Synthetic Humans for Action Recognition from Unseen Viewpoints
TL;DR: In this article, the authors make use of the recent advances in monocular 3D human body reconstruction from real action sequences to automatically render synthetic training videos for the action labels, and investigate the extent of variations and augmentations that are beneficial to improving performance at new viewpoints.
Abstract: Although synthetic training data has been shown to be beneficial for tasks such as human pose estimation, its use for RGB human action recognition is relatively unexplored. Our goal in this work is to answer the question whether synthetic humans can improve the performance of human action recognition, with a particular focus on generalization to unseen viewpoints. We make use of the recent advances in monocular 3D human body reconstruction from real action sequences to automatically render synthetic training videos for the action labels. We make the following contributions: (1) we investigate the extent of variations and augmentations that are beneficial to improving performance at new viewpoints. We consider changes in body shape and clothing for individuals, as well as more action relevant augmentations such as non-uniform frame sampling, and interpolating between the motion of individuals performing the same action; (2) We introduce a new data generation methodology, SURREACT, that allows training of spatio-temporal CNNs for action classification; (3) We substantially improve the state-of-the-art action recognition performance on the NTU RGB+D and UESTC standard human action multi-view benchmarks; Finally, (4) we extend the augmentation approach to in-the-wild videos from a subset of the Kinetics dataset to investigate the case when only one-shot training data is available, and demonstrate improvements in this case as well.
Citations
More filters
TL;DR: This paper reviews both the hand-crafted feature-based and deep learning-based methods for single data modalities and also the methods based on multiple modalities, including the fusion-based frameworks and the co-learning-based approaches for HAR.
Abstract: Human Action Recognition (HAR), aiming to understand human behaviors and then assign category labels, has a wide range of applications, and thus has been attracting increasing attention in the field of computer vision. Generally, human actions can be represented using various data modalities, such as RGB, skeleton, depth, infrared sequence, point cloud, event stream, audio, acceleration, radar, and WiFi, etc., which encode different sources of useful yet distinct information and have various advantages and application scenarios. Consequently, lots of existing works have attempted to investigate different types of approaches for HAR using various modalities. In this paper, we give a comprehensive survey for HAR from the perspective of the input data modalities. Specifically, we review both the hand-crafted feature-based and deep learning-based methods for single data modalities, and also review the methods based on multiple modalities, including the fusion-based frameworks and the co-learning-based approaches. The current benchmark datasets for HAR are also introduced. Finally, we discuss some potentially important research directions in this area.
86 citations
Posted Content•
TL;DR: ACTOR as mentioned in this paper learns an action-aware latent representation for human motions by training a generative variational autoencoder (VAE) with a series of positional encodings.
Abstract: We tackle the problem of action-conditioned generation of realistic and diverse human motion sequences. In contrast to methods that complete, or extend, motion sequences, this task does not require an initial pose or sequence. Here we learn an action-aware latent representation for human motions by training a generative variational autoencoder (VAE). By sampling from this latent space and querying a certain duration through a series of positional encodings, we synthesize variable-length motion sequences conditioned on a categorical action. Specifically, we design a Transformer-based architecture, ACTOR, for encoding and decoding a sequence of parametric SMPL human body models estimated from action recognition datasets. We evaluate our approach on the NTU RGB+D, HumanAct12 and UESTC datasets and show improvements over the state of the art. Furthermore, we present two use cases: improving action recognition through adding our synthesized data to training, and motion denoising. Our code and models will be made available.
51 citations
TL;DR: A comprehensive survey of recent progress in deep learning methods for human action recognition based on the type of input data modality is presented in this article , where the authors present a comparative results on several benchmark datasets for HAR.
Abstract: Human Action Recognition (HAR) aims to understand human behavior and assign a label to each action. It has a wide range of applications, and therefore has been attracting increasing attention in the field of computer vision. Human actions can be represented using various data modalities, such as RGB, skeleton, depth, infrared, point cloud, event stream, audio, acceleration, radar, and WiFi signal, which encode different sources of useful yet distinct information and have various advantages depending on the application scenarios. Consequently, lots of existing works have attempted to investigate different types of approaches for HAR using various modalities. In this paper, we present a comprehensive survey of recent progress in deep learning methods for HAR based on the type of input data modality. Specifically, we review the current mainstream deep learning methods for single data modalities and multiple data modalities, including the fusion-based and the co-learning-based frameworks. We also present comparative results on several benchmark datasets for HAR, together with insightful observations and inspiring future research directions.
30 citations
Posted Content•
TL;DR: This work introduces an unconditional video generative model, InMoDeGAN, targeted to generate high quality videos, as well as to allow for interpretation of the latent space, and confirms that decomposed sub-spaces are interpretable and moreover, generated motion is controllable.
Abstract: In this work, we introduce an unconditional video generative model, InMoDeGAN, targeted to (a) generate high quality videos, as well as to (b) allow for interpretation of the latent space. For the latter, we place emphasis on interpreting and manipulating motion. Towards this, we decompose motion into semantic sub-spaces, which allow for control of generated samples. We design the architecture of InMoDeGAN-generator in accordance to proposed Linear Motion Decomposition, which carries the assumption that motion can be represented by a dictionary, with related vectors forming an orthogonal basis in the latent space. Each vector in the basis represents a semantic sub-space. In addition, a Temporal Pyramid Discriminator analyzes videos at different temporal resolutions. Extensive quantitative and qualitative analysis shows that our model systematically and significantly outperforms state-of-the-art methods on the VoxCeleb2-mini and BAIR-robot datasets w.r.t. video quality related to (a). Towards (b) we present experimental results, confirming that decomposed sub-spaces are interpretable and moreover, generated motion is controllable.
16 citations
Posted Content•
TL;DR: ElderSim as mentioned in this paper is an action simulation platform that can generate synthetic data on elders' daily activities, including RGB videos, two-and three-dimensional skeleton trajectories, and use the data in addition to real datasets to train three state-of-the-art human action recognition models.
Abstract: To train deep learning models for vision-based action recognition of elders' daily activities, we need large-scale activity datasets acquired under various daily living environments and conditions. However, most public datasets used in human action recognition either differ from or have limited coverage of elders' activities in many aspects, making it challenging to recognize elders' daily activities well by only utilizing existing datasets. Recently, such limitations of available datasets have actively been compensated by generating synthetic data from realistic simulation environments and using those data to train deep learning models. In this paper, based on these ideas we develop ElderSim, an action simulation platform that can generate synthetic data on elders' daily activities. For 55 kinds of frequent daily activities of the elders, ElderSim generates realistic motions of synthetic characters with various adjustable data-generating options, and provides different output modalities including RGB videos, two- and three-dimensional skeleton trajectories. We then generate KIST SynADL, a large-scale synthetic dataset of elders' activities of daily living, from ElderSim and use the data in addition to real datasets to train three state-of the-art human action recognition models. From the experiments following several newly proposed scenarios that assume different real and synthetic dataset configurations for training, we observe a noticeable performance improvement by augmenting our synthetic data. We also offer guidance with insights for the effective utilization of synthetic data to help recognize elders' daily activities.
10 citations
References
More filters
27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
123,388 citations
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Abstract: Learning to store information over extended time intervals by recurrent backpropagation takes a very long time, mostly because of insufficient, decaying error backflow. We briefly review Hochreiter's (1991) analysis of this problem, then address it by introducing a novel, efficient, gradient based method called long short-term memory (LSTM). Truncating the gradient where this does not do harm, LSTM can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units. Multiplicative gate units learn to open and close access to the constant error flow. LSTM is local in space and time; its computational complexity per time step and weight is O. 1. Our experiments with artificial data involve local, distributed, real-valued, and noisy pattern representations. In comparisons with real-time recurrent learning, back propagation through time, recurrent cascade correlation, Elman nets, and neural sequence chunking, LSTM leads to many more successful runs, and learns much faster. LSTM also solves complex, artificial long-time-lag tasks that have never been solved by previous recurrent network algorithms.
72,897 citations
TL;DR: This paper demonstrates how constraints from the task domain can be integrated into a backpropagation network through the architecture of the network, successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service.
Abstract: The ability of learning networks to generalize can be greatly enhanced by providing constraints from the task domain. This paper demonstrates how such constraints can be integrated into a backpropagation network through the architecture of the network. This approach has been successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service. A single network learns the entire recognition operation, going from the normalized image of the character to the final classification.
9,775 citations
07 Dec 2015
TL;DR: The learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks.
Abstract: We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are more suitable for spatiotemporal feature learning compared to 2D ConvNets, 2) A homogeneous architecture with small 3x3x3 convolution kernels in all layers is among the best performing architectures for 3D ConvNets, and 3) Our learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks. In addition, the features are compact: achieving 52.8% accuracy on UCF101 dataset with only 10 dimensions and also very efficient to compute due to the fast inference of ConvNets. Finally, they are conceptually very simple and easy to train and use.
7,091 citations
NEC1
TL;DR: This paper reports on an optimum dynamic progxamming (DP) based time-normalization algorithm for spoken word recognition, in which the warping function slope is restricted so as to improve discrimination between words in different categories.
Abstract: This paper reports on an optimum dynamic progxamming (DP) based time-normalization algorithm for spoken word recognition. First, a general principle of time-normalization is given using time-warping function. Then, two time-normalized distance definitions, called symmetric and asymmetric forms, are derived from the principle. These two forms are compared with each other through theoretical discussions and experimental studies. The symmetric form algorithm superiority is established. A new technique, called slope constraint, is successfully introduced, in which the warping function slope is restricted so as to improve discrimination between words in different categories. The effective slope constraint characteristic is qualitatively analyzed, and the optimum slope constraint condition is determined through experiments. The optimized algorithm is then extensively subjected to experimental comparison with various DP-algorithms, previously applied to spoken word recognition by different research groups. The experiment shows that the present algorithm gives no more than about two-thirds errors, even compared to the best conventional algorithm.
5,906 citations