We present a framework capable of tackilng the problem of continual object recognition in a setting which resembles that under whichhumans see and learn. This setting has a set of unique characteristics:it assumes an egocentric point-of-view bound to the needs of a singleperson, which implies a relatively low diversity of data and a coldstart with no data; it requires to operate in an open world, where newobjects can be encounteredat any time; supervision is scarce and hasto be solicited to the user, and completelyunsupervised recognitionof new objects should be possible. Note that this setting differs fromthe one addressed in the open world recognition literature, where supervised feedback is always requested to be able to incorporate newobjects. We propose a first solution to this problem in the form ofa memory-based incremental framework that is capable of storinginformation of each and any object it encounters, while using the supervision of the user to learn to discriminate between known and unknown objects. Our approach is based on four main features: the useof time and space persistence (i.e., the appearance of objects changesrelatively slowly), the use of similarity as the main driving principlefor object recognition and novelty detection, the progressive introduction of new objects in a developmental fashion and the selectiveelicitation of user feedback in an online active learning fashion. Experimental results show the feasibility of open world, generic objectrecognition, the ability to recognize, memorize and re-identify newobjects even in complete absence of user supervision, and the utilityof persistence and incrementality in boosting performance.
University of Bologna（博洛尼亚大学）；Meta AI；KU Leuven（鲁汶大学）；ServiceNow Research（ServiceNow研究院）
Continual Learning, also known as Lifelong or Incremental Learning, has recently gained renewed interest among the Artificial Intelligence research community. Recent research efforts have quickly led to the design of novel algorithms able to reduce the impact of the catastrophic forgetting phenomenon in deep neural networks. Due to this surge of interest in the field, many competitions have been held in recent years, as they are an excellent opportunity to stimulate research in promising directions. This paper summarizes the ideas, design choices, rules, and results of the challenge held at th…
University of Groningen（格罗宁根大学）；University of Barcelona（巴塞罗那大学）；Computer Vision Center（计算机视觉中心）
Nowadays, there is an upsurge of interest in using lifelogging devices. Such devices generate huge amounts of image data; consequently, the need for automatic methods for analyzing and summarizing these data is drastically increasing. We present a new method for familiar scene recognition in egocentric videos, based on background pattern detection through automatically configurable COSFIRE filters. We present some experiments over egocentric data acquired with the Narrative Clip.
University of Barcelona（巴塞罗那大学）；Computer Vision Centre（计算机视觉中心）
Recently, there has been a growing interest in analyzing human daily activities from data collected by wearable cameras. Since the hands are involved in a vast set of daily tasks, detecting hands in egocentric images is an important step towards the recognition of a variety of egocentric actions. However, besides extreme illumination changes in egocentric images, hand detection is not a trivial task because of the intrinsic large variability of hand appearance. We propose a hand detector that exploits skin modeling for fast hand proposal generation and Convolutional Neural Networks for hand re…
Carnegie Mellon University（卡内基梅隆大学）；Microsoft Research（微软研究院）；University of Texas, Austin（德克萨斯大学奥斯汀分校）
Online continual learning from data streams in dynamic environments is a critical direction in the computer vision field. However, realistic benchmarks and fundamental studies in this line are still missing. To bridge the gap, we present a new online continual object detection benchmark with an egocentric video dataset, Objects Around Krishna (OAK). OAK adopts the KrishnaCAM videos, an ego-centric video stream collected over nine months by a graduate student. OAK provides exhaustive bounding box annotations of 80 video snippets (~17.5 hours) for 105 object categories in outdoor scenes. The eme…
University of Colorado, Boulder（科罗拉多大学博尔德分校）；Facebook Reality Labs（Facebook现实实验室）
Although there has been significant research in egocentric action recognition, most methods and tasks, including EPIC-KITCHENS, suppose a fixed set of action classes. Fixed-set classification is useful for benchmarking methods, but is often unrealistic in practical settings due to the compositionality of actions, resulting in a functionally infinite-cardinality label set. In this work, we explore generalization with an open set of classes by unifying two popular approaches: few- and zero-shot generalization (the latter which we reframe as cross-modal few-shot generalization). We propose a new …
This paper presents a framework for recognition of human activity from egocentric video and eye tracking data obtained from a head-mounted eye tracker. Three channels of information such as eye movement, ego-motion, and visual features are combined for the classification of activities. Image features were extracted using a pre-trained convolutional neural network. Eye and ego-motion are quantized, and the windowed histograms are used as the features. The combination of features obtains better accuracy for activity classification as compared to individual features.
University of Barcelona（巴塞罗那大学）；Computer Vision Center（计算机视觉中心）；Universitat Autónoma de Barcelona（巴塞罗那自治大学）
Event boundaries play a crucial role as a pre-processing step for detection, localization, and recognition tasks of human activities in videos. Typically, although their intrinsic subjectiveness, temporal bounds are provided manually as input for training action recognition algorithms. However, their role for activity recognition in the domain of egocentric photostreams has been so far neglected. In this paper, we provide insights of how automatically computed boundaries can impact activity recognition results in the emerging domain of egocentric photostreams. Furthermore, we collected a new a…
University of Groningen（格罗宁根大学）；University of Barcelona（巴塞罗那大学）；Computer Vision Center（计算机视觉中心）
Lifelogging is a process of collecting rich source of information about daily life of people. In this paper, we introduce the problem of sentiment analysis in egocentric events focusing on the moments that compose the images recalling positive, neutral or negative feelings to the observer. We propose a method for the classification of the sentiments in egocentric pictures based on global and semantic image features extracted by Convolutional Neural Networks. We carried out experiments on an egocentric dataset, which we organized in 3 classes on the basis of the sentiment that is recalled to th…
Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；University of Trento（特伦托大学）；Computer Vision Center（计算机视觉中心）；Universitat de Barcelona（巴塞罗那大学）
Egocentric activity recognition is one of the most challenging tasks in video analysis. It requires a fine-grained discrimination of small objects and their manipulation. While some methods base on strong supervision and attention mechanisms, they are either annotation consuming or do not take spatio-temporal patterns into account. In this paper we propose LSTA as a mechanism to focus on features from spatial relevant parts while attention is being tracked smoothly across the video sequence. We demonstrate the effectiveness of LSTA on egocentric activity recognition with an end-to-end trainabl…
Singapore University of Technology and Design（新加坡科技设计大学）；Institute for Infocomm Research（新加坡资讯通信研究院）
With the increasing availability of wearable devices, research on egocentric activity recognition has received much attention recently. In this paper, we build a Multimodal Egocentric Activity dataset which includes egocentric videos and sensor data of 20 fine-grained and diverse activity categories. We present a novel strategy to extract temporal trajectory-like features from sensor data. We propose to apply the Fisher Kernel framework to fuse video and temporal enhanced sensor features. Experiment results show that with careful design of feature extraction and fusion algorithm, sensor data c…
Mobile virtual reality (VR) head mounted displays (HMD) have become popular among consumers in recent years. In this work, we demonstrate real-time egocentric hand gesture detection and localization on mobile HMDs. Our main contributions are: 1) A novel mixed-reality data collection tool to automatic annotate bounding boxes and gesture labels; 2) The largest-to-date egocentric hand gesture and bounding box dataset with more than 400,000 annotated frames; 3) A neural network that runs real time on modern mobile CPUs, and achieves higher than 76% precision on gesture recognition across 8 classes…
Sun Yat-sen University（中山大学）；Peng Cheng Laboratory（鹏城实验室）
Egocentric interaction recognition aims to recognize the camera wearer's interactions with the interactor who faces the camera wearer in egocentric videos. In such a human-human interaction analysis problem, it is crucial to explore the relations between the camera wearer and the interactor. However, most existing works directly model the interactions as a whole and lack modeling the relations between the two interacting persons. To exploit the strong relations for egocentric interaction recognition, we introduce a dual relation modeling framework which learns to model the relations between th…
Egocentric activity recognition in first-person videos has an increasing importance with a variety of applications such as lifelogging, summarization, assisted-living and activity tracking. Existing methods for this task are based on interpretation of various sensor information using pre-determined weights for each feature. In this work, we propose a new framework for egocentric activity recognition problem based on combining audio-visual features with multi-kernel learning (MKL) and multi-kernel boosting (MKBoost). For that purpose, firstly grid optical-flow, virtual-inertia feature, log-cova…
Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；University of Trento（特伦托大学）
In this paper we propose an end-to-end trainable deep neural network model for egocentric activity recognition. Our model is built on the observation that egocentric activities are highly characterized by the objects and their locations in the video. Based on this, we develop a spatial attention mechanism that enables the network to attend to regions containing objects that are correlated with the activity under consideration. We learn highly specialized attention maps for each frame using class-specific activations from a CNN pre-trained for generic image recognition, and use them for spatio-…
University of Bristol（布里斯托大学）；University of Oxford（牛津大学）
We focus on multi-modal fusion for egocentric action recognition, and propose a novel architecture for multi-modal temporal-binding, i.e. the combination of modalities within a range of temporal offsets. We train the architecture with three modalities -- RGB, Flow and Audio -- and combine them with mid-level fusion alongside sparse temporal sampling of fused representations. In contrast with previous works, modalities are fused before temporal aggregation, with shared modality and fusion weights over time. Our proposed architecture is trained end-to-end, outperforming individual modalities as …
Tianjin University（天津大学）；University of South Carolina（南卡罗来纳大学）
With the development of Augmented Reality (AR), egocentric action recognition (EAR) plays important role in accurately understanding demands from the user. However, EAR is designed to help recognize human-machine interaction in single egocentric view, thus difficult to capture interactions between two face-to-face AR users. Paired egocentric interaction recognition (PEIR) is the task to collaboratively recognize the interactions between two persons with the videos in their corresponding views. Unfortunately, existing PEIR methods always directly use linear decision function to fuse the feature…
University of California, Irvine（加州大学欧文分校）；Universidad de Zaragoza（萨拉戈萨大学）
We tackle the problem of estimating the 3D pose of an individual's upper limbs (arms+hands) from a chest mounted depth-camera. Importantly, we consider pose estimation during everyday interactions with objects. Past work shows that strong pose+viewpoint priors and depth-based features are crucial for robust performance. In egocentric views, hands and arms are observable within a well defined volume in front of the camera. We call this volume an egocentric workspace. A notable property is that hand appearance correlates with workspace location. To exploit this correlation, we classify arm+hand …
Korea University（高丽大学）；Purdue University（普渡大学）；Korea Electric Technology Institute（韩国电气技术研究院）；DigiCAP Inc.（DigiCAP公司）
We introduce a multi-stage framework that uses mean curvature on a hand surface and focuses on learning interaction between hand and object by analyzing hand grasp type for hand action recognition in egocentric videos. The proposed method does not require 3D information of objects including 6D object poses which are difficult to annotate for learning an object's behavior while it interacts with hands. Instead, the framework synthesizes the mean curvature of the hand mesh model to encode the hand surface geometry in 3D space. Additionally, our method learns the hand grasp type which is highly c…
University of Technology Sydney（悉尼科技大学）；Baidu Research（百度研究院）
Egocentric video recognition is a natural testbed for diverse interaction reasoning. Due to the large action vocabulary in egocentric video datasets, recent studies usually utilize a two-branch structure for action recognition, ie, one branch for verb classification and the other branch for noun classification. However, correlation studies between the verb and the noun branches have been largely ignored. Besides, the two branches fail to exploit local features due to the absence of a position-aware attention mechanism. In this paper, we propose a novel Symbiotic Attention framework leveraging …
University of Perugia（佩鲁贾大学）；Institut de Robòtica i Informàtica Industrial (CSIC-UPC)（机器人与工业信息研究所（西班牙国家研究委员会-加泰罗尼亚理工大学））
In this paper we propose a new framework to categorize social interactions in egocentric videos, we named InteractionGCN. Our method extracts patterns of relational and non-relational cues at the frame level and uses them to build a relational graph from which the interactional context at the frame level is estimated via a Graph Convolutional Network based approach. Then it propagates this context over time, together with first-person motion information, through a Gated Recurrent Unit architecture. Ablation studies and experimental evaluation on two publicly available datasets validate the pro…
Noldus Information Technology（诺达斯信息技术公司）；Utrecht University（乌得勒支大学）
In this work we employ multitask learning to capitalize on the structure that exists in related supervised tasks to train complex neural networks. It allows training a network for multiple objectives in parallel, in order to improve performance on at least one of them by capitalizing on a shared representation that is developed to accommodate more information than it otherwise would for a single task. We employ this idea to tackle action recognition in egocentric videos by introducing additional supervised tasks. We consider learning the verbs and nouns from which action labels consist of and …
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；Princeton University（普林斯顿大学）；Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）
Head-mounted device-based human-computer interaction often requires egocentric recognition of hand gestures and fingertips detection. In this paper, a unified approach of egocentric hand gesture recognition and fingertip detection is introduced. The proposed algorithm uses a single convolutional neural network to predict the probabilities of finger class and positions of fingertips in one forward propagation. Instead of directly regressing the positions of fingertips from the fully connected layer, the ensemble of the position of fingertips is regressed from the fully convolutional network. Su…
Politecnico di Torino（都灵理工大学）；Italian Institute of Technology（意大利技术研究院）；Consortium Cini（奇尼联盟）
To enable a safe and effective human-robot cooperation, it is crucial to develop models for the identification of human activities. Egocentric vision seems to be a viable solution to solve this problem, and therefore many works provide deep learning solutions to infer human actions from first person videos. However, although very promising, most of these do not consider the major challenges that comes with a realistic deployment, such as the portability of the model, the need for real-time inference, and the robustness with respect to the novel domains (i.e., new spaces, users, tasks). With th…
Capturing interaction of hands with objects is important to autonomously detect human actions from egocentric videos. In this work, we present a pyramid video transformer with a dynamic class token generator for egocentric action recognition. Different from previous video transformers, which use the same static embedding as the class token for diverse inputs, we propose a dynamic class token generator that produces a class token for each input video by analyzing the hand-object interaction and the related motion information. The dynamic class token can diffuse such information to the entire mo…
Natural interaction with virtual objects in AR/VR environments makes for a smooth user experience. Gestures are a natural extension from real world to augmented space to achieve these interactions. Finding discriminating spatio-temporal features relevant to gestures and hands in ego-view is the primary challenge for recognising egocentric gestures. In this work we propose a data driven end-to-end deep learning approach to address the problem of egocentric gesture recognition, which combines an ego-hand encoder network to find ego-hand features, and a recurrent neural network to discern tempora…
Advances in deep learning have enabled the development of models that have exhibited a remarkable tendency to recognize and even localize actions in videos. However, they tend to experience errors when faced with scenes or examples beyond their initial training environment. Hence, they fail to adapt to new domains without significant retraining with large amounts of annotated data. In this paper, we propose to overcome these limitations by moving to an open-world setting by decoupling the ideas of recognition and reasoning. Building upon the compositional representation offered by Grenander's …
University of Bristol（布里斯托大学）；Google Research（谷歌研究院）
In egocentric videos, actions occur in quick succession. We capitalise on the action's temporal context and propose a method that learns to attend to surrounding actions in order to improve recognition performance. To incorporate the temporal context, we propose a transformer-based multimodal model that ingests video and audio as input modalities, with an explicit language model providing action sequence context to enhance the predictions. We test our approach on EPIC-KITCHENS and EGTEA datasets reporting state-of-the-art performance. Our ablations showcase the advantage of utilising temporal …
Meta AI；Georgia Institute of Technology（佐治亚理工学院）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Meta Reality Labs（Meta现实实验室）
Given a video captured from a first person perspective and the environment context of where the video is recorded, can we recognize what the person is doing and identify where the action occurs in the 3D space? We address this challenging problem of jointly recognizing and localizing actions of a mobile user on a known 3D map from egocentric videos. To this end, we propose a novel deep probabilistic model. Our model takes the inputs of a Hierarchical Volumetric Representation (HVR) of the 3D environment and an egocentric video, infers the 3D action location as a latent variable, and recognizes…
It is well known that human gaze carries significant information about visual attention. However, there are three main difficulties in incorporating the gaze data in an attention mechanism of deep neural networks: 1) the gaze fixation points are likely to have measurement errors due to blinking and rapid eye movements; 2) it is unclear when and how much the gaze data is correlated with visual attention; and 3) gaze data is not always available in many real-world situations. In this work, we introduce an effective probabilistic approach to integrate human gaze into spatiotemporal attention for …
GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition
School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；School of Computer Science, The University of Sydney（悉尼大学计算机科学学院）；Department of Computer Science and Technology, Nanjing University（南京大学计算机科学与技术系）；Artificial Intelligence Industrial Technology Research Institute, Nanjing Institute of Technology（南京工程学院人工智能产业技术研究院）
Samsung AI Center Cambridge（三星剑桥人工智能中心）；University of Surrey（萨里大学）
Learning an egocentric action recognition model from video data is challenging due to distractors (e.g., irrelevant objects) in the background. Further integrating object information into an action model is hence beneficial. Existing methods often leverage a generic object detector to identify and represent the objects in the scene. However, several important issues remain. Object class annotations of good quality for the target domain (dataset) are still required for learning good object representation. Besides, previous methods deeply couple the existing action models and need to retrain the…
Trinity College Dublin（都柏林圣三一学院）；Intel Labs China（英特尔中国研究院）
Egocentric gestures are the most natural form of communication for humans to interact with wearable devices such as VR/AR helmets and glasses. A major issue in such scenarios for real-world applications is that may easily become necessary to add new gestures to the system e.g., a proper VR system should allow users to customize gestures incrementally. Traditional deep learning methods require storing all previous class samples in the system and training the model again from scratch by incorporating previous samples and new samples, which costs humongous memory and significantly increases compu…
DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；Zhengzhou University（郑州大学）；University of Wollongong（伍伦贡大学）
In this paper, we propose a \textbf{Tr}ansformer-based RGB-D \textbf{e}gocentric \textbf{a}ction \textbf{r}ecognition framework, called Trear. It consists of two modules, inter-frame attention encoder and mutual-attentional fusion block. Instead of using optical flow or recurrent units, we adopt self-attention mechanism to model the temporal structure of the data from different modalities. Input frames are cropped randomly to mitigate the effect of the data redundancy. Features from each modality are interacted through the proposed fusion block and combined through a simple yet effective fusio…
Wearable cameras can gather large a\-mounts of image data that provide rich visual information about the daily activities of the wearer. Motivated by the large number of health applications that could be enabled by the automatic recognition of daily activities, such as lifestyle characterization for habit improvement, context-aware personal assistance and tele-rehabilitation services, we propose a system to classify 21 daily activities from photo-streams acquired by a wearable photo-camera. Our approach combines the advantages of a Late Fusion Ensemble strategy relying on convolutional neural …
The University of Hong Kong（香港大学）；Microsoft Research Asia（微软亚洲研究院）；TransGP；Texas A&M University（德克萨斯农工大学）
Understanding dynamic hand motions and actions from egocentric RGB videos is a fundamental yet challenging task due to self-occlusion and ambiguity. To address occlusion and ambiguity, we develop a transformer-based framework to exploit temporal information for robust estimation. Noticing the different temporal granularity of and the semantic correlation between hand pose estimation and action recognition, we build a network hierarchy with two cascaded transformer encoders, where the first one exploits the short-term temporal cue for hand pose estimation, and the latter aggregates per-frame po…
Politecnico di Torino（都灵理工大学）；CINI Consortium（CINI联盟）；Politecnico di Milano（米兰理工大学）
Event cameras are novel bio-inspired sensors, which asynchronously capture pixel-level intensity changes in the form of "events". Due to their sensing mechanism, event cameras have little to no motion blur, a very high temporal resolution and require significantly less power and memory than traditional frame-based cameras. These characteristics make them a perfect fit to several real-world applications such as egocentric action recognition on wearable devices, where fast camera motion and limited power challenge traditional vision sensors. However, the ever-growing field of event-based vision …
Given the growing trend of continual learning techniques for deep neural networks focusing on the domain of computer vision, there is a need to identify which of these generalizes well to other tasks such as human activity recognition (HAR). As recent methods have mostly been composed of loss regularization terms and memory replay, we provide a constituent-wise analysis of some prominent task-incremental learning techniques employing these on HAR datasets. We find that most regularization approaches lack substantial effect and provide an intuition of when they fail. Thus, we make the case that…
University of Barcelona（巴塞罗那大学）；Computer Vision Center（计算机视觉中心）
This paper proposes an approach to automatically categorize the social interactions of a user wearing a photo-camera 2fpm, by relying solely on what the camera is seeing. The problem is challenging due to the overwhelming complexity of social life and the extreme intra-class variability of social interactions captured under unconstrained conditions. We adopt the formalization proposed in Bugental's social theory, that groups human relations into five social domains with related categories. Our method is a new deep learning architecture that exploits the hierarchical structure of the label spac…
