Papers by Mohd Khizir Siddiqui
Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis (2022.aacl-main)
Copied to clipboard
| Challenge: | Existing self-supervised learning strategies focus on uni-modal applications . a recent study shows that multimodality is a major challenge for multi-modal systems . |
| Approach: | They propose two self-supervised pre-training methods that employ off-the-shelf multi-modal hate-speech data . they also incorporate multiple specialized pretext tasks to cater to complex multi-modity representation learning . |
| Outcome: | The proposed methods outperform the baseline self-supervised learning strategies on the Memotion challenge and the HarMeme task. |