In this paper, we consider a task of stopping the video stream recognition process of a text field, in which each frame is recognized independently and the individual results are combined together. The video stream recognition stopping problem is an under-researched topic with regards to computer vision, but its relevance for building high-performance video recognition systems is clear.
Firstly, we describe an existing method of optimally stopping such a process based on a modelling of the next combined result. Then, we describe approximations and assumptions which allowed us to build an optimized computation scheme and thus obtain a method with reduced computational complexity.
The methods were evaluated for the tasks of document text field recognition and arbitrary text recognition in a video. The experimental comparison shows that the introduced approximations do not diminish the quality of the stopping method in terms of the achieved combined result precision, while dramatically reducing the time required to make the stopping decision. The results were consistent for both text recognition tasks.
Moscow Institute of Physics and Technology “MIPT”（莫斯科物理技术学院）；Smart Engines（智能引擎公司）；Federal Research Center “Computer Science and Control” of Russian Academy of Sciences（俄罗斯科学院计算机科学与控制联邦研究中心）
In the field of document analysis and recognition using mobile devices for capturing, and the field of object recognition in a video stream, an important problem is determining the time when the capturing process should be stopped. Efficient stopping influences not only the total time spent for performing recognition and data entry, but the expected accuracy of the result as well. This paper is directed on extending the stopping method based on next integrated recognition result modelling, in order for it to be used within a string result recognition model with per-character alternatives. The …
NICTA（澳大利亚国家信息与通信技术研究院）；University of Queensland（昆士兰大学）；Queensland University of Technology（昆士兰科技大学）
In this paper we propose a novel approach to multi-action recognition that performs joint segmentation and classification. This approach models each action using a Gaussian mixture using robust low-dimensional action features. Segmentation is achieved by performing classification on overlapping temporal windows, which are then merged to produce the final result. This approach is considerably less complicated than previous methods which use dynamic programming or computationally expensive hidden Markov models (HMMs). Initial experiments on a stitched version of the KTH dataset show that the pro…
University of Alcala（阿尔卡拉大学）；Polytechnic School（理工学院）；Computer Engineering Department（计算机工程系）
According to several reports published by worldwide organisations, thousands of pedestrians die in road accidents every year. Due to this fact, vehicular technologies have been evolving with the intent of reducing these fatalities. This evolution has not finished yet since, for instance, the predictions of pedestrian paths could improve the current Automatic Emergency Braking Systems (AEBS). For this reason, this paper proposes a method to predict future pedestrian paths, poses and intentions up to 1s in advance. This method is based on Balanced Gaussian Process Dynamical Models (B-GPDMs), whi…
In this report, our approach to tackling the task of ActivityNet 2018 Kinetics-600 challenge is described in detail. Though spatial-temporal modelling methods, which adopt either such end-to-end framework as I3D \cite{i3d} or two-stage frameworks (i.e., CNN+RNN), have been proposed in existing state-of-the-arts for this task, video modelling is far from being well solved. In this challenge, we propose spatial-temporal network (StNet) for better joint spatial-temporal modelling and comprehensively video understanding. Besides, given that multi-modal information is contained in video source, we …
Allen Institute for AI（艾伦人工智能研究所）；University of Michigan-Ann Arbor（密歇根大学安娜堡分校）；Stanford University（斯坦福大学）
Despite the fact that object detection, 3D pose estimation, and sub-category recognition are highly correlated tasks, they are usually addressed independently from each other because of the huge space of parameters. To jointly model all of these tasks, we propose a coarse-to-fine hierarchical representation, where each level of the hierarchy represents objects at a different level of granularity. The hierarchical representation prevents performance loss, which is often caused by the increase in the number of parameters (as we consider more tasks to model), and the joint modelling enables resol…
Harbin University of Science and Technology（哈尔滨理工大学）；University of Cambridge（剑桥大学）；University of Nottingham（诺丁汉大学）
Video-based automatic depression analysis provides a fast, objective and repeatable self-assessment solution, which has been widely developed in recent years. While depression clues may be reflected by human facial behaviours of various temporal scales, most existing approaches either focused on modelling depression from short-term or video-level facial behaviours. In this sense, we propose a two-stage framework that models depression severity from multi-scale short-term and video-level facial behaviours. The short-term depressive behaviour modelling stage first deep learns depression-related …
Recent adversarial learning research has achieved very impressive progress for modelling cross-domain data shifts in appearance space but its counterpart in modelling cross-domain shifts in geometry space lags far behind. This paper presents an innovative Geometry-Aware Domain Adaptation Network (GA-DAN) that is capable of modelling cross-domain shifts concurrently in both geometry space and appearance space and realistically converting images across domains with very different characteristics. In the proposed GA-DAN, a novel multi-modal spatial learning technique is designed which converts a …
Samsung AI Center Cambridge（三星剑桥人工智能中心）；University of Nottingham（诺丁汉大学）
Temporal context is key to the recognition of expressions of emotion. Existing methods, that rely on recurrent or self-attention models to enforce temporal consistency, work on the feature level, ignoring the task-specific temporal dependencies, and fail to model context uncertainty. To alleviate these issues, we build upon the framework of Neural Processes to propose a method for apparent emotion recognition with three key novel components: (a) probabilistic contextual representation with a global latent variable model; (b) temporal context modelling using task-specific predictions in additio…
Joint Multi-Condition Representation Modelling via Matrix Factorisation for Visual Place Recognition
School of Electronics and Computer Science, University of Southampton（苏塞克斯大学电子与计算机科学学院）；Department of Computer Science and Engineering, Hanyang University（翰阳大学计算机科学与工程系）；QUT Centre for Robotics, School of Electrical Engineering and Robotics（昆士兰大学机器人中心、电气工程与机器人学院）；School of Computer Science and Electronic Engineering, University of Essex（埃塞克斯大学计算机科学与电子工程学院）
Massachusetts Institute of Technology（麻省理工学院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research（IBM研究院）；Microsoft（微软）；Boston University（波士顿大学）
Temporal modelling is the key for efficient video action recognition. While understanding temporal information can improve recognition accuracy for dynamic actions, removing temporal redundancy and reusing past features can significantly save computation leading to efficient action recognition. In this paper, we introduce an adaptive temporal fusion network, called AdaFuse, that dynamically fuses channels from current and past feature maps for strong temporal modelling. Specifically, the necessary information from the historical convolution feature maps is fused with current pruned feature map…
Technische Universität München（慕尼黑工业大学）；Reutlingen University（罗伊特林根大学）；University of Surrey（萨里大学）
Face analysis techniques have become a crucial component of human-machine interaction in the fields of assistive and humanoid robotics. However, the variations in head-pose that arise naturally in these environments are still a great challenge. In this paper, we present a real-time capable 3D face modelling framework for 2D in-the-wild images that is applicable for robotics. The fitting of the 3D Morphable Model is based exclusively on automatically detected landmarks. After fitting, the face can be corrected in pose and transformed back to a frontal 2D representation that is more suitable for…
With the widespread of user-generated Internet videos, emotion recognition in those videos attracts increasing research efforts. However, most existing works are based on framelevel visual features and/or audio features, which might fail to model the temporal information, e.g. characteristics accumulated along time. In order to capture video temporal information, in this paper, we propose to analyse features in frequency domain transformed by discrete Fourier transform (DFT features). Frame-level features are firstly extract by a pre-trained deep convolutional neural network (CNN). Then, time …
Sequence-to-sequence models have recently become very popular for tackling handwritten word recognition problems. However, how to effectively integrate an external language model into such recognizer is still a challenging problem. The main challenge faced when training a language model is to deal with the language model corpus which is usually different to the one used for training the handwritten word recognition system. Thus, the bias between both word corpora leads to incorrectness on the transcriptions, providing similar or even worse performances on the recognition task. In this work, we…
Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognition
Australian Institute for Machine Learning (AIML), University of Adelaide（阿德莱德大学澳大利亚机器学习研究所）；Stanford University（斯坦福大学）；Cornell University（康奈尔大学）；Cornell Tech（康奈尔理工学院）；University of Oxford（牛津大学）；St. Vincent’s Institute of Medical Research（圣文森特医学研究所）；Melbourne Integrative Genomics, The University of Melbourne（墨尔本大学墨尔本整合基因组学中心）；St Vincent’s Hospital Melbourne（墨尔本圣文森特医院）；Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey（萨里大学视觉、语音与信号处理中心）；The University of Adelaide（阿德莱德大学）
Recently, video classification attracts intensive research efforts. However, most existing works are based on framelevel visual features, which might fail to model the temporal information, e.g. characteristics accumulated along time. In order to capture video temporal information, we propose to analyse features in frequency domain transformed by discrete Fourier transform (DFT features). Frame-level features are firstly extract by a pre-trained deep convolutional neural network (CNN). Then, time domain features are transformed and interpolated into DFT features. CNN and DFT features are furth…
Daily life activities, such as eating and sleeping, are deeply influenced by a person's culture, hence generating differences in the way a same activity is performed by individuals belonging to different cultures. We argue that taking cultural information into account can improve the performance of systems for the automated recognition of human activities. We propose four different solutions to the problem and present a system which uses a Naive Bayes model to associate cultural information with semantic information extracted from still images. Preliminary experiments with a dataset of images …
This thesis focuses on video understanding for human action and interaction recognition. We start by identifying the main challenges related to action recognition from videos and review how they have been addressed by current methods. Based on these challenges, and by focusing on the temporal aspect of actions, we argue that current fixed-sized spatio-temporal kernels in 3D convolutional neural networks (CNNs) can be improved to better deal with temporal variations in the input. Our contributions are based on the enlargement of the convolutional receptive fields through the introduction of spa…
University of Arizona（亚利桑那大学）；Ohio State University（俄亥俄州立大学）
Gesture recognition and hand motion tracking are important tasks in advanced gesture based interaction systems. In this paper, we propose to apply a sliding windows filtering approach to sample the incoming streams of data from data gloves and a decision tree model to recognize the gestures in real time for a manual grafting operation of a vegetable seedling propagation facility. The sequence of these recognized gestures defines the tasks that are taking place, which helps to evaluate individuals' performances and to identify any bottlenecks in real time. In this work, two pairs of data gloves…
Mercedes-Benz R&D India（梅赛德斯-奔驰印度研发中心）；Indian Institute of Technology, Bombay（印度理工学院孟买分校）；Axogyan AI
Online and Early detection of gestures is crucial for building touchless gesture based interfaces. These interfaces should operate on a stream of video frames instead of the complete video and detect the presence of gestures at an earlier stage than post-completion for providing real time user experience. To achieve this, it is important to recognize the progression of the gesture across different stages so that appropriate responses can be triggered on reaching the desired execution stage. To address this, we propose a simple yet effective multi-task learning framework which models the progre…
A Tactical Behaviour Recognition Framework Based on Causal Multimodal Reasoning: A Study on Covert Audio-Video Analysis Combining GAN Structure Enhancement and Phonetic Accent Modelling
Dhurakij Pundit University（易三仓大学）；The University of Western Australia（西澳大利亚大学）；Association for Computing Machinery（美国计算机协会）；Royal Anthropological Institute（英国皇家人类学学会）
Shanghai Technical Institute of Electronics and Information（上海电子信息职业技术学院）
Human personality decides various aspects of their daily life and working behaviors. Since personality traits are relatively stable over time and unique for each subject, previous approaches frequently infer personality from a single frame or short-term behaviors. Moreover, most of them failed to specifically extract person-specific and unique cues for personality recognition. In this paper, we propose a novel video-based automatic personality traits recognition approach which consists of: (1) a \textbf{domain-specific facial behavior modelling} module that extracts personality-related multi-s…
In this work, our objective is to address the problems of generalization and flexibility for text recognition in documents. We introduce a new model that exploits the repetitive nature of characters in languages, and decouples the visual representation learning and linguistic modelling stages. By doing this, we turn text recognition into a shape matching problem, and thereby achieve generalization in appearance and flexibility in classes. We evaluate the new model on both synthetic and real datasets across different alphabets and show that it can handle challenges that traditional architecture…
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…
This paper proposes an interaction reasoning network for modelling spatio-temporal relationships between hands and objects in video. The proposed interaction unit utilises a Transformer module to reason about each acting hand, and its spatio-temporal relation to the other hand as well as objects being interacted with. We show that modelling two-handed interactions are critical for action recognition in egocentric video, and demonstrate that by using positionally-encoded trajectories, the network can better recognise observed interactions. We evaluate our proposal on EPIC-KITCHENS and Something…
We base our work on the teleosemantic modelling of concepts as abilities implementing the distinct functions of recognition and classification. Accordingly, we model two types of concepts - substance concepts suited for object recognition exploiting visual properties, and classification concepts suited for classification of substance concepts exploiting linguistically grounded properties. The goal in this paper is to demonstrate that object recognition can be construed as classification via visual properties, as distinct from work in mainstream computer vision. Towards that, we present an obje…
Fudan University（复旦大学）；Google Research（谷歌研究院）；University of Oxford（牛津大学）
Modelling long-range dependencies is critical for scene understanding tasks in computer vision. Although convolution neural networks (CNNs) have excelled in many vision tasks, they are still limited in capturing long-range structured relationships as they typically consist of layers of local kernels. A fully-connected graph, such as the self-attention operation in Transformers, is beneficial for such modelling, however, its computational overhead is prohibitive. In this paper, we propose a dynamic graph message passing network, that significantly reduces the computational complexity compared t…
In the deployment of scene-text spotting systems on mobile platforms, lightweight models with low computation are preferable. In concept, end-to-end (E2E) text spotting is suitable for such purposes because it performs text detection and recognition in a single model. However, current state-of-the-art E2E methods rely on heavy feature extractors, recurrent sequence modellings, and complex shape aligners to pursue accuracy, which means their computations are still heavy. We explore the opposite direction: How far can we go without bells and whistles in E2E text spotting? To this end, we propose…
We address the problem of spatio-temporal action detection in videos. Existing methods commonly either ignore temporal context in action recognition and localization, or lack the modelling of flexible shapes of action tubes. In this paper, we propose a two-stage action detector called Deformable Tube Network (DTN), which is composed of a Deformation Tube Proposal Network (DTPN) and a Deformable Tube Recognition Network (DTRN) similar to the Faster R-CNN architecture. In DTPN, a fast proposal linking algorithm (FTL) is introduced to connect region proposals across frames to generate multiple de…
Shanghai Jiao Tong University（上海交通大学）；Westone Cryptologic Research Center（卫士通密码研究中心）
In this paper, we propose Double Supervised Network with Attention Mechanism (DSAN), a novel end-to-end trainable framework for scene text recognition. It incorporates one text attention module during feature extraction which enforces the model to focus on text regions and the whole framework is supervised by two branches. One supervision branch comes from context-level modelling and another comes from one extra supervision enhancement branch which aims at tackling inexplicit semantic information at character level. These two supervisions can benefit each other and yield better performance. Th…
North University of China（中北大学）；Shandong University（山东大学）；University of Electronic Science and Technology of China（电子科技大学）；University of Wollongong（伍伦贡大学）
Pose based hand gesture recognition has been widely studied in the recent years. Compared with full body action recognition, hand gesture involves joints that are more spatially closely distributed with stronger collaboration. This nature requires a different approach from action recognition to capturing the complex spatial features. Many gesture categories, such as "Grab" and "Pinch", have very similar motion or temporal patterns posing a challenge on temporal processing. To address these challenges, this paper proposes a two-stream neural network with one stream being a self-attention based …
