Indoor monitoring of people at their homes has become a popular application in Smart Health. With the advances in Machine Learning and hardware for embedded devices, new distributed approaches for Cyber-Physical Systems (CPSs) are enabled. Also, changing environments and need for cost reduction motivate novel reconfigurable CPS architectures. In this work, we propose an indoor monitoring reconfigurable CPS that uses embedded local nodes (Nvidia Jetson TX2). We embed Deep Learning architectures to address Human Action Recognition. Local processing at these nodes let us tackle some common issues: reduction of data bandwidth usage and preservation of privacy (no raw images are transmitted). Also real-time processing is facilitated since optimized nodes compute only its local video feed. Regarding the reconfiguration, a remote platform monitors CPS qualities and a Quality and Resource Management (QRM) tool sends commands to the CPS core to trigger its reconfiguration. Our proposal is an energy-aware system that triggers reconfiguration based on energy consumption for battery-powered nodes. Reconfiguration reduces up to 22% the local nodes energy consumption extending the device operating time, preserving similar accuracy with respect to the alternative with no reconfiguration.
In the last few years, compression of deep neural networks has become an important strand of machine learning and computer vision research. Deep models require sizeable computational complexity and storage, when used for instance for Human Action Recognition (HAR) from videos, making them unsuitable to be deployed on edge devices. In this paper, we address this issue and propose a method to effectively compress Recurrent Neural Networks (RNNs) such as Gated Recurrent Units (GRUs) and Long-Short-Term-Memory Units (LSTMs) that are used for HAR. We use a Variational Information Bottleneck (VIB) theory-based pruning approach to limit the information flow through the sequential cells of RNNs to a small subset. Further, we combine our pruning method with a specific group-lasso regularization technique that significantly improves compression. The proposed techniques reduce model parameters and memory footprint from latent representations, with little or no reduction in the validation accuracy while increasing the inference speed several-fold. We perform experiments on the three widely used Action Recognition datasets, viz. UCF11, HMDB51, and UCF101, to validate our approach. It is shown that our method achieves over 70 times greater compression than the nearest competitor with comparable accuracy for the task of action recognition on UCF11.
We introduce Knowledge Fusion Transformers for video action classification. We present a self-attention based feature enhancer to fuse action knowledge in 3D inception based spatio-temporal context of the video clip intended to be classified. We show, how using only one stream networks and with little or, no pretraining can pave the way for a performance close to the current state-of-the-art. Additionally, we present how different self-attention architectures used at different levels of the network can be blended-in to enhance feature representation. Our architecture is trained and evaluated on UCF-101 and Charades dataset, where it is competitive with the state of the art. It also exceeds by a large gap from single stream networks with no to less pretraining.
In recent years, many works in the video action recognition literature have shown that two stream models (combining spatial and temporal input streams) are necessary for achieving state of the art performance. In this paper we show the benefits of including yet another stream based on human pose estimated from each frame -- specifically by rendering pose on input RGB frames. At first blush, this additional stream may seem redundant given that human pose is fully determined by RGB pixel values -- however we show (perhaps surprisingly) that this simple and flexible addition can provide complementary gains. Using this insight, we then propose a new model, which we dub PERF-Net (short for Pose Empowered RGB-Flow Net), which combines this new pose stream with the standard RGB and flow based input streams via distillation techniques and show that our model outperforms the state-of-the-art by a large margin in a number of human action recognition datasets while not requiring flow or pose to be explicitly computed at inference time. The proposed pose stream is also part of the winner solution of the ActivityNet Kinetics Challenge 2020.
Event camera is an asynchronous, high frequency vision sensor with low power consumption, which is suitable for human action recognition task. It is vital to encode the spatial-temporal information of event data properly and use standard computer vision tool to learn from the data. In this work, we propose a timestamp image encoding 2D network, which takes the encoded spatial-temporal images of the event data as input and output the action label. Experiment results show that our method can achieve the same level of performance as those RGB-based benchmarks on real world action recognition, and also achieve the SOTA result on gesture recognition.
Generating human action proposals in untrimmed videos is an important yet challenging task with wide applications. Current methods often suffer from the noisy boundary locations and the inferior quality of confidence scores used for proposal retrieving. In this paper, we present BSN++, a new framework which exploits complementary boundary regressor and relation modeling for temporal proposal generation. First, we propose a novel boundary regressor based on the complementary characteristics of both starting and ending boundary classifiers. Specifically, we utilize the U-shaped architecture with nested skip connections to capture rich contexts and introduce bi-directional boundary matching mechanism to improve boundary precision. Second, to account for the proposal-proposal relations ignored in previous methods, we devise a proposal relation block to which includes two self-attention modules from the aspects of position and channel. Furthermore, we find that there inevitably exists data imbalanced problems in the positive/negative proposals and temporal durations, which harm the model performance on tail distributions. To relieve this issue, we introduce the scale-balanced re-sampling strategy. Extensive experiments are conducted on two popular benchmarks: ActivityNet-1.3 and THUMOS14, which demonstrate that BSN++ achieves the state-of-the-art performance. Not surprisingly, the proposed BSN++ ranked 1st place in the CVPR19 - ActivityNet challenge leaderboard on temporal action localization task.
Recent years have witnessed the significant progress of action recognition task with deep networks. However, most of current video networks require large memory and computational resources, which hinders their applications in practice. Existing knowledge distillation methods are limited to the image-level spatial domain, ignoring the temporal and frequency information which provide structural knowledge and are important for video analysis. This paper explores how to train small and efficient networks for action recognition. Specifically, we propose two distillation strategies in the frequency domain, namely the feature spectrum and parameter distribution distillations respectively. Our insight is that appealing performance of action recognition requires \textit{explicitly} modeling the temporal frequency spectrum of video features. Therefore, we introduce a spectrum loss that enforces the student network to mimic the temporal frequency spectrum from the teacher network, instead of \textit{implicitly} distilling features as many previous works. Second, the parameter frequency distribution is further adopted to guide the student network to learn the appearance modeling process from the teacher. Besides, a collaborative learning strategy is presented to optimize the training process from a probabilistic view. Extensive experiments are conducted on several action recognition benchmarks, such as Kinetics, Something-Something, and Jester, which consistently verify effectiveness of our approach, and demonstrate that our method can achieve higher performance than state-of-the-art methods with the same backbone.
Graph neural networks (GNN) are powerful models for many graph-structured tasks. Existing models often assume that the complete structure of the graph is available during training. In practice, however, graph-structured data is usually formed in a streaming fashion so that learning a graph continuously is often necessary. In this paper, we bridge GNN and lifelong learning by converting a continual graph learning problem to a regular graph learning problem so GNN can inherit the lifelong learning techniques developed for convolutional neural networks (CNN). We propose a new topology, the feature graph, which takes features as new nodes and turns nodes into independent graphs. This successfully converts the original problem of node classification to graph classification. In the experiments, we demonstrate the efficiency and effectiveness of feature graph networks (FGN) by continuously learning a sequence of classical graph datasets. We also show that FGN achieves superior performance in two applications, i.e., lifelong human action recognition with wearable devices and feature matching. To the best of our knowledge, FGN is the first method to bridge graph learning and lifelong learning via a novel graph topology. Source code is available at https://github.com/wang-chen/LGL
Human action recognition is an important problem in computer vision. It has a wide range of applications in surveillance, human-computer interaction, augmented reality, video indexing, and retrieval. The varying pattern of spatio-temporal appearance generated by human action is key for identifying the performed action. We have seen a lot of research exploring this dynamics of spatio-temporal appearance for learning a visual representation of human actions. However, most of the research in action recognition is focused on some common viewpoints, and these approaches do not perform well when there is a change in viewpoint. Human actions are performed in a 3-dimensional environment and are projected to a 2-dimensional space when captured as a video from a given viewpoint. Therefore, an action will have a different spatio-temporal appearance from different viewpoints. The research in view-invariant action recognition addresses this problem and focuses on recognizing human actions from unseen viewpoints.
This work addresses the problem of temporal action localization with Variance-Aware Networks (VAN), i.e., DNNs that use second-order statistics in the input and/or the output of regression tasks. We first propose a network (VANp) that when presented with the second-order statistics of the input, i.e., each sample has a mean and a variance, it propagates the mean and the variance throughout the network to deliver outputs with second order statistics. In this framework, both the input and the output could be interpreted as Gaussians. To do so, we derive differentiable analytic solutions, or reasonable approximations, to propagate across commonly used NN layers. To train the network, we define a differentiable loss based on the KL-divergence between the predicted Gaussian and a Gaussian around the ground truth action borders, and use standard back-propagation. Importantly, the variances propagation in VANp does not require any additional parameters, and during testing, does not require any additional computations either. In action localization, the means and the variances of the input are computed at pooling operations, that are typically used to bring arbitrarily long videos to a vector with fixed dimensions. Second, we propose two alternative formulations that augment the first (respectively, the last) layer of a regression network with additional parameters so as to take in the input (respectively, predict in the output) both means and variances. Results in the action localization problem show that the incorporation of second order statistics improves over the baseline network, and that VANp surpasses the accuracy of virtually all other two-stage networks without involving any additional parameters.
Social distancing is a recommended solution by the World Health Organisation (WHO) to minimise the spread of COVID-19 in public places. The majority of governments and national health authorities have set the 2-meter physical distancing as a mandatory safety measure in shopping centres, schools and other covered areas. In this research, we develop a hybrid Computer Vision and YOLOv4-based Deep Neural Network model for automated people detection in the crowd in indoor and outdoor environments using common CCTV security cameras. The proposed DNN model in combination with an adapted inverse perspective mapping (IPM) technique and SORT tracking algorithm leads to a robust people detection and social distancing monitoring. The model has been trained against two most comprehensive datasets by the time of the research the Microsoft Common Objects in Context (MS COCO) and Google Open Image datasets. The system has been evaluated against the Oxford Town Centre dataset with superior performance compared to three state-of-the-art methods. The evaluation has been conducted in challenging conditions, including occlusion, partial visibility, and under lighting variations with the mean average precision of 99.8% and the real-time speed of 24.1 fps. We also provide an online infection risk assessment scheme by statistical analysis of the Spatio-temporal data from people's moving trajectories and the rate of social distancing violations. The developed model is a generic and accurate people detection and tracking solution that can be applied in many other fields such as autonomous vehicles, human action recognition, anomaly detection, sports, crowd analysis, or any other research areas where the human detection is in the centre of attention.
Most of the current action localization methods follow an anchor-based pipeline: depicting action instances by pre-defined anchors, learning to select the anchors closest to the ground truth, and predicting the confidence of anchors with refinements. Pre-defined anchors set prior about the location and duration for action instances, which facilitates the localization for common action instances but limits the flexibility for tackling action instances with drastic varieties, especially for extremely short or extremely long ones. To address this problem, this paper proposes a novel anchor-free action localization module that assists action localization by temporal points. Specifically, this module represents an action instance as a point with its distances to the starting boundary and ending boundary, alleviating the pre-defined anchor restrictions in terms of action localization and duration. The proposed anchor-free module is capable of predicting the action instances whose duration is either extremely short or extremely long. By combining the proposed anchor-free module with a conventional anchor-based module, we propose a novel action localization framework, called A2Net. The cooperation between anchor-free and anchor-based modules achieves superior performance to the state-of-the-art on THUMOS14 (45.5% vs. 42.8%). Furthermore, comprehensive experiments demonstrate the complementarity between the anchor-free and the anchor-based module, making A2Net simple but effective.
One of the major reasons for misclassification of multiplex actions during action recognition is the unavailability of complementary features that provide the semantic information about the actions. In different domains these features are present with different scales and intensities. In existing literature, features are extracted independently in different domains, but the benefits from fusing these multidomain features are not realized. To address this challenge and to extract complete set of complementary information, in this paper, we propose a novel multidomain multimodal fusion framework that extracts complementary and distinct features from different domains of the input modality. We transform input inertial data into signal images, and then make the input modality multidomain and multimodal by transforming spatial domain information into frequency and time-spectrum domain using Discrete Fourier Transform (DFT) and Gabor wavelet transform (GWT) respectively. Features in different domains are extracted by Convolutional Neural networks (CNNs) and then fused by Canonical Correlation based Fusion (CCF) for improving the accuracy of human action recognition. Experimental results on three inertial datasets show the superiority of the proposed method when compared to the state-of-the-art.
This paper attempts at improving the accuracy of Human Action Recognition (HAR) by fusion of depth and inertial sensor data. Firstly, we transform the depth data into Sequential Front view Images(SFI) and fine-tune the pre-trained AlexNet on these images. Then, inertial data is converted into Signal Images (SI) and another convolutional neural network (CNN) is trained on these images. Finally, learned features are extracted from both CNN, fused together to make a shared feature layer, and these features are fed to the classifier. We experiment with two classifiers, namely Support Vector Machines (SVM) and softmax classifier and compare their performances. The recognition accuracies of each modality, depth data alone and sensor data alone are also calculated and compared with fusion based accuracies to highlight the fact that fusion of modalities yields better results than individual modalities. Experimental results on UTD-MHAD and Kinect 2D datasets show that proposed method achieves state of the art results when compared to other recently proposed visual-inertial action recognition methods.
In highway scenarios, an alert human driver will typically anticipate early cut-in and cut-out maneuvers of surrounding vehicles using only visual cues. An automated system must anticipate these situations at an early stage too, to increase the safety and the efficiency of its performance. To deal with lane-change recognition and prediction of surrounding vehicles, we pose the problem as an action recognition/prediction problem by stacking visual cues from video cameras. Two video action recognition approaches are analyzed: two-stream convolutional networks and spatiotemporal multiplier networks. Different sizes of the regions around the vehicles are analyzed, evaluating the importance of the interaction between vehicles and the context information in the performance. In addition, different prediction horizons are evaluated. The obtained results demonstrate the potential of these methodologies to serve as robust predictors of future lane-changes of surrounding vehicles in time horizons between 1 and 2 seconds.
In this paper, we address the problem of temporal action localization with a single stage neural network. In the proposed architecture we model the boundary predictions as uni-variate Gaussian distributions in order to model their uncertainties, which is the first in this area to the best of our knowledge. We use two uncertainty-aware boundary regression losses: first, the Kullback-Leibler divergence between the ground truth location of the boundary and the Gaussian modeling the prediction of the boundary and second, the expectation of the $\ell_1$ loss under the same Gaussian. We show that with both uncertainty modeling approaches improve the detection performance by more than $1.5\%$ in mAP@tIoU=0.5 and that the proposed simple one-stage network performs closely to more complex one and two stage networks.
Over the past few years, there has been significant interest in video action recognition systems and models. However, direct comparison of accuracy and computational performance results remain clouded by differing training environments, hardware specifications, hyperparameters, pipelines, and inference methods. This article provides a direct comparison between fourteen off-the-shelf and state-of-the-art models by ensuring consistency in these training characteristics in order to provide readers with a meaningful comparison across different types of video action recognition algorithms. Accuracy of the models is evaluated using standard Top-1 and Top-5 accuracy metrics in addition to a proposed new accuracy metric. Additionally, we compare computational performance of distributed training from two to sixty-four GPUs on a state-of-the-art HPC system.
Most current pipelines for spatio-temporal action localization connect frame-wise or clip-wise detection results to generate action proposals, where only local information is exploited and the efficiency is hindered by dense per-frame localization. In this paper, we propose Coarse-to-Fine Action Detector (CFAD),an original end-to-end trainable framework for efficient spatio-temporal action localization. The CFAD introduces a new paradigm that first estimates coarse spatio-temporal action tubes from video streams, and then refines the tubes' location based on key timestamps. This concept is implemented by two key components, the Coarse and Refine Modules in our framework. The parameterized modeling of long temporal information in the Coarse Module helps obtain accurate initial tube estimation, while the Refine Module selectively adjusts the tube location under the guidance of key timestamps. Against other methods, theproposed CFAD achieves competitive results on action detection benchmarks of UCF101-24, UCFSports and JHMDB-21 with inference speed that is 3.3x faster than the nearest competitors.
Weakly supervised temporal action localization is a newly emerging yet widely studied topic in recent years. The existing methods can be categorized into two localization-by-classification pipelines, i.e., the pre-classification pipeline and the post-classification pipeline. The pre-classification pipeline first performs classification on each video snippet and then aggregate the snippet-level classification scores to obtain the video-level classification score. In contrast, the post-classification pipeline aggregates the snippet-level features first and then predicts the video-level classification score based on the aggregated feature. Although the classifiers in these two pipelines are used in different ways, the role they play is exactly the same---to classify the given features to identify the corresponding action categories. To this end, an ideal classifier can make both pipelines work. This inspires us to simultaneously learn these two pipelines in a unified framework to obtain an effective classifier. Specifically, in the proposed learning framework, we implement two parallel network streams to model the two localization-by-classification pipelines simultaneously and make the two network streams share the same classifier. This achieves the novel Equivalent Classification Mapping (ECM) mechanism. Moreover, we discover that an ideal classifier may possess two characteristics: 1) The frame-level classification scores obtained from the pre-classification stream and the feature aggregation weights in the post-classification stream should be consistent; 2) The classification results of these two streams should be identical. Based on these two characteristics, we further introduce a weight-transition module and an equivalent training strategy into the proposed learning framework, which assists to thoroughly mine the equivalence mechanism.
Prediction of the action outcome is a new challenge for a robot collaboratively working with humans. With the impressive progress in video action recognition in recent years, fine-grained action recognition from video data turns into a new concern. Fine-grained action recognition detects subtle differences of actions in more specific granularity and is significant in many fields such as human-robot interaction, intelligent traffic management, sports training, health caring. Considering that the different outcomes are closely connected to the subtle differences in actions, fine-grained action recognition is a practical method for action outcome prediction. In this paper, we explore the performance of convolutional gate recurrent unit (ConvGRU) method on a fine-grained action recognition tasks: predicting outcomes of ball-pitching. Based on sequences of RGB images of human actions, the proposed approach achieved the performance of 79.17% accuracy, which exceeds the current state-of-the-art result. We also compared different network implementations and showed the influence of different image sampling methods, different fusion methods and pre-training, etc. Finally, we discussed the advantages and limitations of ConvGRU in such action outcome prediction and fine-grained action recognition tasks.