Conventionally, spatiotemporal modeling network and its complexity are the two most concentrated research topics in video action recognition. Existing state-of-the-art methods have achieved excellent accuracy regardless of the complexity meanwhile efficient spatiotemporal modeling solutions are slightly inferior in performance. In this paper, we attempt to acquire both efficiency and effectiveness simultaneously. First of all, besides traditionally treating H x W x T video frames as space-time signal (viewing from the Height-Width spatial plane), we propose to also model video from the other two Height-Time and Width-Time planes, to capture the dynamics of video thoroughly. Secondly, our model is designed based on 2D CNN backbones and model complexity is well kept in mind by design. Specifically, we introduce a novel multi-view fusion (MVF) module to exploit video dynamics using separable convolution for efficiency. It is a plug-and-play module and can be inserted into off-the-shelf 2D CNNs to form a simple yet effective model called MVFNet. Moreover, MVFNet can be thought of as a generalized video modeling framework and it can specialize to be existing methods such as C2D, SlowOnly, and TSM under different settings. Extensive experiments are conducted on popular benchmarks (i.e., Something-Something V1 & V2, Kinetics, UCF-101, and HMDB-51) to show its superiority. The proposed MVFNet can achieve state-of-the-art performance with 2D CNN's complexity.
We address the problem of capturing temporal information for video classification in 2D networks, without increasing their computational cost. Existing approaches focus on modifying the architecture of 2D networks (e.g. by including filters in the temporal dimension to turn them into 3D networks, or using optical flow, etc.), which increases computation cost. Instead, we propose a novel sampling strategy, where we re-order the channels of the input video, to capture short-term frame-to-frame changes. We observe that without bells and whistles, the proposed sampling strategy improves performanc…
In this paper, we present Fusion-GCN, an approach for multimodal action recognition using Graph Convolutional Networks (GCNs). Action recognition methods based around GCNs recently yielded state-of-the-art performance for skeleton-based action recognition. With Fusion-GCN, we propose to integrate various sensor data modalities into a graph that is trained using a GCN model for multi-modal action recognition. Additional sensor measurements are incorporated into the graph representation, either on a channel dimension (introducing additional node attributes) or spatial dimension (introducing new …
This paper attempts at improving the accuracy of Human Action Recognition (HAR) by fusion of depth and inertial sensor data. Firstly, we transform the depth data into Sequential Front view Images(SFI) and fine-tune the pre-trained AlexNet on these images. Then, inertial data is converted into Signal Images (SI) and another convolutional neural network (CNN) is trained on these images. Finally, learned features are extracted from both CNN, fused together to make a shared feature layer, and these features are fed to the classifier. We experiment with two classifiers, namely Support Vector Machin…
Nanjing University of Science and Technology（南京理工大学）；Huawei Inc.（华为公司）
To understand a complex action, multiple sources of information, including appearance, positional, and semantic features, need to be integrated. However, these features are difficult to be fused since they often differ significantly in modality and dimensionality. In this paper, we present a novel framework that accomplishes this goal by interactive fusion, namely, projecting features across different spaces and guiding it using an auxiliary prediction task. Specifically, we implement the framework in three steps, namely, positional-to-appearance feature extraction, semantic feature interactio…
University of Bristol（布里斯托大学）；University of Oxford（牛津大学）
We focus on multi-modal fusion for egocentric action recognition, and propose a novel architecture for multi-modal temporal-binding, i.e. the combination of modalities within a range of temporal offsets. We train the architecture with three modalities -- RGB, Flow and Audio -- and combine them with mid-level fusion alongside sparse temporal sampling of fused representations. In contrast with previous works, modalities are fused before temporal aggregation, with shared modality and fusion weights over time. Our proposed architecture is trained end-to-end, outperforming individual modalities as …
Humans can easily recognize actions with only a few examples given, while the existing video recognition models still heavily rely on the large-scale labeled data inputs. This observation has motivated an increasing interest in few-shot video action recognition, which aims at learning new actions with only very few labeled samples. In this paper, we propose a depth guided Adaptive Meta-Fusion Network for few-shot video recognition which is termed as AMeFu-Net. Concretely, we tackle the few-shot recognition problem from three aspects: firstly, we alleviate this extremely data-scarce problem by …
Human action recognition is used in many applications such as video surveillance, human computer interaction, assistive living, and gaming. Many papers have appeared in the literature showing that the fusion of vision and inertial sensing improves recognition accuracies compared to the situations when each sensing modality is used individually. This paper provides a survey of the papers in which vision and inertial sensing are used simultaneously within a fusion framework in order to perform human action recognition. The surveyed papers are categorized in terms of fusion approaches, features, …
Massachusetts Institute of Technology（麻省理工学院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research（IBM研究院）；Microsoft（微软）；Boston University（波士顿大学）
Temporal modelling is the key for efficient video action recognition. While understanding temporal information can improve recognition accuracy for dynamic actions, removing temporal redundancy and reusing past features can significantly save computation leading to efficient action recognition. In this paper, we introduce an adaptive temporal fusion network, called AdaFuse, that dynamically fuses channels from current and past feature maps for strong temporal modelling. Specifically, the necessary information from the historical convolution feature maps is fused with current pruned feature map…
This paper proposes a novel Subdivision-Fusion Model (SFM) to recognize human actions. In most action recognition tasks, overlapping feature distribution is a common problem leading to overfitting. In the subdivision stage of the proposed SFM, samples in each category are clustered. Then, such samples are grouped into multiple more concentrated subcategories. Boundaries for the subcategories are easier to find and as consequence overfitting is avoided. In the subsequent fusion stage, the multi-subcategories classification results are converted back to the original category recognition problem.…
Deep convolutional neural networks (ConvNets) have been recently shown to attain state-of-the-art performance for action recognition on standard-resolution videos. However, less attention has been paid to recognition performance at extremely low resolutions (eLR) (e.g., 16 x 12 pixels). Reliable action recognition using eLR cameras would address privacy concerns in various application environments such as private homes, hospitals, nursing/rehabilitation facilities, etc. In this paper, we propose a semi-coupled filter-sharing network that leverages high resolution (HR) videos during training in…
We present a general framework for compositional action recognition -- i.e. action recognition where the labels are composed out of simpler components such as subjects, atomic-actions and objects. The main challenge in compositional action recognition is that there is a combinatorially large set of possible actions that can be composed using basic components. However, compositionality also provides a structure that can be exploited. To do so, we develop and test a novel Structured Attention Fusion (SAF) self-attention mechanism to combine information from object detections, which capture the t…
Single-Stream Multi-Feature Fusion with Temporal Robustness for Gait Emotion Recognition
College of Computer and Information Science, Southwest University（西南大学计算机与信息科学学院）；College of Physical Science and Technology, Southwest University（西南大学物理科学与技术学院）；Wisesoft Inc.（四川川大智胜软件股份有限公司）
Shanghai Jiao Tong University（上海交通大学）；Nanjing University（南京大学）；University of Chinese Academy of Sciences（中国科学院大学）
Action recognition is an important yet challenging task in computer vision. In this paper, we propose a novel deep-based framework for action recognition, which improves the recognition accuracy by: 1) deriving more precise features for representing actions, and 2) reducing the asynchrony between different information streams. We first introduce a coarse-to-fine network which extracts shared deep features at different action class granularities and progressively integrates them to obtain a more accurate feature representation for input actions. We further introduce an asynchronous fusion netwo…
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 t…
In recent years, graph convolutional networks (GCNs) play an increasingly critical role in skeleton-based human action recognition. However, most GCN-based methods still have two main limitations: 1) They only consider the motion information of the joints or process the joints and bones separately, which are unable to fully explore the latent functional correlation between joints and bones for action recognition. 2) Most of these works are performed in the supervised learning way, which heavily relies on massive labeled training data. To address these issues, we propose a semi-supervised skele…
One of the major reasons for misclassification of multiplex actions during action recognition is the unavailability of complementary features that provide the semantic information about the actions. In different domains these features are present with different scales and intensities. In existing literature, features are extracted independently in different domains, but the benefits from fusing these multidomain features are not realized. To address this challenge and to extract complete set of complementary information, in this paper, we propose a novel multidomain multimodal fusion framework…
Multimodal fusion frameworks for Human Action Recognition (HAR) using depth and inertial sensor data have been proposed over the years. In most of the existing works, fusion is performed at a single level (feature level or decision level), missing the opportunity to fuse rich mid-level features necessary for better classification. To address this shortcoming, in this paper, we propose three novel deep multilevel multimodal fusion frameworks to capitalize on different fusion strategies at various stages and to leverage the superiority of multilevel fusion. At input, we transform the depth data …
FLOW: Fusing and Shuffling Global and Local Views for Cross-User Human Activity Recognition with IMUs
School of Computer Science, University of South China（南华大学计算机学院）；School of Computing, University of Ulster（阿尔斯特大学计算学院）；The University of Auckland（奥克兰大学）；School of Computer Science and Technology, Dalian University of Technology（大连理工大学计算机科学与技术学院）
Application of Multimodal Fusion Deep Learning Model in Disease Recognition
Arizona State University（亚利桑那州立大学）；University of Washington（华盛顿大学）；University of California San Diego（加利福尼亚大学圣迭戈分校）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；University of California, Davis（加利福尼亚大学戴维斯分校）；Stevens Institute of Technology（史蒂文斯理工学院）
Huazhong University of Science and Technology（华中科技大学）；Anyang Institute of Technology（安阳工学院）
Facial expression recognition is a challenging task when neural network is applied to pattern recognition. Most of the current recognition research is based on single source facial data, which generally has the disadvantages of low accuracy and low robustness. In this paper, a neural network algorithm of facial expression recognition based on multimodal data fusion is proposed. The algorithm is based on the multimodal data, and it takes the facial image, the histogram of oriented gradient of the image and the facial landmarks as the input, and establishes CNN, LNN and HNN three sub neural netw…
Automatic emotion recognition is a challenging task. In this paper, we present our effort for the audio-video based sub-challenge of the Emotion Recognition in the Wild (EmotiW) 2018 challenge, which requires participants to assign a single emotion label to the video clip from the six universal emotions (Anger, Disgust, Fear, Happiness, Sad and Surprise) and Neutral. The proposed multimodal emotion recognition system takes audio, video and text information into account. Except for handcraft features, we also extract bottleneck features from deep neutral networks (DNNs) via transfer learning. B…
Indian Institute of Information Technology and Management-Kerala（印度喀拉拉邦信息技术与管理学院）；Griffith University（格里菲斯大学）
Examplers of a face are formed from multiple gallery images of a person and are used in the process of classification of a test image. We incorporate such examplers in forming a biologically inspired local binary decisions on similarity based face recognition method. As opposed to single model approaches such as face averages the exampler based approach results in higher recognition accu- racies and stability. Using multiple training samples per person, the method shows the following recognition accuracies: 99.0% on AR, 99.5% on FERET, 99.5% on ORL, 99.3% on EYALE, 100.0% on YALE and 100.0% on…
Multilevel neural networks with dual-stage feature fusion for human activity recognition
Departamento de Informática, Universidad Carlos III de Madrid（信息学院，卡洛斯三世大学）；Departamento de Teoría de la Señal y Comunicaciones, Universidad Carlos III de Madrid（信号与通信理论系，卡洛斯三世大学）；CEIEC, Universidad Francisco de Vitoria（CEIEC，弗朗西斯科·维多利亚大学）
University of Science and Technology of China（中国科学技术大学）；National Engineering Laboratory for Brain-inspired Intelligence（类脑智能技术国家工程实验室）
2D+3D facial expression recognition (FER) can effectively cope with illumination changes and pose variations by simultaneously merging 2D texture and more robust 3D depth information. Most deep learning-based approaches employ the simple fusion strategy that concatenates the multimodal features directly after fully-connected layers, without considering the different degrees of significance for each modality. Meanwhile, how to focus on both 2D and 3D local features in salient regions is still a great challenge. In this letter, we propose the adaptive fusion network with masks (AFNet-M) for 2D+3…
Nanjing University of Posts and Telecommunications（南京邮电大学）
Due to the instability and limitations of unimodal biometric systems, multimodal systems have attracted more and more attention from researchers. However, how to exploit the independent and complementary information between different modalities remains a key and challenging problem. In this paper, we propose a multimodal biometric fusion recognition algorithm based on fingerprints and finger veins (Fingerprint Finger Veins-Channel Spatial Attention Fusion Module, FPV-CSAFM). Specifically, for each pair of fingerprint and finger vein images, we first propose a simple and effective Convolutional…
This paper presents a real-time face recognition system using kinect sensor. The algorithm is implemented on GPU using opencl and significant speed improvements are observed. We use kinect depth image to increase the robustness and reduce computational cost of conventional LBP based face recognition. The main objective of this paper was to perform robust, high speed fusion based face recognition and tracking. The algorithm is mainly composed of three steps. First step is to detect all faces in the video using viola jones algorithm. The second step is online database generation using a tracking…
School of Life Science and Technology, Xidian University（西安电子科技大学生命科学技术学院）
Face recognition has already been well studied under the visible light and the infrared,in both intra-spectral and cross-spectral cases. However, how to fuse different light bands, i.e., hyperspectral face recognition, is still an open research problem, which has the advantages of richer information retaining and all-weather functionality over single band face recognition. Among the very few works for hyperspectral face recognition, traditional non-deep learning techniques are largely used. Thus, we in this paper bring deep learning into the topic of hyperspectral face recognition, and propose…
Despite recent advances in multi-scale deep representations, their limitations are attributed to expensive parameters and weak fusion modules. Hence, we propose an efficient approach to fuse multi-scale deep representations, called convolutional fusion networks (CFN). Owing to using 1$\times$1 convolution and global average pooling, CFN can efficiently generate the side branches while adding few parameters. In addition, we present a locally-connected fusion module, which can learn adaptive weights for the side branches and form a discriminatively fused feature. CFN models trained on the CIFAR …
Human activity recognition serves an important part in building continuous behavioral monitoring systems, which are deployable for visual surveillance, patient rehabilitation, gaming, and even personally inclined smart homes. This paper demonstrates our efforts to develop a collaborative decision fusion mechanism for integrating the predicted scores from multiple learning algorithms trained on smartphone sensor based human activity data. We present an approach for fusing convolutional neural network, recurrent convolutional network, and support vector machine by computing and fusing the relati…
Shanghai Institute for Advanced Communication and Data Science, Shanghai University（上海大学上海先进通信与数据科学研究院）
Although recent works based on deep learning have made progress in improving recognition accuracy on scene text recognition, how to handle low-quality text images in end-to-end deep networks remains a research challenge. In this paper, we propose an Iterative Fusion based Recognizer (IFR) for low quality scene text recognition, taking advantage of refined text images input and robust feature representation. IFR contains two branches which focus on scene text recognition and low quality scene text image recovery respectively. We utilize an iterative collaboration between two branches, which can…
Facial expression recognition is an essential task for various applications, including emotion detection, mental health analysis, and human-machine interactions. In this paper, we propose a multi-modal facial expression recognition method that exploits audio information along with facial images to provide a crucial clue to differentiate some ambiguous facial expressions. Specifically, we introduce a Modal Fusion Module (MFM) to fuse audio-visual information, where image and audio features are extracted from Swin Transformer. Additionally, we tackle the imbalance problem in the dataset by emplo…
This paper demonstrates two different fusion techniques at two different levels of a human face recognition process. The first one is called data fusion at lower level and the second one is the decision fusion towards the end of the recognition process. At first a data fusion is applied on visual and corresponding thermal images to generate fused image. Data fusion is implemented in the wavelet domain after decomposing the images through Daubechies wavelet coefficients (db2). During the data fusion maximum of approximate and other three details coefficients are merged together. After that Prin…
First-person interaction recognition is a challenging task because of unstable video conditions resulting from the camera wearer's movement. For human interaction recognition from a first-person viewpoint, this paper proposes a three-stream fusion network with two main parts: three-stream architecture and three-stream correlation fusion. Thre three-stream architecture captures the characteristics of the target appearance, target motion, and camera ego-motion. Meanwhile the three-stream correlation fusion combines the feature map of each of the three streams to consider the correlations among t…
Despite recent advances in MOOC, the current e-learning systems have advantages of alleviating barriers by time differences, and geographically spatial separation between teachers and students. However, there has been a 'lack of supervision' problem that e-learner's learning unit state(LUS) can't be supervised automatically. In this paper, we present a fusion framework considering three channel data sources: 1) videos/images from a camera, 2) eye movement information tracked by a low solution eye tracker and 3) mouse movement. Based on these data modalities, we propose a novel approach of mult…
PES Institute of Technology（PES理工学院）；PES School of Engineering（PES工程学院）
Optical Character Recognition (OCR) is one of the important fields in image processing and pattern recognition domain. Handwritten character recognition has always been a challenging task. Only a little work can be traced towards the recognition of handwritten characters for the south Indian languages. Kannada is one such south Indian language which is also one of the official language of India. Accurate recognition of Kannada characters is a challenging task because of the high degree of similarity between the characters. Hence, good quality features are to be extracted and better classifiers…
Shanghai AI Laboratory（上海人工智能实验室）；Uisee Research（驭势科技研究院）；ShanghaiTech University（上海科技大学）；Peking University（北京大学）；University of Pennsylvania（宾夕法尼亚大学）
Point cloud processing is a challenging task due to its sparsity and irregularity. Prior works introduce delicate designs on either local feature aggregator or global geometric architecture, but few combine both advantages. We propose Dual-Scale Point Cloud Recognition with High-frequency Fusion (DSPoint) to extract local-global features by concurrently operating on voxels and points. We reverse the conventional design of applying convolution on voxels and attention to points. Specifically, we disentangle point features through channel dimension for dual-scale processing: one by point-wise con…
University of Science and Technology of China（中国科学技术大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
The audio-video based emotion recognition aims to classify a given video into basic emotions. In this paper, we describe our approaches in EmotiW 2019, which mainly explores emotion features and feature fusion strategies for audio and visual modality. For emotion features, we explore audio feature with both speech-spectrogram and Log Mel-spectrogram and evaluate several facial features with different CNN models and different emotion pretrained strategies. For fusion strategies, we explore intra-modal and cross-modal fusion methods, such as designing attention mechanisms to highlights important…
In this paper we present a comparative study on fusion of visual and thermal images using different wavelet transformations. Here, coefficients of discrete wavelet transforms from both visual and thermal images are computed separately and combined. Next, inverse discrete wavelet transformation is taken in order to obtain fused face image. Both Haar and Daubechies (db2) wavelet transforms have been used to compare recognition results. For experiments IRIS Thermal/Visual Face Database was used. Experimental results using Haar and Daubechies wavelets show that the performance of the approach pres…
Halmstad University（哈尔姆斯塔德大学）；University of Malta（马耳他大学）
Current research in iris recognition is moving towards enabling more relaxed acquisition conditions. This has effects on the quality of acquired images, with low resolution being a predominant issue. Here, we evaluate a super-resolution algorithm used to reconstruct iris images based on Eigen-transformation of local image patches. Each patch is reconstructed separately, allowing better quality of enhanced images by preserving local information. Contrast enhancement is used to improve the reconstruction quality, while matcher fusion has been adopted to improve iris recognition performance. We v…
3D shape recognition has attracted more and more attention as a task of 3D vision research. The proliferation of 3D data encourages various deep learning methods based on 3D data. Now there have been many deep learning models based on point-cloud data or multi-view data alone. However, in the era of big data, integrating data of two different modals to obtain a unified 3D shape descriptor is bound to improve the recognition accuracy. Therefore, this paper proposes a fusion network based on multimodal attention mechanism for 3D shape recognition. Considering the limitations of multi-view data, …
University of Trento（特伦托大学）；Peking University（北京大学）；Lingxi Artificial Intelligence Co., Ltd（灵汐人工智能有限公司）
Gesture recognition is a hot topic in computer vision and pattern recognition, which plays a vitally important role in natural human-computer interface. Although great progress has been made recently, fast and robust hand gesture recognition remains an open problem, since the existing methods have not well balanced the performance and the efficiency simultaneously. To bridge it, this work combines image entropy and density clustering to exploit the key frames from hand gesture video for further feature extraction, which can improve the efficiency of recognition. Moreover, a feature fusion stra…
Sign Languages are expressed through hand and upper body gestures as well as facial expressions. Therefore, Sign Language Recognition (SLR) needs to focus on all such cues. Previous work uses hand-crafted mechanisms or network aggregation to extract the different cue features, to increase SLR performance. This is slow and involves complicated architectures. We propose a more straightforward approach that focuses on training separate cue models specializing on the dominant hand, hands, face, and upper body regions. We compare the performance of 3D Convolutional Neural Network (CNN) models speci…
