Publications
2025
2024
- In SubmissionShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion ModelsIn Submission, 2024ShotAdapter enables text-to-multi-shot video generation with minimal fine-tuning, providing users control over shot number, duration, and content through shot-specific text prompts, along with a multi-shot video dataset collection pipeline.
- In SubmissionOptimization-Free Image Immunization Against Diffusion-Based EditingIn Submission, 2024DiffVax is an optimization-free image immunization framework that effectively protects against diffusion-based editing, generalizes to unseen content, is robust against counter-attacks, and shows promise in safeguarding video content.
- In Submission to TPAMITowards Social AI: A Survey on Understanding Social InteractionsIn Submission to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024This is the first survey to provide a comprehensive overview of machine learning studies on social understanding, encompassing both verbal and non-verbal approaches.
- ECCVW 2024 (Oral)
- CVPR 2024 (Highlight)RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion ModelsCVPR (Highlight), 2024RAVE is a zero-shot, lightweight, and fast framework for text-guided video editing, supporting videos of any length utilizing text-to-image pretrained diffusion models.
- IEEE FG 2024Transfer Learning for Cross-dataset Isolated Sign Language Recognition in Under-Resourced DatasetsIEEE International Conference on Automatic Face and Gesture Recognition (IEEE FG), 2024This study provides a publicly available cross-dataset transfer learning benchmark from two existing public Turkish SLR datasets.
2022
- CVPR 2022ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image PriorCVPR, 2022ISNAS-DIP is an image-specific Neural Architecture Search (NAS) strategy designed for the Deep Image Prior (DIP) framework, offering significantly reduced training requirements compared to conventional NAS methods.
- IEEE TACDomain-Incremental Continual Learning for Mitigating Bias in Facial Expression and Action Unit RecognitionIEEE Transactions on Affective Computing, 2022we propose the novel use of Continual Learning (CL), in particular, using Domain-Incremental Learning (Domain-IL) settings, as a potent bias mitigation method to enhance the fairness of Facial Expression Recognition (FER) systems.
- Nano Communication NetworksMolecular index modulation using convolutional neural networksNano Communication Networks, 2022We propose a novel convolutional neural network-based architecture for a uniquely designed molecular multiple-input-single-output topology, aimed at mitigating the detrimental effects of molecular interference in nano molecular communication.
2021
- LEAP-HRI 2021Towards Fair Affective Robotics: Continual Learning for Mitigating Bias in Facial Expression and Action Unit RecognitionWorkshop on Lifelong Learning and Personalization in Long-Term Human-Robot Interaction (LEAP-HRI), 16th ACM/IEEE International Conference on Human-Robot Interaction (HRI), 2021We propose the novel use of Continual Learning (CL) as a potent bias mitigation method to enhance the fairness of Facial Expression Recognition (FER) systems.
- Brain StimulationNeuroweaver: a platform for designing intelligent closed-loop neuromodulation systemsBrain Stimulation: Basic, Translational, and Clinical Research in Neuromodulation, 2021Our interactive platform enables the design of neuromodulation pipelines through a visually intuitive and user-friendly interface. (Google Summer of Code 2021 project)