Search Results for author: Abhinav Dhall

Found 30 papers, 13 papers with code

Audio-visual video face hallucination with frequency supervision and cross modality support by speech based lip reading loss

no code implementations20 Nov 2022 Shailza Sharma, Abhinav Dhall, Vinay Kumar, Vivek Singh Bawa

In order to learn these fine spatio-temporal motion details, we propose a novel cross-modal audio-visual Video Face Hallucination Generative Adversarial Network (VFH-GAN).

Face Hallucination Lip Reading

MARLIN: Masked Autoencoder for facial video Representation LearnINg

1 code implementation12 Nov 2022 Zhixi Cai, Shreya Ghosh, Kalin Stefanov, Abhinav Dhall, Jianfei Cai, Hamid Rezatofighi, Reza Haffari, Munawar Hayat

This paper proposes a self-supervised approach to learn universal facial representations from videos, that can transfer across a variety of facial analysis tasks such as Facial Attribute Recognition (FAR), Facial Expression Recognition (FER), DeepFake Detection (DFD), and Lip Synchronization (LS).

DeepFake Detection Face Swapping +5

RAZE: Region Guided Self-Supervised Gaze Representation Learning

no code implementations4 Aug 2022 Neeru Dubey, Shreya Ghosh, Abhinav Dhall

Automatic eye gaze estimation is an important problem in vision based assistive technology with use cases in different emerging topics such as augmented reality, virtual reality and human-computer interaction.

Gaze Estimation Representation Learning +1

'Labelling the Gaps': A Weakly Supervised Automatic Eye Gaze Estimation

1 code implementation3 Aug 2022 Shreya Ghosh, Abhinav Dhall, Jarrod Knibbe, Munawar Hayat

Our proposed method reduces the annotation effort to as low as 2. 67%, with minimal impact on performance; indicating the potential of our model enabling gaze estimation 'in-the-wild' setup.

Gaze Estimation

Visual Representations of Physiological Signals for Fake Video Detection

no code implementations18 Jul 2022 Kalin Stefanov, Bhawna Paliwal, Abhinav Dhall

We investigate two strategies for combining the video and physiology modalities, either by augmenting the video with information from the physiology or by novelly learning the fusion of those two modalities with a proposed Graph Convolutional Network architecture.

Misinformation

AV-Gaze: A Study on the Effectiveness of Audio Guided Visual Attention Estimation for Non-Profilic Faces

1 code implementation7 Jul 2022 Shreya Ghosh, Abhinav Dhall, Munawar Hayat, Jarrod Knibbe

In challenging real-life conditions such as extreme head-pose, occlusions, and low-resolution images where the visual information fails to estimate visual attention/gaze direction, audio signals could provide important and complementary information.

MTGLS: Multi-Task Gaze Estimation with Limited Supervision

no code implementations23 Oct 2021 Shreya Ghosh, Munawar Hayat, Abhinav Dhall, Jarrod Knibbe

Our proposed framework outperforms the unsupervised state-of-the-art on CAVE (by 6. 43%) and even supervised state-of-the-art methods on Gaze360 (by 6. 59%) datasets.

Gaze Estimation

Frequency Aware Face Hallucination Generative Adversarial Network with Semantic Structural Constraint

no code implementations5 Oct 2021 Shailza Sharma, Abhinav Dhall, Vinay Kumar

To explicitly encode the high frequency components, an auto encoder is proposed to generate high resolution coefficients of Discrete Cosine Transform (DCT).

Face Hallucination

Automatic Gaze Analysis: A Survey of Deep Learning based Approaches

1 code implementation12 Aug 2021 Shreya Ghosh, Abhinav Dhall, Munawar Hayat, Jarrod Knibbe, Qiang Ji

Eye gaze analysis is an important research problem in the field of Computer Vision and Human-Computer Interaction.

Gaze Estimation

Self-Supervised Approach for Facial Movement Based Optical Flow

no code implementations4 May 2021 Muhannad Alkaddour, Usman Tariq, Abhinav Dhall

The aim of this work is threefold: (1) exploring self-supervised techniques to generate optical flow ground truth for face images; (2) computing baseline results on the effects of using face data to train Convolutional Neural Networks (CNN) for predicting optical flow; and (3) using the learned optical flow in micro-expression recognition to demonstrate its effectiveness.

Micro-Expression Recognition Optical Flow Estimation

FakeBuster: A DeepFakes Detection Tool for Video Conferencing Scenarios

no code implementations9 Jan 2021 Vineet Mehta, Parul Gupta, Ramanathan Subramanian, Abhinav Dhall

This paper proposes a new DeepFake detector FakeBuster for detecting impostors during video conferencing and manipulated faces on social media.

Face Swapping

Hyperrealistic Image Inpainting with Hypergraphs

1 code implementation5 Nov 2020 Gourav Wadhwa, Abhinav Dhall, Subrahmanyam Murala, Usman Tariq

In this paper, we introduce hypergraph convolution on spatial features to learn the complex relationship among the data.

Image Inpainting

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

no code implementations12 Jun 2020 Parul Gupta, Komal Chugh, Abhinav Dhall, Ramanathan Subramanian

We present \textbf{FakeET}-- an eye-tracking database to understand human visual perception of \emph{deepfake} videos.

EEG Face Swapping

Speak2Label: Using Domain Knowledge for Creating a Large Scale Driver Gaze Zone Estimation Dataset

no code implementations13 Apr 2020 Shreya Ghosh, Abhinav Dhall, Garima Sharma, Sarthak Gupta, Nicu Sebe

In this paper, a fully automatic technique for labelling an image based gaze behavior dataset for driver gaze zone estimation is proposed.

Gaze Prediction

Predicting Group Cohesiveness in Images

no code implementations31 Dec 2018 Shreya Ghosh, Abhinav Dhall, Nicu Sebe, Tom Gedeon

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.

Clustering and Learning from Imbalanced Data

no code implementations2 Nov 2018 Naman D. Singh, Abhinav Dhall

A learning classifier must outperform a trivial solution, in case of imbalanced data, this condition usually does not hold true.

DIF : Dataset of Perceived Intoxicated Faces for Drunk Person Identification

no code implementations25 May 2018 Vineet Mehta, Devendra Pratap Yadav, Sai Srinadhu Katta, Abhinav Dhall

Convolutional Neural Networks (CNN) and Deep Neural Networks (DNN) are trained for computing the video and audio baselines, respectively.

Person Identification

Prediction and Localization of Student Engagement in the Wild

1 code implementation3 Apr 2018 Amanjot Kaur, Aamir Mustafa, Love Mehta, Abhinav Dhall

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.

Association Multiple Instance Learning

Continuous Multimodal Emotion Recognition Approach for AVEC 2017

no code implementations18 Sep 2017 Narotam Singh, Nittin Singh, Abhinav Dhall

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.

Multimodal Emotion Recognition

Depression Scale Recognition from Audio, Visual and Text Analysis

2 code implementations18 Sep 2017 Shubham Dham, Anirudh Sharma, Abhinav Dhall

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.

Occlusion-Aware Human Pose Estimation with Mixtures of Sub-Trees

no code implementations3 Dec 2015 Ibrahim Radwan, Abhinav Dhall, Roland Goecke

The proposed method handles occlusions during the inference process by identifying overlapping regions between different sub-trees and introducing a penalty term for overlapping parts.

Pose Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.