An Approach to Complex Visual Data Interpretation with Vision-Language Models
Published at The 1st Large Vision - Language Model Learning and Applications Workshop, ACCV 2024
December 8, 2024
Our research adapted the MMMU benchmarks and utilized prompt engineering with a voting-based ensemble method to enhance Large Vision-Language Models' performance on complex visual data interpretation, achieving a top score of 0.85 in the LAVA Workshop 2024 challenge.
AI-Enhanced Photo Authenticity: A User-Focused Approach to Detecting and Analyzing Manipulated Images
Published at The 2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)
August 16, 2024
This paper presents the development of an AI-assisted system designed to aid users in identifying and verifying the genuineness of photos.
A Hybrid Approach for Cheapfake Detection Using Reputation Checking and End-To-End Network
Published at The 1st Workshop on Security-Centric Strategies for Combating Information Disorder, ACM AsiaCCS 2024
July 2, 2024
This research highlights the immense promise of using our proposed hybrid method in the fight against Cheapfakes, making a significant contribution to preserving the integrity of multimedia content.
A Unified Network for Detecting Out-Of-Context Information Using Generative Synthetic Data
Published at The 2024 International Conference on Multimedia Retrieval (ACM ICMR 2024)
June 11, 2024
This paper highlights the notable potential of employing an end-to-end network for Cheapfakes detection, which composes a significant contribution to the advancement of multimedia content integrity.
Transparent Tracking of Spermatozoa with YOLOv8
Published at The MediaEval 2023 Workshop, MMM 2024
February 1, 2024
A research for pointing out an efficient method for detection and tracking of spermatozoa, with YOLOv8 trained on a a COCO-format dataset.