| CyCLIP: Cyclic Contrastive Language-Image Pretraining | May 28, 2022 | Representation LearningVisual Reasoning | CodeCode Available | 1 |
| Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning | May 25, 2022 | text-classificationText Classification | CodeCode Available | 1 |
| Open Vocabulary Extreme Classification Using Generative Models | May 12, 2022 | ClassificationExtreme Multi-Label Classification | —Unverified | 0 |
| A Checkpoint on Multilingual Misogyny Identification | May 1, 2022 | Transfer Learningzero-shot-classification | —Unverified | 0 |
| PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining | Apr 29, 2022 | Image ClassificationLanguage Modeling | —Unverified | 0 |
| No Token Left Behind: Explainability-Aided Image Classification and Generation | Apr 11, 2022 | image-classificationImage Classification | CodeCode Available | 1 |
| Robust Cross-Modal Representation Learning with Progressive Self-Distillation | Apr 10, 2022 | Contrastive LearningImage Captioning | —Unverified | 0 |
| An Analysis of Semantically-Aligned Speech-Text Embeddings | Apr 4, 2022 | Automatic Speech RecognitionAutomatic Speech Recognition (ASR) | —Unverified | 0 |
| Geodesic Multi-Modal Mixup for Robust Fine-Tuning | Mar 8, 2022 | Image Captioningzero-shot-classification | CodeCode Available | 0 |
| Universal Prototype Transport for Zero-Shot Action Recognition and Localization | Mar 8, 2022 | Action RecognitionObject | —Unverified | 0 |
