1 code implementation • CVPR 2023 • 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).
Ranked #1 on Emotion Classification on CMU-MOSEI
1 code implementation • 12 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.
1 code implementation • 5 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.
1 code implementation • 13 Apr 2022 • Zhixi Cai, Kalin Stefanov, Abhinav Dhall, Munawar Hayat
Our baseline method for benchmarking the proposed dataset is a 3DCNN model, termed as Boundary Aware Temporal Forgery Detection (BA-TFD), which is guided via contrastive, boundary matching, and frame classification loss functions.
Ranked #1 on DeepFake Detection on LAV-DF
1 code implementation • 3 May 2023 • Zhixi Cai, Shreya Ghosh, Abhinav Dhall, Tom Gedeon, Kalin Stefanov, Munawar Hayat
The proposed baseline method, Boundary Aware Temporal Forgery Detection (BA-TFD), is a 3D Convolutional Neural Network-based architecture which effectively captures multimodal manipulations.
Ranked #1 on Temporal Forgery Localization on ForgeryNet
1 code implementation • 26 Nov 2023 • Zhixi Cai, Shreya Ghosh, Aman Pankaj Adatia, Munawar Hayat, Abhinav Dhall, Kalin Stefanov
The comprehensive benchmark of the proposed dataset utilizing state-of-the-art deepfake detection and localization methods indicates a significant drop in performance compared to previous datasets.
1 code implementation • 29 May 2020 • Komal Chugh, Parul Gupta, Abhinav Dhall, Ramanathan Subramanian
MDS is computed as an aggregate of dissimilarity scores between audio and visual segments in a video.
1 code implementation • 10 May 2018 • Sai Samarth R. Phaye, Apoorva Sikka, Abhinav Dhall, Deepti Bathula
We propose Dense Capsule Networks (DCNet) and Diverse Capsule Networks (DCNet++).
Ranked #7 on Image Classification on smallNORB
1 code implementation • 25 Apr 2018 • Skand Vishwanath Peri, Abhinav Dhall
The experiments show the effectiveness of the approach on the DFW data.
1 code implementation • 17 Apr 2020 • Vineet Mehta, Abhinav Dhall, Sujata Pal, Shehroz S. Khan
A larger reconstruction error indicates the occurrence of a fall.
1 code implementation • 3 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.
2 code implementations • 18 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.
1 code implementation • 4 Apr 2019 • Neeru Dubey, Shreya Ghosh, Abhinav Dhall
Automatic eye gaze estimation has interested researchers for a while now.
1 code implementation • 1 Feb 2023 • Monisha Singh, Ximi Hoque, Donghuo Zeng, Yanan Wang, Kazushi Ikeda, Abhinav Dhall
The experiments show the usefulness of the proposed dataset.
1 code implementation • 19 Sep 2023 • Surbhi Madan, Rishabh Jain, Gulshan Sharma, Ramanathan Subramanian, Abhinav Dhall
Bodily behavioral language is an important social cue, and its automated analysis helps in enhancing the understanding of artificial intelligence systems.
1 code implementation • 26 Mar 2024 • Hrishav Bakul Barua, Kalin Stefanov, KokSheik Wong, Abhinav Dhall, Ganesh Krishnasamy
High Dynamic Range (HDR) content (i. e., images and videos) has a broad range of applications.
1 code implementation • 3 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.
no code implementations • 13 Jun 2018 • Shreyank Jyoti, Abhinav Dhall
The proposed network achieves state-of-art results on the two databases.
no code implementations • 25 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.
no code implementations • 18 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.
no code implementations • 12 Oct 2016 • Xiaohua Huang, Abhinav Dhall, Xin Liu, Guoying Zhao, Jingang Shi, Roland Goecke, Matti Pietikainen
We fuse face, upperbody and scene information for robustness of GER against the challenging environments.
no code implementations • 3 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.
no code implementations • 23 Aug 2018 • Abhinav Dhall, Amanjot Kaur, Roland Goecke, Tom Gedeon
This paper details the sixth Emotion Recognition in the Wild (EmotiW) challenge.
no code implementations • 2 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.
no code implementations • 31 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.
no code implementations • 13 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.
no code implementations • 12 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.
no code implementations • 9 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.
no code implementations • 4 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 Micro-Expression Recognition +1
no code implementations • 5 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).
no code implementations • 23 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.
1 code implementation • 7 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.
no code implementations • 18 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.
no code implementations • 4 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.
no code implementations • 20 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).
no code implementations • 10 May 2023 • Shreya Ghosh, Rakibul Hasan, Pradyumna Agrawal, Zhixi Cai, Susannah Soon, Abhinav Dhall, Tom Gedeon
To this end, we design a user interface to generate an automatic feedback mechanism that integrates Pavlok and a deep learning based model to detect certain behaviours via an integrated user interface i. e. mobile or desktop application.
no code implementations • 7 Sep 2023 • Hrishav Bakul Barua, Ganesh Krishnasamy, KokSheik Wong, Kalin Stefanov, Abhinav Dhall
High Dynamic Range (HDR) content creation has become an important topic for modern media and entertainment sectors, gaming and Augmented/Virtual Reality industries.
no code implementations • 1 Jan 2024 • Parul Gupta, Tuan Nguyen, Abhinav Dhall, Munawar Hayat, Trung Le, Thanh-Toan Do
The task of Visual Relationship Recognition (VRR) aims to identify relationships between two interacting objects in an image and is particularly challenging due to the widely-spread and highly imbalanced distribution of <subject, relation, object> triplets.
no code implementations • 8 Feb 2024 • Hrishav Bakul Barua, Ganesh Krishnasamy, KokSheik Wong, Abhinav Dhall, Kalin Stefanov
High Dynamic Range (HDR) imaging aims to replicate the high visual quality and clarity of real-world scenes.
no code implementations • 1 Apr 2024 • Shahzeb Naeem, Muhammad Riyyan Khan, Usman Tariq, Abhinav Dhall, Carlos Ivan Colon, Hasan Al-Nashash
A question in the realm of deepfakes is slowly emerging pertaining to whether we can go beyond facial deepfakes and whether it would be beneficial to society.
no code implementations • 2 Apr 2024 • Shahzeb Naeem, Ramzi Al-Sharawi, Muhammad Riyyan Khan, Usman Tariq, Abhinav Dhall, Hasan Al-Nashash
This observation was supported by further analysis of various image properties.