Learning the spatial-temporal representation of motion information is crucial to human action recognition. Nevertheless, most of the existing features or descriptors cannot capture motion information effectively, especially for long-term motion. To address this problem, this paper proposes a long-term motion descriptor called sequential Deep Trajectory Descriptor (sDTD). Specifically, we project dense trajectories into two-dimensional planes, and subsequently a CNN-RNN network is employed to learn an effective representation for long-term motion. Unlike the popular two-stream ConvNets, the sDTD stream is introduced into a three-stream framework so as to identify actions from a video sequence. Consequently, this three-stream framework can simultaneously capture static spatial features, short-term motion and long-term motion in the video. Extensive experiments were conducted on three challenging datasets: KTH, HMDB51 and UCF101. Experimental results show that our method achieves state-of-the-art performance on the KTH and UCF101 datasets, and is comparable to the state-of-the-art methods on the HMDB51 dataset.
In this work we propose to utilize information about human actions to improve pose estimation in monocular videos. To this end, we present a pictorial structure model that exploits high-level information about activities to incorporate higher-order part dependencies by modeling action specific appearance models and pose priors. However, instead of using an additional expensive action recognition framework, the action priors are efficiently estimated by our pose estimation framework. This is achieved by starting with a uniform action prior and updating the action prior during pose estimation. We also show that learning the right amount of appearance sharing among action classes improves the pose estimation. We demonstrate the effectiveness of the proposed method on two challenging datasets for pose estimation and action recognition with over 80,000 test images.
Recently Trajectory-pooled Deep-learning Descriptors were shown to achieve state-of-the-art human action recognition results on a number of datasets. This paper improves their performance by applying rank pooling to each trajectory, encoding the temporal evolution of deep learning features computed along the trajectory. This leads to Evolution-Preserving Trajectory (EPT) descriptors, a novel type of video descriptor that significantly outperforms Trajectory-pooled Deep-learning Descriptors. EPT descriptors are defined based on dense trajectories, and they provide complimentary benefits to video descriptors that are not based on trajectories. In particular, we show that the combination of EPT descriptors and VideoDarwin leads to state-of-the-art performance on Hollywood2 and UCF101 datasets.
To have a robot actively supporting a human during a collaborative task, it is crucial that robots are able to identify the current action in order to predict the next one. Common approaches make use of high-level knowledge, such as object affordances, semantics or understanding of actions in terms of pre- and post-conditions. These approaches often require hand-coded a priori knowledge, time- and resource-intensive or supervised learning techniques. We propose to reframe this problem as an appearance-based place recognition problem. In our framework, we regard sequences of visual images of human actions as a map in analogy to the visual place recognition problem. Observing the task for the second time, our approach is able to recognize pre-observed actions in a one-shot learning approach and is thereby able to recognize the current observation in the task space. We propose two new methods for creating and aligning action observations within a task map. We compare and verify our approaches with real data of humans assembling several types of IKEA flat packs.
Detecting activities in untrimmed videos is an important but challenging task. The performance of existing methods remains unsatisfactory, e.g., they often meet difficulties in locating the beginning and end of a long complex action. In this paper, we propose a generic framework that can accurately detect a wide variety of activities from untrimmed videos. Our first contribution is a novel proposal scheme that can efficiently generate candidates with accurate temporal boundaries. The other contribution is a cascaded classification pipeline that explicitly distinguishes between relevance and completeness of a candidate instance. On two challenging temporal activity detection datasets, THUMOS14 and ActivityNet, the proposed framework significantly outperforms the existing state-of-the-art methods, demonstrating superior accuracy and strong adaptivity in handling activities with various temporal structures.
In this work we introduce a fully end-to-end approach for action detection in videos that learns to directly predict the temporal bounds of actions. Our intuition is that the process of detecting actions is naturally one of observation and refinement: observing moments in video, and refining hypotheses about when an action is occurring. Based on this insight, we formulate our model as a recurrent neural network-based agent that interacts with a video over time. The agent observes video frames and decides both where to look next and when to emit a prediction. Since backpropagation is not adequate in this non-differentiable setting, we use REINFORCE to learn the agent's decision policy. Our model achieves state-of-the-art results on the THUMOS'14 and ActivityNet datasets while observing only a fraction (2% or less) of the video frames.
Despite a lot of research efforts devoted in recent years, how to efficiently learn long-term dependencies from sequences still remains a pretty challenging task. As one of the key models for sequence learning, recurrent neural network (RNN) and its variants such as long short term memory (LSTM) and gated recurrent unit (GRU) are still not powerful enough in practice. One possible reason is that they have only feedforward connections, which is different from the biological neural system that is typically composed of both feedforward and feedback connections. To address this problem, this paper proposes a biologically-inspired deep network, called shuttleNet\footnote{Our code is available at \url{https://github.com/shiyemin/shuttlenet}}. Technologically, the shuttleNet consists of several processors, each of which is a GRU while associated with multiple groups of cells and states. Unlike traditional RNNs, all processors inside shuttleNet are loop connected to mimic the brain's feedforward and feedback connections, in which they are shared across multiple pathways in the loop connection. Attention mechanism is then employed to select the best information flow pathway. Extensive experiments conducted on two benchmark datasets (i.e UCF101 and HMDB51) show that we can beat state-of-the-art methods by simply embedding shuttleNet into a CNN-RNN framework.
The recognition of actions from video sequences has many applications in health monitoring, assisted living, surveillance, and smart homes. Despite advances in sensing, in particular related to 3D video, the methodologies to process the data are still subject to research. We demonstrate superior results by a system which combines recurrent neural networks with convolutional neural networks in a voting approach. The gated-recurrent-unit-based neural networks are particularly well-suited to distinguish actions based on long-term information from optical tracking data; the 3D-CNNs focus more on detailed, recent information from video data. The resulting features are merged in an SVM which then classifies the movement. In this architecture, our method improves recognition rates of state-of-the-art methods by 14% on standard data sets.
The traditional bag-of-words approach has found a wide range of applications in computer vision. The standard pipeline consists of a generation of a visual vocabulary, a quantization of the features into histograms of visual words, and a classification step for which usually a support vector machine in combination with a non-linear kernel is used. Given large amounts of data, however, the model suffers from a lack of discriminative power. This applies particularly for action recognition, where the vast amount of video features needs to be subsampled for unsupervised visual vocabulary generation. Moreover, the kernel computation can be very expensive on large datasets. In this work, we propose a recurrent neural network that is equivalent to the traditional bag-of-words approach but enables for the application of discriminative training. The model further allows to incorporate the kernel computation into the neural network directly, solving the complexity issue and allowing to represent the complete classification system within a single network. We evaluate our method on four recent action recognition benchmarks and show that the conventional model as well as sparse coding methods are outperformed.
Despite the fact that many 3D human activity benchmarks being proposed, most existing action datasets focus on the action recognition tasks for the segmented videos. There is a lack of standard large-scale benchmarks, especially for current popular data-hungry deep learning based methods. In this paper, we introduce a new large scale benchmark (PKU-MMD) for continuous multi-modality 3D human action understanding and cover a wide range of complex human activities with well annotated information. PKU-MMD contains 1076 long video sequences in 51 action categories, performed by 66 subjects in three camera views. It contains almost 20,000 action instances and 5.4 million frames in total. Our dataset also provides multi-modality data sources, including RGB, depth, Infrared Radiation and Skeleton. With different modalities, we conduct extensive experiments on our dataset in terms of two scenarios and evaluate different methods by various metrics, including a new proposed evaluation protocol 2D-AP. We believe this large-scale dataset will benefit future researches on action detection for the community.
Scene flow describes the motion of 3D objects in real world and potentially could be the basis of a good feature for 3D action recognition. However, its use for action recognition, especially in the context of convolutional neural networks (ConvNets), has not been previously studied. In this paper, we propose the extraction and use of scene flow for action recognition from RGB-D data. Previous works have considered the depth and RGB modalities as separate channels and extract features for later fusion. We take a different approach and consider the modalities as one entity, thus allowing feature extraction for action recognition at the beginning. Two key questions about the use of scene flow for action recognition are addressed: how to organize the scene flow vectors and how to represent the long term dynamics of videos based on scene flow. In order to calculate the scene flow correctly on the available datasets, we propose an effective self-calibration method to align the RGB and depth data spatially without knowledge of the camera parameters. Based on the scene flow vectors, we propose a new representation, namely, Scene Flow to Action Map (SFAM), that describes several long term spatio-temporal dynamics for action recognition. We adopt a channel transform kernel to transform the scene flow vectors to an optimal color space analogous to RGB. This transformation takes better advantage of the trained ConvNets models over ImageNet. Experimental results indicate that this new representation can surpass the performance of state-of-the-art methods on two large public datasets.
Recent two-stream deep Convolutional Neural Networks (ConvNets) have made significant progress in recognizing human actions in videos. Despite their success, methods extending the basic two-stream ConvNet have not systematically explored possible network architectures to further exploit spatiotemporal dynamics within video sequences. Further, such networks often use different baseline two-stream networks. Therefore, the differences and the distinguishing factors between various methods using Recurrent Neural Networks (RNN) or convolutional networks on temporally-constructed feature vectors (Temporal-ConvNet) are unclear. In this work, we first demonstrate a strong baseline two-stream ConvNet using ResNet-101. We use this baseline to thoroughly examine the use of both RNNs and Temporal-ConvNets for extracting spatiotemporal information. Building upon our experimental results, we then propose and investigate two different networks to further integrate spatiotemporal information: 1) temporal segment RNN and 2) Inception-style Temporal-ConvNet. We demonstrate that using both RNNs (using LSTMs) and Temporal-ConvNets on spatiotemporal feature matrices are able to exploit spatiotemporal dynamics to improve the overall performance. However, each of these methods require proper care to achieve state-of-the-art performance; for example, LSTMs require pre-segmented data or else they cannot fully exploit temporal information. Our analysis identifies specific limitations for each method that could form the basis of future work. Our experimental results on UCF101 and HMDB51 datasets achieve state-of-the-art performances, 94.1% and 69.0%, respectively, without requiring extensive temporal augmentation.
Interpretability of deep neural networks (DNNs) is essential since it enables users to understand the overall strengths and weaknesses of the models, conveys an understanding of how the models will behave in the future, and how to diagnose and correct potential problems. However, it is challenging to reason about what a DNN actually does due to its opaque or black-box nature. To address this issue, we propose a novel technique to improve the interpretability of DNNs by leveraging the rich semantic information embedded in human descriptions. By concentrating on the video captioning task, we first extract a set of semantically meaningful topics from the human descriptions that cover a wide range of visual concepts, and integrate them into the model with an interpretive loss. We then propose a prediction difference maximization algorithm to interpret the learned features of each neuron. Experimental results demonstrate its effectiveness in video captioning using the interpretable features, which can also be transferred to video action recognition. By clearly understanding the learned features, users can easily revise false predictions via a human-in-the-loop procedure.
A human action can be seen as transitions between one's body poses over time, where the transition depicts a temporal relation between two poses. Recognizing actions thus involves learning a classifier sensitive to these pose transitions as well as to static poses. In this paper, we introduce a novel method called transitions forests, an ensemble of decision trees that both learn to discriminate static poses and transitions between pairs of two independent frames. During training, node splitting is driven by alternating two criteria: the standard classification objective that maximizes the discrimination power in individual frames, and the proposed one in pairwise frame transitions. Growing the trees tends to group frames that have similar associated transitions and share same action label incorporating temporal information that was not available otherwise. Unlike conventional decision trees where the best split in a node is determined independently of other nodes, the transition forests try to find the best split of nodes jointly (within a layer) for incorporating distant node transitions. When inferring the class label of a new frame, it is passed down the trees and the prediction is made based on previous frame predictions and the current one in an efficient and online manner. We apply our method on varied skeleton action recognition and online detection datasets showing its suitability over several baselines and state-of-the-art approaches.
Recently, action proposal methods have played an important role in action recognition tasks, as they reduce the search space dramatically. Most unsupervised action proposal methods tend to generate hundreds of action proposals which include many noisy, inconsistent, and unranked action proposals, while supervised action proposal methods take advantage of predefined object detectors (e.g., human detector) to refine and score the action proposals, but they require thousands of manual annotations to train. Given the action proposals in a video, the goal of the proposed work is to generate a few better action proposals that are ranked properly. In our approach, we first divide action proposal into sub-proposal and then use Dynamic Programming based graph optimization scheme to select the optimal combinations of sub-proposals from different proposals and assign each new proposal a score. We propose a new unsupervised image-based actioness detector that leverages web images and employs it as one of the node scores in our graph formulation. Moreover, we capture motion information by estimating the number of motion contours within each action proposal patch. The proposed method is an unsupervised method that neither needs bounding box annotations nor video level labels, which is desirable with the current explosion of large-scale action datasets. Our approach is generic and does not depend on a specific action proposal method. We evaluate our approach on several publicly available trimmed and un-trimmed datasets and obtain better performance compared to several proposal ranking methods. In addition, we demonstrate that properly ranked proposals produce significantly better action detection as compared to state-of-the-art proposal based methods.
This paper studies the joint learning of action recognition and temporal localization in long, untrimmed videos. We employ a multi-task learning framework that performs the three highly related steps of action proposal, action recognition, and action localization refinement in parallel instead of the standard sequential pipeline that performs the steps in order. We develop a novel temporal actionness regression module that estimates what proportion of a clip contains action. We use it for temporal localization but it could have other applications like video retrieval, surveillance, summarization, etc. We also introduce random shear augmentation during training to simulate viewpoint change. We evaluate our framework on three popular video benchmarks. Results demonstrate that our joint model is efficient in terms of storage and computation in that we do not need to compute and cache dense trajectory features, and that it is several times faster than its sequential ConvNets counterpart. Yet, despite being more efficient, it outperforms state-of-the-art methods with respect to accuracy.
Recently, Wi-Fi has caught tremendous attention for its ubiquity, and, motivated by Wi-Fi's low cost and privacy preservation, researchers have been putting lots of investigation into its potential on action recognition and even person identification. In this paper, we offer an comprehensive overview on these two topics in Wi-Fi. Also, through looking at these two topics from an unprecedented perspective, we could achieve generality instead of designing specific ad-hoc features for each scenario. Observing the great resemblance of Channel State Information (CSI, a fine-grained information captured from the received Wi-Fi signal) to texture, we proposed a brand-new framework based on computer vision methods. To minimize the effect of location dependency embedded in CSI, we propose a novel de-noising method based on Singular Value Decomposition (SVD) to eliminate the background energy and effectively extract the channel information of signals reflected by human bodies. From the experiments conducted, we demonstrate the feasibility and efficacy of the proposed methods. Also, we conclude factors that would affect the performance and highlight a few promising issues that require further deliberation.
Most popular deep learning based models for action recognition are designed to generate separate predictions within their short temporal windows, which are often aggregated by heuristic means to assign an action label to the full video segment. Given that not all frames from a video characterize the underlying action, pooling schemes that impose equal importance to all frames might be unfavorable. In an attempt towards tackling this challenge, we propose a novel pooling scheme, dubbed SVM pooling, based on the notion that among the bag of features generated by a CNN on all temporal windows, there is at least one feature that characterizes the action. To this end, we learn a decision hyperplane that separates this unknown yet useful feature from the rest. Applying multiple instance learning in an SVM setup, we use the parameters of this separating hyperplane as a descriptor for the video. Since these parameters are directly related to the support vectors in a max-margin framework, they serve as robust representations for pooling of the CNN features. We devise a joint optimization objective and an efficient solver that learns these hyperplanes per video and the corresponding action classifiers over the hyperplanes. Showcased experiments on the standard HMDB and UCF101 datasets demonstrate state-of-the-art performance.
In this paper we address the problem of human action recognition from video sequences. Inspired by the exemplary results obtained via automatic feature learning and deep learning approaches in computer vision, we focus our attention towards learning salient spatial features via a convolutional neural network (CNN) and then map their temporal relationship with the aid of Long-Short-Term-Memory (LSTM) networks. Our contribution in this paper is a deep fusion framework that more effectively exploits spatial features from CNNs with temporal features from LSTM models. We also extensively evaluate their strengths and weaknesses. We find that by combining both the sets of features, the fully connected features effectively act as an attention mechanism to direct the LSTM to interesting parts of the convolutional feature sequence. The significance of our fusion method is its simplicity and effectiveness compared to other state-of-the-art methods. The evaluation results demonstrate that this hierarchical multi stream fusion method has higher performance compared to single stream mapping methods allowing it to achieve high accuracy outperforming current state-of-the-art methods in three widely used databases: UCF11, UCFSports, jHMDB.
Training of Convolutional Neural Networks (CNNs) on long video sequences is computationally expensive due to the substantial memory requirements and the massive number of parameters that deep architectures demand. Early fusion of video frames is thus a standard technique, in which several consecutive frames are first agglomerated into a compact representation, and then fed into the CNN as an input sample. For this purpose, a summarization approach that represents a set of consecutive RGB frames by a single dynamic image to capture pixel dynamics is proposed recently. In this paper, we introduce a novel ordered representation of consecutive optical flow frames as an alternative and argue that this representation captures the action dynamics more effectively than RGB frames. We provide intuitions on why such a representation is better for action recognition. We validate our claims on standard benchmark datasets and demonstrate that using summaries of flow images lead to significant improvements over RGB frames while achieving accuracy comparable to the state-of-the-art on UCF101 and HMDB datasets.