Alert button
Picture for Munawar Hayat

Munawar Hayat

Alert button

EraseDiff: Erasing Data Influence in Diffusion Models

Jan 11, 2024
Jing Wu, Trung Le, Munawar Hayat, Mehrtash Harandi

Viaarxiv icon

DiffAugment: Diffusion based Long-Tailed Visual Relationship Recognition

Jan 01, 2024
Parul Gupta, Tuan Nguyen, Abhinav Dhall, Munawar Hayat, Trung Le, Thanh-Toan Do

Viaarxiv icon

AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset

Nov 26, 2023
Zhixi Cai, Shreya Ghosh, Aman Pankaj Adatia, Munawar Hayat, Abhinav Dhall, Kalin Stefanov

Viaarxiv icon

Unified Open-Vocabulary Dense Visual Prediction

Jul 17, 2023
Hengcan Shi, Munawar Hayat, Jianfei Cai

Figure 1 for Unified Open-Vocabulary Dense Visual Prediction
Figure 2 for Unified Open-Vocabulary Dense Visual Prediction
Figure 3 for Unified Open-Vocabulary Dense Visual Prediction
Figure 4 for Unified Open-Vocabulary Dense Visual Prediction
Viaarxiv icon

Open-Vocabulary Object Detection via Scene Graph Discovery

Jul 07, 2023
Hengcan Shi, Munawar Hayat, Jianfei Cai

Figure 1 for Open-Vocabulary Object Detection via Scene Graph Discovery
Figure 2 for Open-Vocabulary Object Detection via Scene Graph Discovery
Figure 3 for Open-Vocabulary Object Detection via Scene Graph Discovery
Figure 4 for Open-Vocabulary Object Detection via Scene Graph Discovery
Viaarxiv icon

"Glitch in the Matrix!": A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization

May 05, 2023
Zhixi Cai, Shreya Ghosh, Abhinav Dhall, Tom Gedeon, Kalin Stefanov, Munawar Hayat

Figure 1 for "Glitch in the Matrix!": A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization
Figure 2 for "Glitch in the Matrix!": A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization
Figure 3 for "Glitch in the Matrix!": A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization
Figure 4 for "Glitch in the Matrix!": A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization
Viaarxiv icon

Real-time Trajectory-based Social Group Detection

Apr 12, 2023
Simindokht Jahangard, Munawar Hayat, Hamid Rezatofighi

Figure 1 for Real-time Trajectory-based Social Group Detection
Figure 2 for Real-time Trajectory-based Social Group Detection
Figure 3 for Real-time Trajectory-based Social Group Detection
Figure 4 for Real-time Trajectory-based Social Group Detection
Viaarxiv icon

ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning

Mar 22, 2023
Islam Nassar, Munawar Hayat, Ehsan Abbasnejad, Hamid Rezatofighi, Gholamreza Haffari

Figure 1 for ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning
Figure 2 for ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning
Figure 3 for ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning
Figure 4 for ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning
Viaarxiv icon

MARLIN: Masked Autoencoder for facial video Representation LearnINg

Nov 12, 2022
Zhixi Cai, Shreya Ghosh, Kalin Stefanov, Abhinav Dhall, Jianfei Cai, Hamid Rezatofighi, Reza Haffari, Munawar Hayat

Figure 1 for MARLIN: Masked Autoencoder for facial video Representation LearnINg
Figure 2 for MARLIN: Masked Autoencoder for facial video Representation LearnINg
Figure 3 for MARLIN: Masked Autoencoder for facial video Representation LearnINg
Figure 4 for MARLIN: Masked Autoencoder for facial video Representation LearnINg
Viaarxiv icon

LAVA: Label-efficient Visual Learning and Adaptation

Oct 19, 2022
Islam Nassar, Munawar Hayat, Ehsan Abbasnejad, Hamid Rezatofighi, Mehrtash Harandi, Gholamreza Haffari

Figure 1 for LAVA: Label-efficient Visual Learning and Adaptation
Figure 2 for LAVA: Label-efficient Visual Learning and Adaptation
Figure 3 for LAVA: Label-efficient Visual Learning and Adaptation
Figure 4 for LAVA: Label-efficient Visual Learning and Adaptation
Viaarxiv icon