arXiv subjects

Abhinav Dhall

Publications and source records attributed to Abhinav Dhall.

At least 73 records · Page 4Linked to original sources

arXiv2021

FakeBuster: A DeepFakes Detection Tool for Video Conferencing Scenarios

This paper proposes a new DeepFake detector FakeBuster for detecting impostors during video conferencing and manipulated faces on social media. FakeBuster is a standalone deep learning based solution, which enables a user to detect if another person's video is manipulated or spoofed during a video conferencing based meeting. This tool is independent of video conferencing solutions and has been tested with Zoom and Skype applications. It uses a 3D convolutional neural network for predicting video segment-wise fakeness scores. The network is trained on a combination of datasets such as Deeperforensics, DFDC, VoxCeleb, and deepfake videos created using locally captured (for video conferencing scenarios) images. This leads to different environments and perturbations in the dataset, which improves the generalization of the deepfake network.

cs.CV↗

arXiv2020

Hyperrealistic Image Inpainting with Hypergraphs

Image inpainting is a non-trivial task in computer vision due to multiple possibilities for filling the missing data, which may be dependent on the global information of the image. Most of the existing approaches use the attention mechanism to learn the global context of the image. This attention mechanism produces semantically plausible but blurry results because of incapability to capture the global context. In this paper, we introduce hypergraph convolution on spatial features to learn the complex relationship among the data. We introduce a trainable mechanism to connect nodes using hyperedges for hypergraph convolution. To the best of our knowledge, hypergraph convolution have never been used on spatial features for any image-to-image tasks in computer vision. Further, we introduce gated convolution in the discriminator to enforce local consistency in the predicted image. The experiments on Places2, CelebA-HQ, Paris Street View, and Facades datasets, show that our approach achieves state-of-the-art results.

cs.CV↗

arXiv2020

Motion and Region Aware Adversarial Learning for Fall Detection with Thermal Imaging

Automatic fall detection is a vital technology for ensuring the health and safety of people. Home-based camera systems for fall detection often put people's privacy at risk. Thermal cameras can partially or fully obfuscate facial features, thus preserving the privacy of a person. Another challenge is the less occurrence of falls in comparison to the normal activities of daily living. As fall occurs rarely, it is non-trivial to learn algorithms due to class imbalance. To handle these problems, we formulate fall detection as an anomaly detection within an adversarial framework using thermal imaging. We present a novel adversarial network that comprises of two-channel 3D convolutional autoencoders which reconstructs the thermal data and the optical flow input sequences respectively. We introduce a technique to track the region of interest, a region-based difference constraint, and a joint discriminator to compute the reconstruction error. A larger reconstruction error indicates the occurrence of a fall. The experiments on a publicly available thermal fall dataset show the superior results obtained compared to the standard baseline.

cs.CV↗

arXiv2020

The eyes know it: FakeET -- An Eye-tracking Database to Understand Deepfake Perception

We present \textbf{FakeET}-- an eye-tracking database to understand human visual perception of \emph{deepfake} videos. Given that the principal purpose of deepfakes is to deceive human observers, FakeET is designed to understand and evaluate the ease with which viewers can detect synthetic video artifacts. FakeET contains viewing patterns compiled from 40 users via the \emph{Tobii} desktop eye-tracker for 811 videos from the \textit{Google Deepfake} dataset, with a minimum of two viewings per video. Additionally, EEG responses acquired via the \emph{Emotiv} sensor are also available. The compiled data confirms (a) distinct eye movement characteristics for \emph{real} vs \emph{fake} videos; (b) utility of the eye-track saliency maps for spatial forgery localization and detection, and (c) Error Related Negativity (ERN) triggers in the EEG responses, and the ability of the \emph{raw} EEG signal to distinguish between \emph{real} and \emph{fake} videos.

cs.CV↗

arXiv2019

DIF : Dataset of Perceived Intoxicated Faces for Drunk Person Identification

Traffic accidents cause over a million deaths every year, of which a large fraction is attributed to drunk driving. An automated intoxicated driver detection system in vehicles will be useful in reducing accidents and related financial costs. Existing solutions require special equipment such as electrocardiogram, infrared cameras or breathalyzers. In this work, we propose a new dataset called DIF (Dataset of perceived Intoxicated Faces) which contains audio-visual data of intoxicated and sober people obtained from online sources. To the best of our knowledge, this is the first work for automatic bimodal non-invasive intoxication detection. Convolutional Neural Networks (CNN) and Deep Neural Networks (DNN) are trained for computing the video and audio baselines, respectively. 3D CNN is used to exploit the Spatio-temporal changes in the video. A simple variation of the traditional 3D convolution block is proposed based on inducing non-linearity between the spatial and temporal channels. Extensive experiments are performed to validate the approach and baselines.

cs.CV↗

arXiv2019

Predicting Group Cohesiveness in Images

The cohesiveness of a group is an essential indicator of the emotional state, structure and success of a group of people. We study the factors that influence the perception of group-level cohesion and propose methods for estimating the human-perceived cohesion on the group cohesiveness scale. In order to identify the visual cues (attributes) for cohesion, we conducted a user survey. Image analysis is performed at a group-level via a multi-task convolutional neural network. For analyzing the contribution of facial expressions of the group members for predicting the Group Cohesion Score (GCS), a capsule network is explored. We add GCS to the Group Affect database and propose the `GAF-Cohesion database'. The proposed model performs well on the database and is able to achieve near human-level performance in predicting a group's cohesion score. It is interesting to note that group cohesion as an attribute, when jointly trained for group-level emotion prediction, helps in increasing the performance for the later task. This suggests that group-level emotion and cohesion are correlated.

cs.CV↗

arXiv2019

Unsupervised Learning of Eye Gaze Representation from the Web

Automatic eye gaze estimation has interested researchers for a while now. In this paper, we propose an unsupervised learning based method for estimating the eye gaze region. To train the proposed network "Ize-Net" in self-supervised manner, we collect a large `in the wild' dataset containing 1,54,251 images from the web. For the images in the database, we divide the gaze into three regions based on an automatic technique based on pupil-centers localization and then use a feature-based technique to determine the gaze region. The performance is evaluated on the Tablet Gaze and CAVE datasets by fine-tuning results of Ize-Net for the task of eye gaze estimation. The feature representation learned is also used to train traditional machine learning algorithms for eye gaze estimation. The results demonstrate that the proposed method learns a rich data representation, which can be efficiently fine-tuned for any eye gaze estimation dataset.

cs.CV↗

arXiv2018

Speech-Gesture Mapping and Engagement Evaluation in Human Robot Interaction

A robot needs contextual awareness, effective speech production and complementing non-verbal gestures for successful communication in society. In this paper, we present our end-to-end system that tries to enhance the effectiveness of non-verbal gestures. For achieving this, we identified prominently used gestures in performances by TED speakers and mapped them to their corresponding speech context and modulated speech based upon the attention of the listener. The proposed method utilized Convolutional Pose Machine [4] to detect the human gesture. Dominant gestures of TED speakers were used for learning the gesture-to-speech mapping. The speeches by them were used for training the model. We also evaluated the engagement of the robot with people by conducting a social survey. The effectiveness of the performance was monitored by the robot and it self-improvised its speech pattern on the basis of the attention level of the audience, which was calculated using visual feedback from the camera. The effectiveness of interaction as well as the decisions made during improvisation was further evaluated based on the head-pose detection and interaction survey.

cs.RO↗

arXiv2018

Clustering and Learning from Imbalanced Data

A learning classifier must outperform a trivial solution, in case of imbalanced data, this condition usually does not hold true. To overcome this problem, we propose a novel data level resampling method - Clustering Based Oversampling for improved learning from class imbalanced datasets. The essential idea behind the proposed method is to use the distance between a minority class sample and its respective cluster centroid to infer the number of new sample points to be generated for that minority class sample. The proposed algorithm has very less dependence on the technique used for finding cluster centroids and does not effect the majority class learning in any way. It also improves learning from imbalanced data by incorporating the distribution structure of minority class samples in generation of new data samples. The newly generated minority class data is handled in a way as to prevent outlier production and overfitting. Implementation analysis on different datasets using deep neural networks as the learning classifier shows the effectiveness of this method as compared to other synthetic data resampling techniques across several evaluation metrics.

cs.LG↗

arXiv2018

A Global Alignment Kernel based Approach for Group-level Happiness Intensity Estimation

With the progress in automatic human behavior understanding, analysing the perceived affect of multiple people has been recieved interest in affective computing community. Unlike conventional facial expression analysis, this paper primarily focuses on analysing the behaviour of multiple people in an image. The proposed method is based on support vector regression with the combined global alignment kernels (GAKs) to estimate the happiness intensity of a group of people. We first exploit Riesz-based volume local binary pattern (RVLBP) and deep convolutional neural network (CNN) based features for characterizing facial images. Furthermore, we propose to use the GAK for RVLBP and deep CNN features, respectively for explicitly measuring the similarity of two group-level images. Specifically, we exploit the global weight sort scheme to sort the face images from group-level image according to their spatial weights, making an efficient data structure to GAK. Lastly, we propose Multiple kernel learning based on three combination strategies for combining two respective GAKs based on RVLBP and deep CNN features, such that enhancing the discriminative ability of each GAK. Intensive experiments are performed on the challenging group-level happiness intensity database, namely HAPPEI. Our experimental results demonstrate that the proposed approach achieves promising performance for group happiness intensity analysis, when compared with the recent state-of-the-art methods.

cs.CV↗

arXiv2018

EmotiW 2018: Audio-Video, Student Engagement and Group-Level Affect Prediction

This paper details the sixth Emotion Recognition in the Wild (EmotiW) challenge. EmotiW 2018 is a grand challenge in the ACM International Conference on Multimodal Interaction 2018, Colorado, USA. The challenge aims at providing a common platform to researchers working in the affective computing community to benchmark their algorithms on `in the wild' data. This year EmotiW contains three sub-challenges: a) Audio-video based emotion recognition; b) Student engagement prediction; and c) Group-level emotion recognition. The databases, protocols and baselines are discussed in detail.

cs.CV↗

arXiv2018

Prediction and Localization of Student Engagement in the Wild

In this paper, we introduce a new dataset for student engagement detection and localization. Digital revolution has transformed the traditional teaching procedure and a result analysis of the student engagement in an e-learning environment would facilitate effective task accomplishment and learning. Well known social cues of engagement/disengagement can be inferred from facial expressions, body movements and gaze pattern. In this paper, student's response to various stimuli videos are recorded and important cues are extracted to estimate variations in engagement level. In this paper, we study the association of a subject's behavioral cues with his/her engagement level, as annotated by labelers. We then localize engaging/non-engaging parts in the stimuli videos using a deep multiple instance learning based framework, which can give useful insight into designing Massive Open Online Courses (MOOCs) video material. Recognizing the lack of any publicly available dataset in the domain of user engagement, a new `in the wild' dataset is created to study the subject engagement problem. The dataset contains 195 videos captured from 78 subjects which is about 16.5 hours of recording. We present detailed baseline results using different classifiers ranging from traditional machine learning to deep learning based approaches. The subject independent analysis is performed so that it can be generalized to new users. The problem of engagement prediction is modeled as a weakly supervised learning problem. The dataset is manually annotated by different labelers for four levels of engagement independently and the correlation studies between annotated and predicted labels of videos by different classifiers is reported. This dataset creation is an effort to facilitate research in various e-learning environments such as intelligent tutoring systems, MOOCs, and others.

cs.CV↗

arXiv2018

Expression Empowered ResiDen Network for Facial Action Unit Detection

The paper explores the topic of Facial Action Unit (FAU) detection in the wild. In particular, we are interested in answering the following questions: (1) how useful are residual connections across dense blocks for face analysis? (2) how useful is the information from a network trained for categorical Facial Expression Recognition (FER) for the task of FAU detection? The proposed network (ResiDen) exploits dense blocks along with residual connections and uses auxiliary information from a FER network. The experiments are performed on the EmotionNet and DISFA datasets. The experiments show the usefulness of facial expression information for AU detection. The proposed network achieves state-of-art results on the two databases. Analysis of the results for cross database protocol shows the effectiveness of the network.

cs.CV↗

arXiv2018

Dense and Diverse Capsule Networks: Making the Capsules Learn Better

Past few years have witnessed exponential growth of interest in deep learning methodologies with rapidly improving accuracies and reduced computational complexity. In particular, architectures using Convolutional Neural Networks (CNNs) have produced state-of-the-art performances for image classification and object recognition tasks. Recently, Capsule Networks (CapsNet) achieved significant increase in performance by addressing an inherent limitation of CNNs in encoding pose and deformation. Inspired by such advancement, we asked ourselves, can we do better? We propose Dense Capsule Networks (DCNet) and Diverse Capsule Networks (DCNet++). The two proposed frameworks customize the CapsNet by replacing the standard convolutional layers with densely connected convolutions. This helps in incorporating feature maps learned by different layers in forming the primary capsules. DCNet, essentially adds a deeper convolution network, which leads to learning of discriminative feature maps. Additionally, DCNet++ uses a hierarchical architecture to learn capsules that represent spatial information in a fine-to-coarser manner, which makes it more efficient for learning complex data. Experiments on image classification task using benchmark datasets demonstrate the efficacy of the proposed architectures. DCNet achieves state-of-the-art performance (99.75%) on MNIST dataset with twenty fold decrease in total training iterations, over the conventional CapsNet. Furthermore, DCNet++ performs better than CapsNet on SVHN dataset (96.90%), and outperforms the ensemble of seven CapsNet models on CIFAR-10 by 0.31% with seven fold decrease in number of parameters.

cs.CV↗

arXiv2018

DisguiseNet : A Contrastive Approach for Disguised Face Verification in the Wild

This paper describes our approach for the Disguised Faces in the Wild (DFW) 2018 challenge. The task here is to verify the identity of a person among disguised and impostors images. Given the importance of the task of face verification it is essential to compare methods across a common platform. Our approach is based on VGG-face architecture paired with Contrastive loss based on cosine distance metric. For augmenting the data set, we source more data from the internet. The experiments show the effectiveness of the approach on the DFW data. We show that adding extra data to the DFW dataset with noisy labels also helps in increasing the generalization performance of the network. The proposed network achieves 27.13% absolute increase in accuracy over the DFW baseline.

cs.CV↗

arXiv2017

Continuous Multimodal Emotion Recognition Approach for AVEC 2017

This paper reports the analysis of audio and visual features in predicting the continuous emotion dimensions under the seventh Audio/Visual Emotion Challenge (AVEC 2017), which was done as part of a B.Tech. 2nd year internship project. For visual features we used the HOG (Histogram of Gradients) features, Fisher encodings of SIFT (Scale-Invariant Feature Transform) features based on Gaussian mixture model (GMM) and some pretrained Convolutional Neural Network layers as features; all these extracted for each video clip. For audio features we used the Bag-of-audio-words (BoAW) representation of the LLDs (low-level descriptors) generated by openXBOW provided by the organisers of the event. Then we trained fully connected neural network regression model on the dataset for all these different modalities. We applied multimodal fusion on the output models to get the Concordance correlation coefficient on Development set as well as Test set.

cs.CV↗

arXiv2017

Depression Scale Recognition from Audio, Visual and Text Analysis

Depression is a major mental health disorder that is rapidly affecting lives worldwide. Depression not only impacts emotional but also physical and psychological state of the person. Its symptoms include lack of interest in daily activities, feeling low, anxiety, frustration, loss of weight and even feeling of self-hatred. This report describes work done by us for Audio Visual Emotion Challenge (AVEC) 2017 during our second year BTech summer internship. With the increase in demand to detect depression automatically with the help of machine learning algorithms, we present our multimodal feature extraction and decision level fusion approach for the same. Features are extracted by processing on the provided Distress Analysis Interview Corpus-Wizard of Oz (DAIC-WOZ) database. Gaussian Mixture Model (GMM) clustering and Fisher vector approach were applied on the visual data; statistical descriptors on gaze, pose; low level audio features and head pose and text features were also extracted. Classification is done on fused as well as independent features using Support Vector Machine (SVM) and neural networks. The results obtained were able to cross the provided baseline on validation data set by 17% on audio features and 24.5% on video features.

cs.CV↗

arXiv2016

Analyzing the Affect of a Group of People Using Multi-modal Framework

Millions of images on the web enable us to explore images from social events such as a family party, thus it is of interest to understand and model the affect exhibited by a group of people in images. But analysis of the affect expressed by multiple people is challenging due to varied indoor and outdoor settings, and interactions taking place between various numbers of people. A few existing works on Group-level Emotion Recognition (GER) have investigated on face-level information. Due to the challenging environments, face may not provide enough information to GER. Relatively few studies have investigated multi-modal GER. Therefore, we propose a novel multi-modal approach based on a new feature description for understanding emotional state of a group of people in an image. In this paper, we firstly exploit three kinds of rich information containing face, upperbody and scene in a group-level image. Furthermore, in order to integrate multiple person's information in a group-level image, we propose an information aggregation method to generate three features for face, upperbody and scene, respectively. We fuse face, upperbody and scene information for robustness of GER against the challenging environments. Intensive experiments are performed on two challenging group-level emotion databases to investigate the role of face, upperbody and scene as well as multi-modal framework. Experimental results demonstrate that our framework achieves very promising performance for GER.

cs.CV↗