GoswamiV. x 4
bookRéférences 4
Flava: A foundational language and vision alignment model
… The hateful memes challenge: Detecting hate speech in multimodal memes. Proceedings of ...
2026-01-20 00:00:00
Revisiting Machine Translation for Cross-lingual Classification
… In contrast, translate-train performs best at shallower tasks like sentiment analysis, ...
2023-05-23 00:00:00
Human-adversarial visual question answering
Performance on the most commonly used Visual Question Answering dataset (VQA v2) is starting to appr...
12-in-1: Multi-task vision and language representation learning
… We thus learn a separate classifier of the same form that predicts the sentiment (entai...