The work in this paper is driven by the question how to exploit the temporal cues available in videos for their accurate classification, and for human action recognition in particular? Thus far, the vision community has focused on spatio-temporal approaches with fixed temporal convolution kernel depths. We introduce a new temporal layer that models variable temporal convolution kernel depths. We embed this new temporal layer in our proposed 3D CNN. We extend the DenseNet architecture - which normally is 2D - with 3D filters and pooling kernels. We name our proposed video convolutional network `Temporal 3D ConvNet'~(T3D) and its new temporal layer `Temporal Transition Layer'~(TTL). Our experiments show that T3D outperforms the current state-of-the-art methods on the HMDB51, UCF101 and Kinetics datasets. The other issue in training 3D ConvNets is about training them from scratch with a huge labeled dataset to get a reasonable performance. So the knowledge learned in 2D ConvNets is completely ignored. Another contribution in this work is a simple and effective technique to transfer knowledge from a pre-trained 2D CNN to a randomly initialized 3D CNN for a stable weight initialization. This allows us to significantly reduce the number of training samples for 3D CNNs. Thus, by finetuning this network, we beat the performance of generic and recent methods in 3D CNNs, which were trained on large video datasets, e.g. Sports-1M, and finetuned on the target datasets, e.g. HMDB51/UCF101. The T3D codes will be released
Despite the recent deep learning (DL) revolution, kernel machines still remain powerful methods for action recognition. DL has brought the use of large datasets and this is typically a problem for kernel approaches, which are not scaling up efficiently due to kernel Gram matrices. Nevertheless, kernel methods are still attractive and more generally applicable since they can equally manage different sizes of the datasets, also in cases where DL techniques show some limitations. This work investigates these issues by proposing an explicit approximated representation that, together with a linear model, is an equivalent, yet scalable, implementation of a kernel machine. Our approximation is directly inspired by the exact feature map that is induced by an RBF Gaussian kernel but, unlike the latter, it is finite dimensional and very compact. We justify the soundness of our idea with a theoretical analysis which proves the unbiasedness of the approximation, and provides a vanishing bound for its variance, which is shown to decrease much rapidly than in alternative methods in the literature. In a broad experimental validation, we assess the superiority of our approximation in terms of 1) ease and speed of training, 2) compactness of the model, and 3) improvements with respect to the state-of-the-art performance.
We propose a feature for action recognition called Trajectory-Set (TS), on top of the improved Dense Trajectory (iDT). The TS feature encodes only trajectories around densely sampled interest points, without any appearance features. Experimental results on the UCF50, UCF101, and HMDB51 action datasets demonstrate that TS is comparable to state-of-the-arts, and outperforms many other methods; for HMDB the accuracy of 85.4%, compared to the best accuracy of 80.2% obtained by a deep method. Our code is available on-line at https://github.com/Gauffret/TrajectorySet .
Motion representation plays a vital role in human action recognition in videos. In this study, we introduce a novel compact motion representation for video action recognition, named Optical Flow guided Feature (OFF), which enables the network to distill temporal information through a fast and robust approach. The OFF is derived from the definition of optical flow and is orthogonal to the optical flow. The derivation also provides theoretical support for using the difference between two frames. By directly calculating pixel-wise spatiotemporal gradients of the deep feature maps, the OFF could be embedded in any existing CNN based video action recognition framework with only a slight additional cost. It enables the CNN to extract spatiotemporal information, especially the temporal information between frames simultaneously. This simple but powerful idea is validated by experimental results. The network with OFF fed only by RGB inputs achieves a competitive accuracy of 93.3% on UCF-101, which is comparable with the result obtained by two streams (RGB and optical flow), but is 15 times faster in speed. Experimental results also show that OFF is complementary to other motion modalities such as optical flow. When the proposed method is plugged into the state-of-the-art video action recognition framework, it has 96:0% and 74:2% accuracy on UCF-101 and HMDB-51 respectively. The code for this project is available at https://github.com/kevin-ssy/Optical-Flow-Guided-Feature.
We propose a framework that learns a representation transferable across different domains and tasks in a label efficient manner. Our approach battles domain shift with a domain adversarial loss, and generalizes the embedding to novel task using a metric learning-based approach. Our model is simultaneously optimized on labeled source data and unlabeled or sparsely labeled data in the target domain. Our method shows compelling results on novel classes within a new domain even when only a few labeled examples per class are available, outperforming the prevalent fine-tuning approach. In addition, we demonstrate the effectiveness of our framework on the transfer learning task from image object recognition to video action recognition.
A novel deep neural network training paradigm that exploits the conjoint information in multiple heterogeneous sources is proposed. Specifically, in a RGB-D based action recognition task, it cooperatively trains a single convolutional neural network (named c-ConvNet) on both RGB visual features and depth features, and deeply aggregates the two kinds of features for action recognition. Differently from the conventional ConvNet that learns the deep separable features for homogeneous modality-based classification with only one softmax loss function, the c-ConvNet enhances the discriminative power of the deeply learned features and weakens the undesired modality discrepancy by jointly optimizing a ranking loss and a softmax loss for both homogeneous and heterogeneous modalities. The ranking loss consists of intra-modality and cross-modality triplet losses, and it reduces both the intra-modality and cross-modality feature variations. Furthermore, the correlations between RGB and depth data are embedded in the c-ConvNet, and can be retrieved by either of the modalities and contribute to the recognition in the case even only one of the modalities is available. The proposed method was extensively evaluated on two large RGB-D action recognition datasets, ChaLearn LAP IsoGD and NTU RGB+D datasets, and one small dataset, SYSU 3D HOI, and achieved state-of-the-art results.
3D action recognition has broad applications in human-computer interaction and intelligent surveillance. However, recognizing similar actions remains challenging since previous literature fails to capture motion and shape cues effectively from noisy depth data. In this paper, we propose a novel two-layer Bag-of-Visual-Words (BoVW) model, which suppresses the noise disturbances and jointly encodes both motion and shape cues. First, background clutter is removed by a background modeling method that is designed for depth data. Then, motion and shape cues are jointly used to generate robust and distinctive spatial-temporal interest points (STIPs): motion-based STIPs and shape-based STIPs. In the first layer of our model, a multi-scale 3D local steering kernel (M3DLSK) descriptor is proposed to describe local appearances of cuboids around motion-based STIPs. In the second layer, a spatial-temporal vector (STV) descriptor is proposed to describe the spatial-temporal distributions of shape-based STIPs. Using the Bag-of-Visual-Words (BoVW) model, motion and shape cues are combined to form a fused action representation. Our model performs favorably compared with common STIP detection and description methods. Thorough experiments verify that our model is effective in distinguishing similar actions and robust to background clutter, partial occlusions and pepper noise.
The unsupervised Pretraining method has been widely used in aiding human action recognition. However, existing methods focus on reconstructing the already present frames rather than generating frames which happen in future.In this paper, We propose an improved Variantial Autoencoder model to extract the features with a high connection to the coming scenarios, also known as Predictive Learning. Our framework lists as following: two steam 3D-convolution neural networks are used to extract both spatial and temporal information as latent variables. Then a resample method is introduced to create new normal distribution probabilistic latent variables and finally, the deconvolution neural network will use these latent variables generate next frames. Through this possess, we train the model to focus more on how to generate the future and thus it will extract the future high connected features. In the experiment stage, A large number of experiments on UT and UCF101 datasets reveal that future generation aids Prediction does improve the performance. Moreover, the Future Representation Learning Network reach a higher score than other methods when in half observation. This means that Future Representation Learning is better than the traditional Representation Learning and other state- of-the-art methods in solving the human action prediction problems to some extends.
We present a system for covert automated deception detection in real-life courtroom trial videos. We study the importance of different modalities like vision, audio and text for this task. On the vision side, our system uses classifiers trained on low level video features which predict human micro-expressions. We show that predictions of high-level micro-expressions can be used as features for deception prediction. Surprisingly, IDT (Improved Dense Trajectory) features which have been widely used for action recognition, are also very good at predicting deception in videos. We fuse the score of classifiers trained on IDT features and high-level micro-expressions to improve performance. MFCC (Mel-frequency Cepstral Coefficients) features from the audio domain also provide a significant boost in performance, while information from transcripts is not very beneficial for our system. Using various classifiers, our automated system obtains an AUC of 0.877 (10-fold cross-validation) when evaluated on subjects which were not part of the training set. Even though state-of-the-art methods use human annotations of micro-expressions for deception detection, our fully automated approach outperforms them by 5%. When combined with human annotations of micro-expressions, our AUC improves to 0.922. We also present results of a user-study to analyze how well do average humans perform on this task, what modalities they use for deception detection and how they perform if only one modality is accessible. Our project page can be found at \url{https://doubaibai.github.io/DARE/}.
In this paper we propose the use of quantum genetic algorithm to optimize the support vector machine (SVM) for human action recognition. The Microsoft Kinect sensor can be used for skeleton tracking, which provides the joints' position data. However, how to extract the motion features for representing the dynamics of a human skeleton is still a challenge due to the complexity of human motion. We present a highly efficient features extraction method for action classification, that is, using the joint angles to represent a human skeleton and calculating the variance of each angle during an action time window. Using the proposed representation, we compared the human action classification accuracy of two approaches, including the optimized SVM based on quantum genetic algorithm and the conventional SVM with grid search. Experimental results on the MSR-12 dataset show that the conventional SVM achieved an accuracy of $ 93.85\% $. The proposed approach outperforms the conventional method with an accuracy of $ 96.15\% $.
We propose a new spatio-temporal attention based mechanism for human action recognition able to automatically attend to the hands most involved into the studied action and detect the most discriminative moments in an action. Attention is handled in a recurrent manner employing Recurrent Neural Network (RNN) and is fully-differentiable. In contrast to standard soft-attention based mechanisms, our approach does not use the hidden RNN state as input to the attention model. Instead, attention distributions are extracted using external information: human articulated pose. We performed an extensive ablation study to show the strengths of this approach and we particularly studied the conditioning aspect of the attention mechanism. We evaluate the method on the largest currently available human action recognition dataset, NTU-RGB+D, and report state-of-the-art results. Other advantages of our model are certain aspects of explanability, as the spatial and temporal attention distributions at test time allow to study and verify on which parts of the input data the method focuses.
Most of the top performing action recognition methods use optical flow as a "black box" input. Here we take a deeper look at the combination of flow and action recognition, and investigate why optical flow is helpful, what makes a flow method good for action recognition, and how we can make it better. In particular, we investigate the impact of different flow algorithms and input transformations to better understand how these affect a state-of-the-art action recognition method. Furthermore, we fine tune two neural-network flow methods end-to-end on the most widely used action recognition dataset (UCF101). Based on these experiments, we make the following five observations: 1) optical flow is useful for action recognition because it is invariant to appearance, 2) optical flow methods are optimized to minimize end-point-error (EPE), but the EPE of current methods is not well correlated with action recognition performance, 3) for the flow methods tested, accuracy at boundaries and at small displacements is most correlated with action recognition performance, 4) training optical flow to minimize classification error instead of minimizing EPE improves recognition performance, and 5) optical flow learned for the task of action recognition differs from traditional optical flow especially inside the human body and at the boundary of the body. These observations may encourage optical flow researchers to look beyond EPE as a goal and guide action recognition researchers to seek better motion cues, leading to a tighter integration of the optical flow and action recognition communities.
This paper presents a new large-scale dataset for recognition and temporal localization of human actions collected from Web videos. We refer to it as HACS (Human Action Clips and Segments). We leverage both consensus and disagreement among visual classifiers to automatically mine candidate short clips from unlabeled videos, which are subsequently validated by human annotators. The resulting dataset is dubbed HACS Clips. Through a separate process we also collect annotations defining action segment boundaries. This resulting dataset is called HACS Segments. Overall, HACS Clips consists of 1.5M annotated clips sampled from 504K untrimmed videos, and HACS Seg-ments contains 139K action segments densely annotatedin 50K untrimmed videos spanning 200 action categories. HACS Clips contains more labeled examples than any existing video benchmark. This renders our dataset both a large scale action recognition benchmark and an excellent source for spatiotemporal feature learning. In our transferlearning experiments on three target datasets, HACS Clips outperforms Kinetics-600, Moments-In-Time and Sports1Mas a pretraining source. On HACS Segments, we evaluate state-of-the-art methods of action proposal generation and action localization, and highlight the new challenges posed by our dense temporal annotations.
We introduce a simple yet surprisingly powerful model to incorporate attention in action recognition and human object interaction tasks. Our proposed attention module can be trained with or without extra supervision, and gives a sizable boost in accuracy while keeping the network size and computational cost nearly the same. It leads to significant improvements over state of the art base architecture on three standard action recognition benchmarks across still images and videos, and establishes new state of the art on MPII dataset with 12.5% relative improvement. We also perform an extensive analysis of our attention module both empirically and analytically. In terms of the latter, we introduce a novel derivation of bottom-up and top-down attention as low-rank approximations of bilinear pooling methods (typically used for fine-grained classification). From this perspective, our attention formulation suggests a novel characterization of action recognition as a fine-grained recognition problem.
As the success of deep models has led to their deployment in all areas of computer vision, it is increasingly important to understand how these representations work and what they are capturing. In this paper, we shed light on deep spatiotemporal representations by visualizing what two-stream models have learned in order to recognize actions in video. We show that local detectors for appearance and motion objects arise to form distributed representations for recognizing human actions. Key observations include the following. First, cross-stream fusion enables the learning of true spatiotemporal features rather than simply separate appearance and motion features. Second, the networks can learn local representations that are highly class specific, but also generic representations that can serve a range of classes. Third, throughout the hierarchy of the network, features become more abstract and show increasing invariance to aspects of the data that are unimportant to desired distinctions (e.g. motion patterns across various speeds). Fourth, visualizations can be used not only to shed light on learned representations, but also to reveal idiosyncracies of training data and to explain failure cases of the system.
Most existing Convolutional Neural Networks(CNNs) used for action recognition are either difficult to optimize or underuse crucial temporal information. Inspired by the fact that the recurrent model consistently makes breakthroughs in the task related to sequence, we propose a novel Multi-Level Recurrent Residual Networks(MRRN) which incorporates three recognition streams. Each stream consists of a Residual Networks(ResNets) and a recurrent model. The proposed model captures spatiotemporal information by employing both alternative ResNets to learn spatial representations from static frames and stacked Simple Recurrent Units(SRUs) to model temporal dynamics. Three distinct-level streams learned low-, mid-, high-level representations independently are fused by computing a weighted average of their softmax scores to obtain the complementary representations of the video. Unlike previous models which boost performance at the cost of time complexity and space complexity, our models have a lower complexity by employing shortcut connection and are trained end-to-end with greater efficiency. MRRN displays significant performance improvements compared to CNN-RNN framework baselines and obtains comparable performance with the state-of-the-art, achieving 51.3% on HMDB-51 dataset and 81.9% on UCF-101 dataset although no additional data.
A major emerging challenge is how to protect people's privacy as cameras and computer vision are increasingly integrated into our daily lives, including in smart devices inside homes. A potential solution is to capture and record just the minimum amount of information needed to perform a task of interest. In this paper, we propose a fully-coupled two-stream spatiotemporal architecture for reliable human action recognition on extremely low resolution (e.g., 12x16 pixel) videos. We provide an efficient method to extract spatial and temporal features and to aggregate them into a robust feature representation for an entire action video sequence. We also consider how to incorporate high resolution videos during training in order to build better low resolution action recognition models. We evaluate on two publicly-available datasets, showing significant improvements over the state-of-the-art.
We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds. Modeling the spatial-audio-temporal dynamics even for actions occurring in 3 second videos poses many challenges: meaningful events do not include only people, but also objects, animals, and natural phenomena; visual and auditory events can be symmetrical in time ("opening" is "closing" in reverse), and either transient or sustained. We describe the annotation process of our dataset (each video is tagged with one action or activity label among 339 different classes), analyze its scale and diversity in comparison to other large-scale video datasets for action recognition, and report results of several baseline models addressing separately, and jointly, three modalities: spatial, temporal and auditory. The Moments in Time dataset, designed to have a large coverage and diversity of events in both visual and auditory modalities, can serve as a new challenge to develop models that scale to the level of complexity and abstract reasoning that a human processes on a daily basis.
Human action recognition in 3D skeleton sequences has attracted a lot of research attention. Recently, Long Short-Term Memory (LSTM) networks have shown promising performance in this task due to their strengths in modeling the dependencies and dynamics in sequential data. As not all skeletal joints are informative for action recognition, and the irrelevant joints often bring noise which can degrade the performance, we need to pay more attention to the informative ones. However, the original LSTM network does not have explicit attention ability. In this paper, we propose a new class of LSTM network, Global Context-Aware Attention LSTM (GCA-LSTM), for skeleton based action recognition. This network is capable of selectively focusing on the informative joints in each frame of each skeleton sequence by using a global context memory cell. To further improve the attention capability of our network, we also introduce a recurrent attention mechanism, with which the attention performance of the network can be enhanced progressively. Moreover, we propose a stepwise training scheme in order to train our network effectively. Our approach achieves state-of-the-art performance on five challenging benchmark datasets for skeleton based action recognition.
Over the past decade, multivariate time series classification has received great attention. We propose transforming the existing univariate time series classification models, the Long Short Term Memory Fully Convolutional Network (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN), into a multivariate time series classification model by augmenting the fully convolutional block with a squeeze-and-excitation block to further improve accuracy. Our proposed models outperform most state-of-the-art models while requiring minimum preprocessing. The proposed models work efficiently on various complex multivariate time series classification tasks such as activity recognition or action recognition. Furthermore, the proposed models are highly efficient at test time and small enough to deploy on memory constrained systems.