In recent years, more and more videos are captured from the first-person viewpoint by wearable cameras. Such first-person video provides additional information besides the traditional third-person video, and thus has a wide range of applications. However, techniques for analyzing the first-person video can be fundamentally different from those for the third-person video, and it is even more difficult to explore the shared information from both viewpoints. In this paper, we propose a novel method for first- and third-person video co-analysis. At the core of our method is the notion of "joint attention", indicating the learnable representation that corresponds to the shared attention regions in different viewpoints and thus links the two viewpoints. To this end, we develop a multi-branch deep network with a triplet loss to extract the joint attention from the first- and third-person videos via self-supervised learning. We evaluate our method on the public dataset with cross-viewpoint video matching tasks. Our method outperforms the state-of-the-art both qualitatively and quantitatively. We also demonstrate how the learned joint attention can benefit various applications through a set of additional experiments.
Facebook AI Research（Facebook AI研究院）；UT Austin（德克萨斯大学奥斯汀分校）
We introduce an approach for pre-training egocentric video models using large-scale third-person video datasets. Learning from purely egocentric data is limited by low dataset scale and diversity, while using purely exocentric (third-person) data introduces a large domain mismatch. Our idea is to discover latent signals in third-person video that are predictive of key egocentric-specific properties. Incorporating these signals as knowledge distillation losses during pre-training results in models that benefit from both the scale and diversity of third-person video data, as well as representati…
Carnegie Mellon University（卡内基梅隆大学）；Inria（法国国家信息与自动化研究所）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Several theories in cognitive neuroscience suggest that when people interact with the world, or simulate interactions, they do so from a first-person egocentric perspective, and seamlessly transfer knowledge between third-person (observer) and first-person (actor). Despite this, learning such models for human action recognition has not been achievable due to the lack of data. This paper takes a step in this direction, with the introduction of Charades-Ego, a large-scale dataset of paired first-person and third-person videos, involving 112 people, with 4000 paired videos. This enables learning …
Indiana University Bloomington（印第安纳大学伯明顿分校）；University of California, Davis（加利福尼亚大学戴维斯分校）
We consider scenarios in which we wish to perform joint scene understanding, object tracking, activity recognition, and other tasks in environments in which multiple people are wearing body-worn cameras while a third-person static camera also captures the scene. To do this, we need to establish person-level correspondences across first- and third-person videos, which is challenging because the camera wearer is not visible from his/her own egocentric video, preventing the use of direct feature matching. In this paper, we propose a new semi-Siamese Convolutional Neural Network architecture to ad…
National Taiwan University（台湾大学）；National Chiao Tung University（国立交通大学）
Video highlight or summarization is among interesting topics in computer vision, which benefits a variety of applications like viewing, searching, or storage. However, most existing studies rely on training data of third-person videos, which cannot easily generalize to highlight the first-person ones. With the goal of deriving an effective model to summarize first-person videos, we propose a novel deep neural network architecture for describing and discriminating vital spatiotemporal information across videos with different points of view. Our proposed model is realized in a semi-supervised se…
Carnegie Mellon University（卡内基梅隆大学）；Inria（法国国家信息与自动化研究所）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
In Actor and Observer we introduced a dataset linking the first and third-person video understanding domains, the Charades-Ego Dataset. In this paper we describe the egocentric aspect of the dataset and present annotations for Charades-Ego with 68,536 activity instances in 68.8 hours of first and third-person video, making it one of the largest and most diverse egocentric datasets available. Charades-Ego furthermore shares activity classes, scripts, and methodology with the Charades dataset, that consist of additional 82.3 hours of third-person video with 66,500 activity instances. Charades-Eg…
In a world of pervasive cameras, public spaces are often captured from multiple perspectives by cameras of different types, both fixed and mobile. An important problem is to organize these heterogeneous collections of videos by finding connections between them, such as identifying correspondences between the people appearing in the videos and the people holding or wearing the cameras. In this paper, we wish to solve two specific problems: (1) given two or more synchronized third-person videos of a scene, produce a pixel-level segmentation of each visible person and identify corresponding peopl…
We focus on first-person action recognition from egocentric videos. Unlike third person domain, researchers have divided first-person actions into two categories: involving hand-object interactions and the ones without, and developed separate techniques for the two action categories. Further, it has been argued that traditional cues used for third person action recognition do not suffice, and egocentric specific features, such as head motion and handled objects have been used for such actions. Unlike the state-of-the-art approaches, we show that a regular two stream Convolutional Neural Networ…
We explore the problem of intersection classification using monocular on-board passive vision, with the goal of classifying traffic scenes with respect to road topology. We divide the existing approaches into two broad categories according to the type of input data: (a) first person vision (FPV) approaches, which use an egocentric view sequence as the intersection is passed; and (b) third person vision (TPV) approaches, which use a single view immediately before entering the intersection. The FPV and TPV approaches each have advantages and disadvantages. Therefore, we aim to combine them into …
Tianjin University（天津大学）；Zhengzhou University（郑州大学）；University of Wollongong（伍伦贡大学）
Analysis of human interaction is one important research topic of human motion analysis. It has been studied either using first person vision (FPV) or third person vision (TPV). However, the joint learning of both types of vision has so far attracted little attention. One of the reasons is the lack of suitable datasets that cover both FPV and TPV. In addition, existing benchmark datasets of either FPV or TPV have several limitations, including the limited number of samples, participant subjects, interaction categories, and modalities. In this work, we contribute a large-scale human interaction …
First-person (egocentric) and third person (exocentric) videos are drastically different in nature. The relationship between these two views have been studied in recent years, however, it has yet to be fully explored. In this work, we introduce two datasets (synthetic and natural/real) containing simultaneously recorded egocentric and exocentric videos. We also explore relating the two domains (egocentric and exocentric) in two aspects. First, we synthesize images in the egocentric domain from the exocentric domain using a conditional generative adversarial network (cGAN). We show that with en…
In this paper, a new video classification methodology is proposed which can be applied in both first and third person videos. The main idea behind the proposed strategy is to capture complementary information of appearance and motion efficiently by performing two independent streams on the videos. The first stream is aimed to capture long-term motions from shorter ones by keeping track of how elements in optical flow images have changed over time. Optical flow images are described by pre-trained networks that have been trained on large scale image datasets. A set of multi-channel time series a…
Institut de Robòtica i Informàtica Industrial, CSIC-UPC（西班牙国家研究委员会-加泰罗尼亚理工大学工业机器人与信息技术研究所）
In this paper, we propose a novel approach to enhance the 3D body pose estimation of a person computed from videos captured from a single wearable camera. The key idea is to leverage high-level features linking first- and third-views in a joint embedding space. To learn such embedding space we introduce First2Third-Pose, a new paired synchronized dataset of nearly 2,000 videos depicting human activities captured from both first- and third-view perspectives. We explicitly consider spatial- and motion-domain features, combined using a semi-Siamese architecture trained in a self-supervised fashio…
MIT（麻省理工学院）；Facebook AI Research（脸书人工智能研究院）；CMU（卡内基梅隆大学）
We study a generalized setup for learning from demonstration to build an agent that can manipulate novel objects in unseen scenarios by looking at only a single video of human demonstration from a third-person perspective. To accomplish this goal, our agent should not only learn to understand the intent of the demonstrated third-person video in its context but also perform the intended task in its environment configuration. Our central insight is to enforce this structure explicitly during learning by decoupling what to achieve (intended task) from how to perform it (controller). We propose a …
Humans learn to imitate by observing others. However, robot imitation learning generally requires expert demonstrations in the first-person view (FPV). Collecting such FPV videos for every robot could be very expensive. Third-person imitation learning (TPIL) is the concept of learning action policies by observing other agents in a third-person view (TPV), similar to what humans do. This ultimately allows utilizing human and robot demonstration videos in TPV from many different data sources, for the policy learning. In this paper, we present a TPIL approach for robot tasks with egomotion. Altho…
Learning to solve precision-based manipulation tasks from visual feedback using Reinforcement Learning (RL) could drastically reduce the engineering efforts required by traditional robot systems. However, performing fine-grained motor control from visual inputs alone is challenging, especially with a static third-person camera as often used in previous work. We propose a setting for robotic manipulation in which the agent receives visual feedback from both a third-person camera and an egocentric camera mounted on the robot's wrist. While the third-person camera is static, the egocentric camera…
Text-based person retrieval aims to find the query person based on a textual description. The key is to learn a common latent space mapping between visual-textual modalities. To achieve this goal, existing works employ segmentation to obtain explicitly cross-modal alignments or utilize attention to explore salient alignments. These methods have two shortcomings: 1) Labeling cross-modal alignments are time-consuming. 2) Attention methods can explore salient cross-modal alignments but may ignore some subtle and valuable pairs. To relieve these issues, we introduce an Implicit Visual-Textual (IVT…
University of Pennsylvania（宾夕法尼亚大学）；University of Minnesota（明尼苏达大学）；UC Berkeley（加州大学伯克利分校）；ICSI（国际计算机科学研究所）
Unlike traditional third-person cameras mounted on robots, a first-person camera, captures a person's visual sensorimotor object interactions from up close. In this paper, we study the tight interplay between our momentary visual attention and motor action with objects from a first-person camera. We propose a concept of action-objects---the objects that capture person's conscious visual (watching a TV) or tactile (taking a cup) interactions. Action-objects may be task-dependent but since many tasks share common person-object spatial configurations, action-objects exhibit a characteristic 3D sp…
DI ENS PSL（巴黎高等师范学院PSL计算机系）；Inria（法国国家信息与自动化研究所）；CIIRC, CTU in Prague（捷克技术大学布拉格人工智能中心）；LAAS-CNRS（法国国家科学研究中心系统分析与体系结构实验室）
In this paper, we introduce a method to automatically reconstruct the 3D motion of a person interacting with an object from a single RGB video. Our method estimates the 3D poses of the person and the object, contact positions, and forces and torques actuated by the human limbs. The main contributions of this work are three-fold. First, we introduce an approach to jointly estimate the motion and the actuation forces of the person on the manipulated object by modeling contacts and the dynamics of their interactions. This is cast as a large-scale trajectory optimization problem. Second, we develo…
University IUAV of Venice（威尼斯IUAV大学）；Ca’ Foscari University of Venice（威尼斯大学）；University of Parma（帕尔马大学）；University of Central Florida（中佛罗里达大学）
In this paper, a unified three-layer hierarchical approach for solving tracking problems in multiple non-overlapping cameras is proposed. Given a video and a set of detections (obtained by any person detector), we first solve within-camera tracking employing the first two layers of our framework and, then, in the third layer, we solve across-camera tracking by merging tracks of the same person in all cameras in a simultaneous fashion. To best serve our purpose, a constrained dominant sets clustering (CDSC) technique, a parametrized version of standard quadratic optimization, is employed to sol…
University of Technology Sydney（悉尼科技大学）；UTSA（得克萨斯大学圣安东尼奥分校）；USTC（中国科学技术大学）；UCSD（加利福尼亚大学圣迭戈分校）
We present a novel large-scale dataset and comprehensive baselines for end-to-end pedestrian detection and person recognition in raw video frames. Our baselines address three issues: the performance of various combinations of detectors and recognizers, mechanisms for pedestrian detection to help improve overall re-identification accuracy and assessing the effectiveness of different detectors for re-identification. We make three distinct contributions. First, a new dataset, PRW, is introduced to evaluate Person Re-identification in the Wild, using videos acquired through six synchronized camera…
See What You Seek: Semantic Contextual Integration for Cloth-Changing Person Re-Identification
Sanya Science and Education Innovation Park, Wuhan University of Technology（武汉理工大学三亚科学教育创新园）；Hubei Key Laboratory of Transportation Internet of Things, School of Computer Science and Artificial Intelligence, Wuhan University of Technology（武汉理工大学交通运输物联网重点实验室）；Hubei Key Laboratory of Big Data Intelligent Analysis and Application, School of Computer Science and Information Engineering, Hubei University（湖北大数据智能分析与应用重点实验室）；National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University（国家多媒体软件工程研究中心）；School of Computing, Macquarie University（麦考瑞大学计算机学院）；Rapid-Rich Object Search Lab, School of Electrical and Electronic Engineering, Nanyang Technological University（快速富对象搜索实验室）
We propose and investigate an identity sensitive joint embedding of face and voice. Such an embedding enables cross-modal retrieval from voice to face and from face to voice. We make the following four contributions: first, we show that the embedding can be learnt from videos of talking faces, without requiring any identity labels, using a form of cross-modal self-supervision; second, we develop a curriculum learning schedule for hard negative mining targeted to this task, that is essential for learning to proceed successfully; third, we demonstrate and evaluate cross-modal retrieval for ident…
Chongqing University（重庆大学）；Hefei University of Technology（合肥工业大学）
This paper proposes a pedestrian detection and re-identification (re-id) integration net (I-Net) in an end-to-end learning framework. The I-Net is used in real-world video surveillance scenarios, where the target person needs to be searched in the whole scene videos, while the annotations of pedestrian bounding boxes are unavailable. By comparing to the OIM which is a work for joint detection and re-id, we have three distinct contributions. First, we introduce a Siamese architecture of I-Net instead of 1 stream, such that a verification task can be implemented. Second, we propose a novel on-li…
Egocentric videos are characterised by their ability to have the first person view. With the popularity of Google Glass and GoPro, use of egocentric videos is on the rise. Recognizing action of the wearer from egocentric videos is an important problem. Unstructured movement of the camera due to natural head motion of the wearer causes sharp changes in the visual field of the egocentric camera causing many standard third person action recognition techniques to perform poorly on such videos. Objects present in the scene and hand gestures of the wearer are the most important cues for first person…
Interaction group detection has been previously addressed with bottom-up approaches which relied on the position and orientation information of individuals. These approaches were primarily based on pairwise affinity matrices and were limited to static, third-person views. This problem can greatly benefit from a holistic approach based on Graph Neural Networks (GNNs) beyond pairwise relationships, due to the inherent spatial configuration that exists between individuals who form interaction groups. Our proposed method, GROup detection With Link prediction (GROWL), demonstrates the effectiveness…
SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions
The University of Hong Kong（香港大学）；Carnegie Mellon University（卡内基梅隆大学）；Johns Hopkins University（约翰霍普金斯大学）；University of California Irvine（加州大学尔湾分校）；Stanford University（斯坦福大学）
Bharati Vidyapeeth’s College of Engineering（巴拉蒂维迪亚佩斯工程学院）
In this paper, we propose a novel pipeline for the 3D reconstruction of the full body from egocentric viewpoints. 3-D reconstruction of the human body from egocentric viewpoints is a challenging task as the view is skewed and the body parts farther from the cameras are occluded. One such example is the view from cameras installed below VR headsets. To achieve this task, we first make use of conditional GANs to translate the egocentric views to full body third-person views. This increases the comprehensibility of the image and caters to occlusions. The generated third-person view is further sen…
Crowd management relies on inspection of surveillance video either by operators or by object detection models. These models are large, making it difficult to deploy them on resource constrained edge hardware. Instead, the computations are often offloaded to a (third party) cloud platform. While crowd management may be a legitimate application, transferring video from the camera to remote infrastructure may open the door for extracting additional information that are infringements of privacy, like person tracking or face recognition. In this paper, we use adversarial training to obtain a lightw…
I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning
Beijing Jiaotong University（北京交通大学）；HUJING Digital Media & Entertainment Group（汇晶数字媒体与娱乐集团）；MAIS Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所MAIS）
We study how the choice of visual perspective affects learning and generalization in the context of physical manipulation from raw sensor observations. Compared with the more commonly used global third-person perspective, a hand-centric (eye-in-hand) perspective affords reduced observability, but we find that it consistently improves training efficiency and out-of-distribution generalization. These benefits hold across a variety of learning algorithms, experimental settings, and distribution shifts, and for both simulated and real robot apparatuses. However, this is only the case when hand-cen…
