current datasets evaluate only the task of face-clustering, rather than person-clustering. This limits their applicability to downstream applications such as story understanding which require person-level, rather than only face-level, reasoning. In t…
MPI for Informatics（马克斯·普朗克信息学研究所）；University of Bonn（波恩大学）；Amazon Research（亚马逊研究院）；Google Research（谷歌研究院）
Human poses and motions are important cues for analysis of videos with people and there is strong evidence that representations based on body pose are highly effective for a variety of tasks such as activity recognition, content retrieval and social signal processing. In this work, we aim to further advance the state of the art by establishing "PoseTrack", a new large-scale benchmark for video-based human pose estimation and articulated tracking, and bringing together the community of researchers working on visual human analysis. The benchmark encompasses three competition tracks focusing on i…
The Chinese University of Hong Kong（香港中文大学）；Tsinghua University（清华大学）；SenseTime Research（商汤科技研究院）
In real-world applications, e.g. law enforcement and video retrieval, one often needs to search a certain person in long videos with just one portrait. This is much more challenging than the conventional settings for person re-identification, as the search may need to be carried out in the environments different from where the portrait was taken. In this paper, we aim to tackle this challenge and propose a novel framework, which takes into account the identity invariance along a tracklet, thus allowing person identities to be propagated via both the visual and the temporal links. We also devel…
Both the tasks of multi-person human pose estimation and pose tracking in videos are quite challenging. Existing methods can be categorized into two groups: top-down and bottom-up approaches. In this paper, following the top-down approach, we aim to build a strong baseline system with three modules: human candidate detector, single-person pose estimator and human pose tracker. Firstly, we choose a generic object detector among state-of-the-art methods to detect human candidates. Then, the cascaded pyramid network is used to estimate the corresponding human pose. Finally, we use a flow-based po…
University of Science and Technology of China（中国科学技术大学）；University of Chinese Academy of Sciences（中国科学院大学）；Megvii Inc.(Face++)（旷视科技（Face++））
Video-based person re-identification (ReID) is a challenging problem, where some video tracks of people across non-overlapping cameras are available for matching. Feature aggregation from a video track is a key step for video-based person ReID. Many existing methods tackle this problem by average/maximum temporal pooling or RNNs with attention. However, these methods cannot deal with temporal dependency and spatial misalignment problems at the same time. We are inspired by video action recognition that involves the identification of different actions from video tracks. Firstly, we use 3D convo…
The City College of New York, City University（纽约市立大学纽约城市学院）；Microsoft（微软）；University of Pittsburgh（匹兹堡大学）
Using an ego-centric camera to do localization and tracking is highly needed for urban navigation and indoor assistive system when GPS is not available or not accurate enough. The traditional hand-designed feature tracking and estimation approach would fail without visible features. Recently, there are several works exploring to use context features to do localization. However, all of these suffer severe accuracy loss if given no visual context information. To provide a possible solution to this problem, this paper proposes a camera system with both ego-downward and third-static view to perfor…
Inria Paris（巴黎法国国立信息学及其自动化研究院）；ENS（巴黎高等师范学院）；CNRS（法国国家科学研究中心）；Inria Grenoble（格勒诺布尔法国国立信息学及其自动化研究院）；LJK（让·库隆实验室）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；National Research University Higher School of Economics（高等经济大学）
This paper addresses spatio-temporal localization of human actions in video. In order to localize actions in time, we propose a recurrent localization network (RecLNet) designed to model the temporal structure of actions on the level of person tracks. Our model is trained to simultaneously recognize and localize action classes in time and is based on two layer gated recurrent units (GRU) applied separately to two streams, i.e. appearance and optical flow streams. When used together with state-of-the-art person detection and tracking, our model is shown to improve substantially spatio-temporal …
Autonomous robotic systems operating in human environments must understand their surroundings to make accurate and safe decisions. In crowded human scenes with close-up human-robot interaction and robot navigation, a deep understanding requires reasoning about human motion and body dynamics over time with human body pose estimation and tracking. However, existing datasets either do not provide pose annotations or include scene types unrelated to robotic applications. Many datasets also lack the diversity of poses and occlusions found in crowded human scenes. To address this limitation we intro…
Indian Institute of Information Technology, Sri City（印度斯里卡特里信息技术学院）
3D animation of humans in action is quite challenging as it involves using a huge setup with several motion trackers all over the person's body to track the movements of every limb. This is time-consuming and may cause the person discomfort in wearing exoskeleton body suits with motion sensors. In this work, we present a trivial yet effective solution to generate 3D animation of multiple persons from a 2D video using deep learning. Although significant improvement has been achieved recently in 3D human pose estimation, most of the prior works work well in case of single person pose estimation …
Norwegian University of Science and Technology（挪威科技大学）；University of Imam Abdulrahman Bin Faisal（伊玛目·阿卜杜勒拉赫曼·本·费萨尔大学）；University of Ha'il（哈伊勒大学）；Hamad Bin Khalifa University（哈马德·本·哈利法大学）
For multi-target tracking, target representation plays a crucial rule in performance. State-of-the-art approaches rely on the deep learning-based visual representation that gives an optimal performance at the cost of high computational complexity. In this paper, we come up with a simple yet effective target representation for human tracking. Our inspiration comes from the fact that the human body goes through severe deformation and inter/intra occlusion over the passage of time. So, instead of tracking the whole body part, a relative rigid organ tracking is selected for tracking the human over…
Traditionally, audio-visual automatic speech recognition has been studied under the assumption that the speaking face on the visual signal is the face matching the audio. However, in a more realistic setting, when multiple faces are potentially on screen one needs to decide which face to feed to the A/V ASR system. The present work takes the recent progress of A/V ASR one step further and considers the scenario where multiple people are simultaneously on screen (multi-person A/V ASR). We propose a fully differentiable A/V ASR model that is able to handle multiple face tracks in a video. Instea…
