Papers by Selen Pehlivan
Text-to-Multimodal Retrieval with Bimodal Input Fusion in Shared Cross-Modal Transformer (2024.lrec-main)
Copied to clipboard
| Challenge: | Multimodal video retrieval systems are needed for multimodal content retrieval . multimodal video search systems are sub-optimal for multi-modal content representations . |
| Approach: | They propose a model that learns retrieval cues for the textual query from multiple modalities and a shared embedding space with task-specific contrastive loss functions. |
| Outcome: | The proposed model outperforms state-of-the-art methods on the MSR-VTT and YouCook2 datasets and shows significant improvements from baseline. |
Learning to Describe Implicit Changes: Noise-robust Pre-training for Image Difference Captioning (2025.findings-emnlp)
Copied to clipboard
Zixin Guo, Jiayang Sun, Tzu-Jui Julius Wang, Abduljalil Radman, Selen Pehlivan, Min Cao, Jorma Laaksonen
| Challenge: | Large Multimodal Models (LMMs) are used to capture subtle differences between images but are noisy and coarse summaries. |
| Approach: | They propose a noise-robust approach to image difference capture using large multimodal models . they use LMMs with structured prompts to generate fine-grained change descriptions . |
| Outcome: | The proposed model outperforms streamlined architectures and improves inference efficiency. |