Search Results for author: Gaurav Bharaj

Found 20 papers, 2 papers with code

What Does an Audio Deepfake Detector Focus on? A Study in the Time Domain

no code implementations23 Jan 2025 Petr Grinberg, Ankur Kumar, Surya Koppisetti, Gaurav Bharaj

Adding explanations to audio deepfake detection (ADD) models will boost their real-world application by providing insight on the decision making process.

Audio Deepfake Detection Decision Making +2

Learn from Real: Reality Defender's Submission to ASVspoof5 Challenge

no code implementations9 Oct 2024 Yi Zhu, Chirag Goel, Surya Koppisetti, Trang Tran, Ankur Kumar, Gaurav Bharaj

Our system SLIM learns the style-linguistics dependency embeddings from various types of bonafide speech using self-supervised contrastive learning.

Audio Deepfake Detection Contrastive Learning +2

SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection

no code implementations26 Jul 2024 Yi Zhu, Surya Koppisetti, Trang Tran, Gaurav Bharaj

The learned features are then used in complement with standard pretrained acoustic features (e. g., Wav2vec) to learn a classifier on the real and fake classes.

Audio Deepfake Detection DeepFake Detection +1

Towards Attention-based Contrastive Learning for Audio Spoof Detection

no code implementations3 Jul 2024 Chirag Goel, Surya Koppisetti, Ben Colman, Ali Shahriyari, Gaurav Bharaj

Experiments show that our framework successfully disentangles the bonafide and spoof classes and helps learn better classifiers for the task.

Contrastive Learning Representation Learning

AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection

no code implementations CVPR 2024 Trevine Oorloff, Surya Koppisetti, Nicolò Bonettini, Divyaraj Solanki, Ben Colman, Yaser Yacoob, Ali Shahriyari, Gaurav Bharaj

We present Audio-Visual Feature Fusion (AVFF), a two-stage cross-modal learning method that explicitly captures the correspondence between the audio and visual modalities for improved deepfake detection.

Contrastive Learning DeepFake Detection +2

FaceLift: Semi-supervised 3D Facial Landmark Localization

no code implementations CVPR 2024 David Ferman, Pablo Garrido, Gaurav Bharaj

In the supervised learning case, such methods usually rely on 3D landmark datasets derived from 3DMM-based registration that often lack spatial definition alignment, as compared with that chosen by hand-labeled human consensus, e. g., how are eyebrow landmarks defined?

3D Face Reconstruction 3D Facial Landmark Localization +1

Common Sense Reasoning for Deepfake Detection

1 code implementation31 Jan 2024 Yue Zhang, Ben Colman, Xiao Guo, Ali Shahriyari, Gaurav Bharaj

To address these challenges, we frame deepfake detection as a Deepfake Detection VQA (DD-VQA) task and model human intuition by providing textual explanations that describe common sense reasons for labeling an image as real or fake.

Binary Classification Common Sense Reasoning +4

Common-Sense Bias Modeling for Classification Tasks

no code implementations24 Jan 2024 Miao Zhang, Zee Fryer, Ben Colman, Ali Shahriyari, Gaurav Bharaj

To this end, we propose a novel framework to extract comprehensive biases in image datasets based on textual descriptions, a common sense-rich modality.

Classification Common Sense Reasoning

Implicit Neural Head Synthesis via Controllable Local Deformation Fields

no code implementations CVPR 2023 Chuhan Chen, Matthew O'Toole, Gaurav Bharaj, Pablo Garrido

We build on part-based implicit shape models that decompose a global deformation field into local ones.

Few-shot Geometry-Aware Keypoint Localization

no code implementations CVPR 2023 Xingzhe He, Gaurav Bharaj, David Ferman, Helge Rhodin, Pablo Garrido

Supervised keypoint localization methods rely on large manually labeled image datasets, where objects can deform, articulate, or occlude.

3D geometry Object Localization

Unsupervised Facial Performance Editing via Vector-Quantized StyleGAN Representations

no code implementations ICCV 2023 Berkay Kicanaoglu, Pablo Garrido, Gaurav Bharaj

Such representations along with 3D tracking can be used as self-supervision to train a generator with control over coarse expressions and finer facial attributes.

Face Generation Face Model +3

Towards Device Efficient Conditional Image Generation

no code implementations19 Mar 2022 Nisarg A. Shah, Gaurav Bharaj

We present a novel algorithm to reduce tensor compute required by a conditional image generation autoencoder without sacrificing quality of photo-realistic image generation.

Conditional Image Generation

Multi-Domain Multi-Definition Landmark Localization for Small Datasets

no code implementations19 Mar 2022 David Ferman, Gaurav Bharaj

Training a small dataset alongside a large(r) dataset helps with robust learning for the former, and provides a universal mechanism for facial landmark localization for new and/or smaller standard datasets.

Decoder Face Alignment

Generative Landmarks

no code implementations8 Apr 2021 David Ferman, Gaurav Bharaj

We propose a general purpose approach to detect landmarks with improved temporal consistency, and personalization.

Generative Adversarial Network Translation

Grapheme-to-Phoneme Transformer Model for Transfer Learning Dialects

no code implementations8 Apr 2021 Eric Engelhart, Mahsa Elyasi, Gaurav Bharaj

And transformer-based models require significant training data, and do not generalize well, especially for dialects with limited data.

Text to Speech Transfer Learning

Flavored Tacotron: Conditional Learning for Prosodic-linguistic Features

no code implementations8 Apr 2021 Mahsa Elyasi, Gaurav Bharaj

In this work, we propose a novel carefully designed strategy for conditioning Tacotron-2 on two fundamental prosodic features in English -- stress syllable and pitch accent, that help achieve more natural prosody.

Decoder Speech Synthesis +2

Practical Face Reconstruction via Differentiable Ray Tracing

1 code implementation13 Jan 2021 Abdallah Dib, Gaurav Bharaj, Junghyun Ahn, Cédric Thébault, Philippe-Henri Gosselin, Marco Romeo, Louis Chevallier

The proposed method models scene illumination via a novel, parameterized virtual light stage, which in-conjunction with differentiable ray-tracing, introduces a coarse-to-fine optimization formulation for face reconstruction.

3D geometry Attribute +1

StyleRig: Rigging StyleGAN for 3D Control over Portrait Images

no code implementations CVPR 2020 Ayush Tewari, Mohamed Elgharib, Gaurav Bharaj, Florian Bernard, Hans-Peter Seidel, Patrick Pérez, Michael Zollhöfer, Christian Theobalt

StyleGAN generates photorealistic portrait images of faces with eyes, teeth, hair and context (neck, shoulders, background), but lacks a rig-like control over semantic face parameters that are interpretable in 3D, such as face pose, expressions, and scene illumination.

Face Reflectance and Geometry Modeling via Differentiable Ray Tracing

no code implementations3 Oct 2019 Abdallah Dib, Gaurav Bharaj, Junghyun Ahn, Cedric Thebault, Philippe-Henri Gosselin, Louis Chevallier

We present a novel strategy to automatically reconstruct 3D faces from monocular images with explicitly disentangled facial geometry (pose, identity and expression), reflectance (diffuse and specular albedo), and self-shadows.

FML: Face Model Learning from Videos

no code implementations CVPR 2019 Ayush Tewari, Florian Bernard, Pablo Garrido, Gaurav Bharaj, Mohamed Elgharib, Hans-Peter Seidel, Patrick Pérez, Michael Zollhöfer, Christian Theobalt

In contrast, we propose multi-frame video-based self-supervised training of a deep network that (i) learns a face identity model both in shape and appearance while (ii) jointly learning to reconstruct 3D faces.

3D Reconstruction Face Model +1

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