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 maps with the goal of improving both recognition accuracy and efficiency. In addition, we use a skipping operation to further reduce the computation cost of action recognition. Extensive experiments on Something V1 & V2, Jester and Mini-Kinetics show that our approach can achieve about 40% computation savings with comparable accuracy to state-of-the-art methods. The project page can be found at https://mengyuest.github.io/AdaFuse/
Southeast University（东南大学）；Microsoft Research Asia（微软亚洲研究院）；The Johns Hopkins University（约翰斯·霍普金斯大学）
Occlusion is probably the biggest challenge for human pose estimation in the wild. Typical solutions often rely on intrusive sensors such as IMUs to detect occluded joints. To make the task truly unconstrained, we present AdaFuse, an adaptive multiview fusion method, which can enhance the features in occluded views by leveraging those in visible views. The core of AdaFuse is to determine the point-point correspondence between two views which we solve effectively by exploring the sparsity of the heatmap representation. We also learn an adaptive fusion weight for each camera view to reflect its …
AdaFuse-Det: Adaptive Cross-Modal Fusion of Event Cameras for Robust Object Detection in Low-Light RGB Imagery
SRM University AP, India（印度SRM大学AP分校）；Aptiv, Bengaluru, India（印度Aptiv公司，班加罗尔）；Arizona State University, USA（美国亚利桑那州立大学）；Sejong University, South Korea（韩国世宗大学）；Indian Institute of Information Technology Sri City, India（印度Sri City信息学院）
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 …
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 …
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）
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…
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…
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, …
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…
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 …
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…
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…
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…
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…
Only a few studies have been reported regarding human ear recognition in long wave infrared band. Thus, we have created ear database based on long wave infrared band. We have called that the database is long wave infrared band MIDAS consisting of 2430 records of 81 subjects. Thermal band provides seamless operation both night and day, robust against spoofing with understanding live ear and invariant to illumination conditions for human ear recognition. We have proposed to use different algorithms to reveal the distinctive features. Then, we have reduced the number of dimensions using subspace …
Feature Representation Learning with Adaptive Displacement Generation and Transformer Fusion for Micro-Expression Recognition
Wuhan University（武汉大学）；Meta Reality Labs（Meta现实实验室）；OPPO US Research Center, InnoPeak Technology Inc（OPPO美国研究中心，InnoPeak科技公司）；FiberHome Telecommunication Technologies Co., Ltd（烽火通信科技股份有限公司）
CMFN: Cross-Modal Fusion Network for Irregular Scene Text Recognition
Intelligent Software Research Center, Institute of Software Chinese Academy of Sciences（中国科学院软件研究所智能软件研究中心）；University of Chinese Academy of Sciences（中国科学院大学）；The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所复杂系统认知与决策智能实验室）；State Key Laboratory of Computer Science, Institute of Software Chinese Academy of Sciences（中国科学院软件研究所计算机科学国家重点实验室）
In this paper we present a technique for fusion of optical and thermal face images based on image pixel fusion approach. Out of several factors, which affect face recognition performance in case of visual images, illumination changes are a significant factor that needs to be addressed. Thermal images are better in handling illumination conditions but not very consistent in capturing texture details of the faces. Other factors like sunglasses, beard, moustache etc also play active role in adding complicacies to the recognition process. Fusion of thermal and visual images is a solution to overco…
Automation and Control Institute (ACIN), TU Wien（维也纳技术大学自动化与控制研究所）；Italian Institute of Technology（意大利理工学院）
Providing machines with the ability to recognize objects like humans has always been one of the primary goals of machine vision. The introduction of RGB-D cameras has paved the way for a significant leap forward in this direction thanks to the rich information provided by these sensors. However, the machine vision community still lacks an effective method to synergically use the RGB and depth data to improve object recognition. In order to take a step in this direction, we introduce a novel end-to-end architecture for RGB-D object recognition called recurrent convolutional fusion (RCFusion). O…
University of South Carolina（南卡罗来纳大学）；Innopeak Technology Inc.（Innopeak科技公司）；Sigma Technologies（12西格玛科技公司）；JD.com, Inc.（京东集团）；University of Washington Bothell（华盛顿大学博塞尔分校）
Emotion recognition plays an important role in human-computer interaction (HCI) and has been extensively studied for decades. Although tremendous improvements have been achieved for posed expressions, recognizing human emotions in "close-to-real-world" environments remains a challenge. In this paper, we proposed two strategies to fuse information extracted from different modalities, i.e., audio and visual. Specifically, we utilized LBP-TOP, an ensemble of CNNs, and a bi-directional LSTM (BLSTM) to extract features from the visual channel, and the OpenSmile toolkit to extract features from the …
University of South Florida（南佛罗里达大学）；Federal University of Bahia（巴伊亚联邦大学）
We present an unconstrained ear recognition framework that outperforms state-of-the-art systems in different publicly available image databases. To this end, we developed CNN-based solutions for ear normalization and description, we used well-known handcrafted descriptors, and we fused learned and handcrafted features to improve recognition. We designed a two-stage landmark detector that successfully worked under untrained scenarios. We used the results generated to perform a geometric image normalization that boosted the performance of all evaluated descriptors. Our CNN descriptor outperforme…
JJT University（JJT大学）；GRMECT Research Center（GRMECT研究中心）
Hybrid approach has a special status among Face Recognition Systems as they combine different recognition approaches in an either serial or parallel to overcome the shortcomings of individual methods. This paper explores the area of Hybrid Face Recognition using score based strategy as a combiner/fusion process. In proposed approach, the recognition system operates in two modes: training and classification. Training mode involves normalization of the face images (training set), extracting appropriate features using Principle Component Analysis (PCA) and Independent Component Analysis (ICA). Th…
Convolution neural netwotks (CNNs) are successfully applied in image recognition task. In this study, we explore the approach of automatic herbal recognition with CNNs and build the standard Chinese herbs datasets firstly. According to the characteristics of herbal images, we proposed the competitive attentional fusion pyramid networks to model the features of herbal image, which mdoels the relationship of feature maps from different levels, and re-weights multi-level channels with channel-wise attention mechanism. In this way, we can dynamically adjust the weight of feature maps from various …
A Multi-Stage Adaptive Feature Fusion Neural Network for Multimodal Gait Recognition
Central South University（中南大学）；Southern University of Science and Technology（南方科技大学）；Research Institute of Trustworthy Autonomous System, Southern University of Science and Technology（南方科技大学可信自主系统研究院）
Tripura University（特里普拉大学）；Jadavpur University（贾达普大学）；Université Pierre et Marie Curie, Paris-6（皮埃尔和玛丽·居里大学（巴黎第六大学））；Université Denis Diderot, Paris-7（丹尼斯·狄德罗大学（巴黎第七大学））
This paper presents a comparative study of two different methods, which are based on fusion and polar transformation of visual and thermal images. Here, investigation is done to handle the challenges of face recognition, which include pose variations, changes in facial expression, partial occlusions, variations in illumination, rotation through different angles, change in scale etc. To overcome these obstacles we have implemented and thoroughly examined two different fusion techniques through rigorous experimentation. In the first method log-polar transformation is applied to the fused images …
Jiangsu University（江苏大学）；Nanjing Institute of Technology（南京工程学院）；University of Oulu（奥卢大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Xiamen University（厦门大学）
Micro-Expression Recognition has become challenging, as it is extremely difficult to extract the subtle facial changes of micro-expressions. Recently, several approaches proposed several expression-shared features algorithms for micro-expression recognition. However, they do not reveal the specific discriminative characteristics, which lead to sub-optimal performance. This paper proposes a novel Feature Refinement ({FR}) with expression-specific feature learning and fusion for micro-expression recognition. It aims to obtain salient and discriminative features for specific expressions and also …
We introduce a deep convolutional neural networks (CNN) architecture to classify facial attributes and recognize face images simultaneously via a shared learning paradigm to improve the accuracy for facial attribute prediction and face recognition performance. In this method, we use facial attributes as an auxiliary source of information to assist CNN features extracted from the face images to improve the face recognition performance. Specifically, we use a shared CNN architecture that jointly predicts facial attributes and recognize face images simultaneously via a shared learning parameters,…
Institute for Human-Machine Communication（人机通信研究所）；Technical University of Munich（慕尼黑工业大学）
Acquiring spatio-temporal states of an action is the most crucial step for action classification. In this paper, we propose a data level fusion strategy, Motion Fused Frames (MFFs), designed to fuse motion information into static images as better representatives of spatio-temporal states of an action. MFFs can be used as input to any deep learning architecture with very little modification on the network. We evaluate MFFs on hand gesture recognition tasks using three video datasets - Jester, ChaLearn LAP IsoGD and NVIDIA Dynamic Hand Gesture Datasets - which require capturing long-term tempora…
