The temporal component of videos provides an important clue for activity recognition, as a number of activities can be reliably recognized based on the motion information. In view of that, this work proposes a novel temporal stream for two-stream convolutional networks based on images computed from the optical flow magnitude and orientation, named Magnitude-Orientation Stream (MOS), to learn the motion in a better and richer manner. Our method applies simple nonlinear transformations on the vertical and horizontal components of the optical flow to generate input images for the temporal stream. Experimental results, carried on two well-known datasets (HMDB51 and UCF101), demonstrate that using our proposed temporal stream as input to existing neural network architectures can improve their performance for activity recognition. Results demonstrate that our temporal stream provides complementary information able to improve the classical two-stream methods, indicating the suitability of our approach to be used as a temporal video representation.
Activity recognition from long unstructured egocentric photo-streams has several applications in assistive technology such as health monitoring and frailty detection, just to name a few. However, one of its main technical challenges is to deal with the low frame rate of wearable photo-cameras, which causes abrupt appearance changes between consecutive frames. In consequence, important discriminatory low-level features from motion such as optical flow cannot be estimated. In this paper, we present a batch-driven approach for training a deep learning architecture that strongly rely on Long short…
STSBench: A Large-Scale Dataset for Modeling Neuronal Activity in the Dorsal Stream of Primate Visual Cortex
Neuroscience Interdepartmental Program, Stanford University（斯坦福大学神经科学跨学科项目）；Department of Neurobiology, Stanford University（斯坦福大学神经生物学系）；Howard Hughes Medical Institute, Stanford University（斯坦福大学霍华德·霍夫曼医学研究所）
University of South China（南华大学）；University of Ulster（阿尔斯特大学）；University of Science and Technology Beijing（北京科技大学）
Sensor-based human activity segmentation and recognition are two important and challenging problems in many real-world applications and they have drawn increasing attention from the deep learning community in recent years. Most of the existing deep learning works were designed based on pre-segmented sensor streams and they have treated activity segmentation and recognition as two separate tasks. In practice, performing data stream segmentation is very challenging. We believe that both activity segmentation and recognition may convey unique information which can complement each other to improve…
University College London（伦敦大学学院）；Dithen（Dithen公司）
We investigate video classification via a two-stream convolutional neural network (CNN) design that directly ingests information extracted from compressed video bitstreams. Our approach begins with the observation that all modern video codecs divide the input frames into macroblocks (MBs). We demonstrate that selective access to MB motion vector (MV) information within compressed video bitstreams can also provide for selective, motion-adaptive, MB pixel decoding (a.k.a., MB texture decoding). This in turn allows for the derivation of spatio-temporal video activity regions at extremely high spe…
Anhui University（安徽大学）；Tencent YouTu Lab（腾讯优图实验室）；Beijing Institute of Technology（北京理工大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Peng Cheng Laboratory（鹏城实验室）；Peking University（北京大学）
The main streams of human activity recognition (HAR) algorithms are developed based on RGB cameras which are suffered from illumination, fast motion, privacy-preserving, and large energy consumption. Meanwhile, the biologically inspired event cameras attracted great interest due to their unique features, such as high dynamic range, dense temporal but sparse spatial resolution, low latency, low power, etc. As it is a newly arising sensor, even there is no realistic large-scale dataset for HAR. Considering its great practical value, in this paper, we propose a large-scale benchmark dataset to br…
In this work, we present a framework based on multi-stream convolutional neural networks (CNNs) for group activity recognition. Streams of CNNs are separately trained on different modalities and their predictions are fused at the end. Each stream has two branches to predict the group activity based on person and scene level representations. A new modality based on the human pose estimation is presented to add extra information to the model. We evaluate our method on the Volleyball and Collective Activity datasets. Experimental results show that the proposed framework is able to achieve state-o…
Korea Advanced Institute of Science and Technology（韩国科学技术院）
The human activity recognition in the IoT environment plays the central role in the ambient assisted living, where the human activities can be represented as a concatenated event stream generated from various smart objects. From the concatenated event stream, each activity should be distinguished separately for the human activity recognition to provide services that users may need. In this regard, accurately segmenting the entire stream at the precise boundary of each activity is indispensable high priority task to realize the activity recognition. Multiple human activities in an IoT environme…
We address the problem of temporal activity detection in continuous, untrimmed video streams. This is a difficult task that requires extracting meaningful spatio-temporal features to capture activities, accurately localizing the start and end times of each activity. We introduce a new model, Region Convolutional 3D Network (R-C3D), which encodes the video streams using a three-dimensional fully convolutional network, then generates candidate temporal regions containing activities and finally classifies selected regions into specific activities. Computation is saved due to the sharing of convol…
Comsats University（科姆萨特大学）；University of Leicester（莱斯特大学）；University of Calabria（卡拉布里亚大学）；Free University of Bozen-Bolzano（博岑-博尔扎诺自由大学）；Edinburgh Napier University（爱丁堡龙比亚大学）
Object recognition from live video streams comes with numerous challenges such as the variation in illumination conditions and poses. Convolutional neural networks (CNNs) have been widely used to perform intelligent visual object recognition. Yet, CNNs still suffer from severe accuracy degradation, particularly on illumination-variant datasets. To address this problem, we propose a new CNN method based on orientation fusion for visual object recognition. The proposed cloud-based video analytics system pioneers the use of bi-dimensional empirical mode decomposition to split a video frame into i…
Current approaches for activity recognition often ignore constraints on computational resources: 1) they rely on extensive feature computation to obtain rich descriptors on all frames, and 2) they assume batch-mode access to the entire test video at once. We propose a new active approach to activity recognition that prioritizes "what to compute when" in order to make timely predictions. The main idea is to learn a policy that dynamically schedules the sequence of features to compute on selected frames of a given test video. In contrast to traditional static feature selection, our approach cont…
Activity detection is one of the attractive computer vision tasks to exploit the video streams captured by widely installed cameras. Although achieving impressive performance, conventional activity detection algorithms are usually designed under certain constraints, such as using trimmed and/or object-centered video clips as inputs. Therefore, they failed to deal with the multi-scale multi-instance cases in real-world unconstrained video streams, which are untrimmed and have large field-of-views. Real-time requirements for streaming analysis also mark brute force expansion of them unfeasible. …
Wearable cameras can gather large a\-mounts of image data that provide rich visual information about the daily activities of the wearer. Motivated by the large number of health applications that could be enabled by the automatic recognition of daily activities, such as lifestyle characterization for habit improvement, context-aware personal assistance and tele-rehabilitation services, we propose a system to classify 21 daily activities from photo-streams acquired by a wearable photo-camera. Our approach combines the advantages of a Late Fusion Ensemble strategy relying on convolutional neural …
Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）
Activity detection from first-person videos (FPV) captured using a wearable camera is an active research field with potential applications in many sectors, including healthcare, law enforcement, and rehabilitation. State-of-the-art methods use optical flow-based hybrid techniques that rely on features derived from the motion of objects from consecutive frames. In this work, we developed a two-stream network, the \emph{SegCodeNet}, that uses a network branch containing video-streams with color-coded semantic segmentation masks of relevant objects in addition to the original RGB video-stream. We…
A Novel Two Stream Decision Level Fusion of Vision and Inertial Sensors Data for Automatic Multimodal Human Activity Recognition System
Academy of Scientific and Innovative Research (AcSIR)（科学与创新研究院）；CSIR-Central Electronics Engineering Research Institute (CEERI)（CSIR-中央电子工程研究所）；Birla Institute of Technology and Science Pilani（毕拉理工学院皮拉尼分校）；Edge Hill University（边山大学）
Human activity recognition based on video streams has received numerous attentions in recent years. Due to lack of depth information, RGB video based activity recognition performs poorly compared to RGB-D video based solutions. On the other hand, acquiring depth information, inertia etc. is costly and requires special equipment, whereas RGB video streams are available in ordinary cameras. Hence, our goal is to investigate whether similar or even higher accuracy can be achieved with RGB-only modality. In this regard, we propose a novel framework that couples skeleton data extracted from RGB vid…
We bring together ideas from recent work on feature design for egocentric action recognition under one framework by exploring the use of deep convolutional neural networks (CNN). Recent work has shown that features such as hand appearance, object attributes, local hand motion and camera ego-motion are important for characterizing first-person actions. To integrate these ideas under one framework, we propose a twin stream network architecture, where one stream analyzes appearance information and the other stream analyzes motion information. Our appearance stream encodes prior knowledge of the e…
Dual-Attention and Adversarial Transfer Networks for Sim-to-Real Cross-Orientation Wireless Sensing
National Graduate College for Engineers, Southern University of Science and Technology（南方科技大学国家工程师学院）；Harbin Institute of Technology（哈尔滨工业大学）；Southern University of Science and Technology（南方科技大学）
We address the problem of activity detection in continuous, untrimmed video streams. This is a difficult task that requires extracting meaningful spatio-temporal features to capture activities, accurately localizing the start and end times of each activity. We introduce a new model, Region Convolutional 3D Network (R-C3D), which encodes the video streams using a three-dimensional fully convolutional network, then generates candidate temporal regions containing activities, and finally classifies selected regions into specific activities. Computation is saved due to the sharing of convolutional …
Georgia Institute of Technology（佐治亚理工学院）；Georgia Tech Research Institution（佐治亚理工研究所）
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 (Te…
University of Rochester（罗切斯特大学）；University of Michigan（密歇根大学）
Video action recognition, a critical problem in video understanding, has been gaining increasing attention. To identify actions induced by complex object-object interactions, we need to consider not only spatial relations among objects in a single frame, but also temporal relations among different or the same objects across multiple frames. However, existing approaches that model video representations and non-local features are either incapable of explicitly modeling relations at the object-object level or unable to handle streaming videos. In this paper, we propose a novel dynamic hidden grap…
This article proposes a novel attention-based body pose encoding for human activity recognition that presents a enriched representation of body-pose that is learned. The enriched data complements the 3D body joint position data and improves model performance. In this paper, we propose a novel approach that learns enhanced feature representations from a given sequence of 3D body joints. To achieve this encoding, the approach exploits 1) a spatial stream which encodes the spatial relationship between various body joints at each time point to learn spatial structure involving the spatial distribu…
Univ Lyon, INSA-Lyon, CNRS, LIRIS（里昂大学，里昂国立应用科学学院，法国国家科学研究中心，里昂信息科学与技术实验室）；Laboratoire d’Informatique de l’Université de Tours (EA 6300), INSA Centre Val de Loire（图尔大学信息学实验室，卢瓦尔河谷国立应用科学学院）
We address human action recognition from multi-modal video data involving articulated pose and RGB frames and propose a two-stream approach. The pose stream is processed with a convolutional model taking as input a 3D tensor holding data from a sub-sequence. A specific joint ordering, which respects the topology of the human body, ensures that different convolutional layers correspond to meaningful levels of abstraction. The raw RGB stream is handled by a spatio-temporal soft-attention mechanism conditioned on features from the pose network. An LSTM network receives input from a set of image l…
Multi-modal systems are quite common in the context of human activity recognition; widely used RGB-D sensors (Kinect is the most prominent example) give access to parallel data streams, typically RGB images, depth data, skeleton information. The richness of multimodal information has been largely exploited in many works in the literature, while an analysis of their effectiveness for incremental template updating has not been investigated so far. This paper is aimed at defining a general framework for unsupervised template updating in multi-modal systems, where the different data sources can pr…
Georgia Institute of Technology（佐治亚理工学院）；University of Oxford（牛津大学）
The lack of large-scale, labeled data sets impedes progress in developing robust and generalized predictive models for on-body sensor-based human activity recognition (HAR). Labeled data in human activity recognition is scarce and hard to come by, as sensor data collection is expensive, and the annotation is time-consuming and error-prone. To address this problem, we introduce IMUTube, an automated processing pipeline that integrates existing computer vision and signal processing techniques to convert videos of human activity into virtual streams of IMU data. These virtual IMU streams represen…
University of California, Merced（加州大学默塞德分校）；University of Southern California（南加州大学）
This paper is the first work to perform spatio-temporal mapping of human activity using the visual content of geo-tagged videos. We utilize a recent deep-learning based video analysis framework, termed hidden two-stream networks, to recognize a range of activities in YouTube videos. This framework is efficient and can run in real time or faster which is important for recognizing events as they occur in streaming video or for reducing latency in analyzing already captured video. This is, in turn, important for using video in smart-city applications. We perform a series of experiments to show ou…
Noninvasive precision modulation of high-level neural population activity via natural vision perturbations
McGovern Institute for Brain Research, Dept. of Brain and Cognitive Sciences, Massachusetts Institute of Technology（麦戈文脑科学研究所，脑科学与认知科学系，麻省理工学院）；Center for Brains, Minds, and Machines, MIT（脑、心智与机器中心，麻省理工学院）；MIT Quest for Intelligence（麻省理工学院智能探索计划）
This technical report present an overview of our system proposed for the spatio-temporal action localization(SAL) task in ActivityNet Challenge 2019. Unlike previous two-streams-based works, we focus on exploring the end-to-end trainable architecture using only RGB sequential images. To this end, we employ a previously proposed simple yet effective two-branches network called SlowFast Networks which is capable of capturing both short- and long-term spatiotemporal features. Moreover, to handle the severe class imbalance and overfitting problems, we propose a correlation-preserving data augmenta…
