Today, many of the home automation systems deployed are mostly controlled by humans. This control by humans restricts the automation of home appliances to an extent. Also, most of the deployed home automation systems use the Internet of Things technology to control the appliances. In this paper, we propose a system developed using action recognition to fully automate the home appliances. We recognize the three actions of a person (sitting, standing and lying) along with the recognition of an empty room. The accuracy of the system was 90% in the real-life test experiments. With this system, we remove the human intervention in home automation systems for controlling the home appliances and at the same time we ensure the data privacy and reduce the energy consumption by efficiently and optimally using home appliances.
Recognizing human actions is a core challenge for autonomous systems as they directly share the same space with humans. Systems must be able to recognize and assess human actions in real-time. In order to train corresponding data-driven algorithms, a significant amount of annotated training data is required. We demonstrated a pipeline to detect humans, estimate their pose, track them over time and recognize their actions in real-time with standard monocular camera sensors. For action recognition, we encode the human pose into a new data format called Encoded Human Pose Image (EHPI) that can then be classified using standard methods from the computer vision community. With this simple procedure we achieve competitive state-of-the-art performance in pose-based action detection and can ensure real-time performance. In addition, we show a use case in the context of autonomous driving to demonstrate how such a system can be trained to recognize human actions using simulation data.
Generalized zero-shot action recognition is a challenging problem, where the task is to recognize new action categories that are unavailable during the training stage, in addition to the seen action categories. Existing approaches suffer from the inherent bias of the learned classifier towards the seen action categories. As a consequence, unseen category samples are incorrectly classified as belonging to one of the seen action categories. In this paper, we set out to tackle this issue by arguing for a separate treatment of seen and unseen action categories in generalized zero-shot action recognition. We introduce an out-of-distribution detector that determines whether the video features belong to a seen or unseen action category. To train our out-of-distribution detector, video features for unseen action categories are synthesized using generative adversarial networks trained on seen action category features. To the best of our knowledge, we are the first to propose an out-of-distribution detector based GZSL framework for action recognition in videos. Experiments are performed on three action recognition datasets: Olympic Sports, HMDB51 and UCF101. For generalized zero-shot action recognition, our proposed approach outperforms the baseline (f-CLSWGAN) with absolute gains (in classification accuracy) of 7.0%, 3.4%, and 4.9%, respectively, on these datasets.
Domain alignment in convolutional networks aims to learn the degree of layer-specific feature alignment beneficial to the joint learning of source and target datasets. While increasingly popular in convolutional networks, there have been no previous attempts to achieve domain alignment in recurrent networks. Similar to spatial features, both source and target domains are likely to exhibit temporal dependencies that can be jointly learnt and aligned. In this paper we introduce Dual-Domain LSTM (DDLSTM), an architecture that is able to learn temporal dependencies from two domains concurrently. It performs cross-contaminated batch normalisation on both input-to-hidden and hidden-to-hidden weights, and learns the parameters for cross-contamination, for both single-layer and multi-layer LSTM architectures. We evaluate DDLSTM on frame-level action recognition using three datasets, taking a pair at a time, and report an average increase in accuracy of 3.5%. The proposed DDLSTM architecture outperforms standard, fine-tuned, and batch-normalised LSTMs.
In this paper, we investigate how to learn rich and robust feature representations for audio classification from visual data and acoustic images, a novel audio data modality. Former models learn audio representations from raw signals or spectral data acquired by a single microphone, with remarkable results in classification and retrieval. However, such representations are not so robust towards variable environmental sound conditions. We tackle this drawback by exploiting a new multimodal labeled action recognition dataset acquired by a hybrid audio-visual sensor that provides RGB video, raw audio signals, and spatialized acoustic data, also known as acoustic images, where the visual and acoustic images are aligned in space and synchronized in time. Using this richer information, we train audio deep learning models in a teacher-student fashion. In particular, we distill knowledge into audio networks from both visual and acoustic image teachers. Our experiments suggest that the learned representations are more powerful and have better generalization capabilities than the features learned from models trained using just single-microphone audio data.
Modern machine learning datasets can have biases for certain representations that are leveraged by algorithms to achieve high performance without learning to solve the underlying task. This problem is referred to as "representation bias". The question of how to reduce the representation biases of a dataset is investigated and a new dataset REPresentAtion bIas Removal (REPAIR) procedure is proposed. This formulates bias minimization as an optimization problem, seeking a weight distribution that penalizes examples easy for a classifier built on a given feature representation. Bias reduction is then equated to maximizing the ratio between the classification loss on the reweighted dataset and the uncertainty of the ground-truth class labels. This is a minimax problem that REPAIR solves by alternatingly updating classifier parameters and dataset resampling weights, using stochastic gradient descent. An experimental set-up is also introduced to measure the bias of any dataset for a given representation, and the impact of this bias on the performance of recognition models. Experiments with synthetic and action recognition data show that dataset REPAIR can significantly reduce representation bias, and lead to improved generalization of models trained on REPAIRed datasets. The tools used for characterizing representation bias, and the proposed dataset REPAIR algorithm, are available at https://github.com/JerryYLi/Dataset-REPAIR/.
Video temporal action detection aims to temporally localize and recognize the action in untrimmed videos. Existing one-stage approaches mostly focus on unifying two subtasks, i.e., localization of action proposals and classification of each proposal through a fully shared backbone. However, such design of encapsulating all components of two subtasks in one single network might restrict the training by ignoring the specialized characteristic of each subtask. In this paper, we propose a novel Decoupled Single Shot temporal Action Detection (Decouple-SSAD) method to mitigate such problem by decoupling the localization and classification in a one-stage scheme. Particularly, two separate branches are designed in parallel to enable each component to own representations privately for accurate localization or classification. Each branch produces a set of action anchor layers by applying deconvolution to the feature maps of the main stream. Each branch produces a set of feature maps by applying deconvolution to the feature maps of the main stream. High-level semantic information from deeper layers is thus incorporated to enhance the feature representations. We conduct extensive experiments on THUMOS14 dataset and demonstrate superior performance over state-of-the-art methods. Our code is available online.
Detecting temporal extents of human actions in videos is a challenging computer vision problem that requires detailed manual supervision including frame-level labels. This expensive annotation process limits deploying action detectors to a limited number of categories. We propose a novel method, called WSGN, that learns to detect actions from \emph{weak supervision}, using only video-level labels. WSGN learns to exploit both video-specific and dataset-wide statistics to predict relevance of each frame to an action category. This strategy leads to significant gains in action detection for two standard benchmarks THUMOS14 and Charades. Our method obtains excellent results compared to state-of-the-art methods that uses similar features and loss functions on THUMOS14 dataset. Similarly, our weakly supervised method is only 0.3% mAP behind a state-of-the-art supervised method on challenging Charades dataset for action localization.
Human action recognition remains an important yet challenging task. This work proposes a novel action recognition system. It uses a novel Multiple View Region Adaptive Multi-resolution in time Depth Motion Map (MV-RAMDMM) formulation combined with appearance information. Multiple stream 3D Convolutional Neural Networks (CNNs) are trained on the different views and time resolutions of the region adaptive Depth Motion Maps. Multiple views are synthesised to enhance the view invariance. The region adaptive weights, based on localised motion, accentuate and differentiate parts of actions possessing faster motion. Dedicated 3D CNN streams for multi-time resolution appearance information (RGB) are also included. These help to identify and differentiate between small object interactions. A pre-trained 3D-CNN is used here with fine-tuning for each stream along with multiple class Support Vector Machines (SVM)s. Average score fusion is used on the output. The developed approach is capable of recognising both human action and human-object interaction. Three public domain datasets including: MSR 3D Action,Northwestern UCLA multi-view actions and MSR 3D daily activity are used to evaluate the proposed solution. The experimental results demonstrate the robustness of this approach compared with state-of-the-art algorithms.
We propose a method for human action recognition, one that can localize the spatiotemporal regions that `define' the actions. This is a challenging task due to the subtlety of human actions in video and the co-occurrence of contextual elements. To address this challenge, we utilize conjugate samples of human actions, which are video clips that are contextually similar to human action samples but do not contain the action. We introduce a novel attentional mechanism that can spatially and temporally separate human actions from the co-occurring contextual factors. The separation of the action and context factors is weakly supervised, eliminating the need for laboriously detailed annotation of these two factors in training samples. Our method can be used to build human action classifiers with higher accuracy and better interpretability. Experiments on several human action recognition datasets demonstrate the quantitative and qualitative benefits of our approach.
We consider the task of training a neural network to anticipate human actions in video. This task is challenging given the complexity of video data, the stochastic nature of the future, and the limited amount of annotated training data. In this paper, we propose a novel knowledge distillation framework that uses an action recognition network to supervise the training of an action anticipation network, guiding the latter to attend to the relevant information needed for correctly anticipating the future actions. This framework is possible thanks to a novel loss function to account for positional shifts of semantic concepts in a dynamic video. The knowledge distillation framework is a form of self-supervised learning, and it takes advantage of unlabeled data. Experimental results on JHMDB and EPIC-KITCHENS dataset show the effectiveness of our approach.
The Dense Trajectories concept is one of the most successful approaches in action recognition, suitable for scenarios involving a significant amount of motion. However, due to noise and background motion, many generated trajectories are irrelevant to the actual human activity and can potentially lead to performance degradation. In this paper, we propose Localized Trajectories as an improved version of Dense Trajectories where motion trajectories are clustered around human body joints provided by RGB-D cameras and then encoded by local Bag-of-Words. As a result, the Localized Trajectories concept provides a more discriminative representation of actions as compared to Dense Trajectories. Moreover, we generalize Localized Trajectories to 3D by using the modalities offered by RGB-D cameras. One of the main advantages of using RGB-D data to generate trajectories is that they include radial displacements that are perpendicular to the image plane. Extensive experiments and analysis are carried out on five different datasets.
While many action recognition datasets consist of collections of brief, trimmed videos each containing a relevant action, videos in the real-world (e.g., on YouTube) exhibit very different properties: they are often several minutes long, where brief relevant clips are often interleaved with segments of extended duration containing little change. Applying densely an action recognition system to every temporal clip within such videos is prohibitively expensive. Furthermore, as we show in our experiments, this results in suboptimal recognition accuracy as informative predictions from relevant clips are outnumbered by meaningless classification outputs over long uninformative sections of the video. In this paper we introduce a lightweight "clip-sampling" model that can efficiently identify the most salient temporal clips within a long video. We demonstrate that the computational cost of action recognition on untrimmed videos can be dramatically reduced by invoking recognition only on these most salient clips. Furthermore, we show that this yields significant gains in recognition accuracy compared to analysis of all clips or randomly/uniformly selected clips. On Sports1M, our clip sampling scheme elevates the accuracy of an already state-of-the-art action classifier by 7% and reduces by more than 15 times its computational cost.
Recognising actions in videos relies on labelled supervision during training, typically the start and end times of each action instance. This supervision is not only subjective, but also expensive to acquire. Weak video-level supervision has been successfully exploited for recognition in untrimmed videos, however it is challenged when the number of different actions in training videos increases. We propose a method that is supervised by single timestamps located around each action instance, in untrimmed videos. We replace expensive action bounds with sampling distributions initialised from these timestamps. We then use the classifier's response to iteratively update the sampling distributions. We demonstrate that these distributions converge to the location and extent of discriminative action segments. We evaluate our method on three datasets for fine-grained recognition, with increasing number of different actions per video, and show that single timestamps offer a reasonable compromise between recognition performance and labelling effort, performing comparably to full temporal supervision. Our update method improves top-1 test accuracy by up to 5.4%. across the evaluated datasets.
Can performance on the task of action quality assessment (AQA) be improved by exploiting a description of the action and its quality? Current AQA and skills assessment approaches propose to learn features that serve only one task - estimating the final score. In this paper, we propose to learn spatio-temporal features that explain three related tasks - fine-grained action recognition, commentary generation, and estimating the AQA score. A new multitask-AQA dataset, the largest to date, comprising of 1412 diving samples was collected to evaluate our approach (https://github.com/ParitoshParmar/MTL-AQA). We show that our MTL approach outperforms STL approach using two different kinds of architectures: C3D-AVG and MSCADC. The C3D-AVG-MTL approach achieves the new state-of-the-art performance with a rank correlation of 90.44%. Detailed experiments were performed to show that MTL offers better generalization than STL, and representations from action recognition models are not sufficient for the AQA task and instead should be learned.
Traditional 3D Convolutional Neural Networks (CNNs) are computationally expensive, memory intensive, prone to overfit, and most importantly, there is a need to improve their feature learning capabilities. To address these issues, we propose Rectified Local Phase Volume (ReLPV) block, an efficient alternative to the standard 3D convolutional layer. The ReLPV block extracts the phase in a 3D local neighborhood (e.g., 3x3x3) of each position of the input map to obtain the feature maps. The phase is extracted by computing 3D Short Term Fourier Transform (STFT) at multiple fixed low frequency points in the 3D local neighborhood of each position. These feature maps at different frequency points are then linearly combined after passing them through an activation function. The ReLPV block provides significant parameter savings of at least, 3^3 to 13^3 times compared to the standard 3D convolutional layer with the filter sizes 3x3x3 to 13x13x13, respectively. We show that the feature learning capabilities of the ReLPV block are significantly better than the standard 3D convolutional layer. Furthermore, it produces consistently better results across different 3D data representations. We achieve state-of-the-art accuracy on the volumetric ModelNet10 and ModelNet40 datasets while utilizing only 11% parameters of the current state-of-the-art. We also improve the state-of-the-art on the UCF-101 split-1 action recognition dataset by 5.68% (when trained from scratch) while using only 15% of the parameters of the state-of-the-art. The project webpage is available at https://sites.google.com/view/lp-3dcnn/home.
Building correspondences across different modalities, such as video and language, has recently become critical in many visual recognition applications, such as video captioning. Inspired by machine translation, recent models tackle this task using an encoder-decoder strategy. The (video) encoder is traditionally a Convolutional Neural Network (CNN), while the decoding (for language generation) is done using a Recurrent Neural Network (RNN). Current state-of-the-art methods, however, train encoder and decoder separately. CNNs are pretrained on object and/or action recognition tasks and used to encode video-level features. The decoder is then optimised on such static features to generate the video's description. This disjoint setup is arguably sub-optimal for input (video) to output (description) mapping. In this work, we propose to optimise both encoder and decoder simultaneously in an end-to-end fashion. In a two-stage training setting, we first initialise our architecture using pre-trained encoders and decoders -- then, the entire network is trained end-to-end in a fine-tuning stage to learn the most relevant features for video caption generation. In our experiments, we use GoogLeNet and Inception-ResNet-v2 as encoders and an original Soft-Attention (SA-) LSTM as a decoder. Analogously to gains observed in other computer vision problems, we show that end-to-end training significantly improves over the traditional, disjoint training process. We evaluate our End-to-End (EtENet) Networks on the Microsoft Research Video Description (MSVD) and the MSR Video to Text (MSR-VTT) benchmark datasets, showing how EtENet achieves state-of-the-art performance across the board.
Skeleton-based human action recognition has attracted great interest thanks to the easy accessibility of the human skeleton data. Recently, there is a trend of using very deep feedforward neural networks to model the 3D coordinates of joints without considering the computational efficiency. In this paper, we propose a simple yet effective semantics-guided neural network (SGN) for skeleton-based action recognition. We explicitly introduce the high level semantics of joints (joint type and frame index) into the network to enhance the feature representation capability. In addition, we exploit the relationship of joints hierarchically through two modules, i.e., a joint-level module for modeling the correlations of joints in the same frame and a framelevel module for modeling the dependencies of frames by taking the joints in the same frame as a whole. A strong baseline is proposed to facilitate the study of this field. With an order of magnitude smaller model size than most previous works, SGN achieves the state-of-the-art performance on the NTU60, NTU120, and SYSU datasets. The source code is available at https://github.com/microsoft/SGN.
Video action detectors are usually trained using datasets with fully-supervised temporal annotations. Building such datasets is an expensive task. To alleviate this problem, recent methods have tried to leverage weak labeling, where videos are untrimmed and only a video-level label is available. In this paper, we propose RefineLoc, a novel weakly-supervised temporal action localization method. RefineLoc uses an iterative refinement approach by estimating and training on snippet-level pseudo ground truth at every iteration. We show the benefit of this iterative approach and present an extensive analysis of five different pseudo ground truth generators. We show the effectiveness of our model on two standard action datasets, ActivityNet v1.2 and THUMOS14. RefineLoc shows competitive results with the state-of-the-art in weakly-supervised temporal localization. Additionally, our iterative refinement process is able to significantly improve the performance of two state-of-the-art methods, setting a new state-of-the-art on THUMOS14.
We focus on the word-level visual lipreading, which requires to decode the word from the speaker's video. Recently, many state-of-the-art visual lipreading methods explore the end-to-end trainable deep models, involving the use of 2D convolutional networks (e.g., ResNet) as the front-end visual feature extractor and the sequential model (e.g., Bi-LSTM or Bi-GRU) as the back-end. Although a deep 2D convolution neural network can provide informative image-based features, it ignores the temporal motion existing between the adjacent frames. In this work, we investigate the spatial-temporal capacity power of I3D (Inflated 3D ConvNet) for visual lipreading. We demonstrate that, after pre-trained on the large-scale video action recognition dataset (e.g., Kinetics), our models show a considerable improvement of performance on the task of lipreading. A comparison between a set of video model architectures and input data representation is also reported. Our extensive experiments on LRW shows that a two-stream I3D model with RGB video and optical flow as the inputs achieves the state-of-the-art performance.