Vision-Language Models

An Explainable Toolbox for Evaluating Pre-trained Vision-Language Models EMNLP 2022 Are Vision-Language Transformers Learning Multimodal Representations? A Probing Perspective AAAI 2022 Assessing Multilingual Fairness in Pre-trained Multimodal Representations ACL 2022 Bootstrapping a high quality multilingual multimodal dataset for Bletchley ACML 2022 Bridging the Gap between Recognition-level Pre-training and Commonsensical Vision-language Tasks ACL 2022 Character-centric Story Visualization via Visual Planning and Token Alignment EMNLP 2022 CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks NeurIPS 2022 CLIP-Forge: Towards Zero-Shot Text-To-Shape Generation CVPR 2022 CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP NeurIPS 2022 Contrastive Language-Image Pre-Training with Knowledge Graphs NeurIPS 2022 Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations ACL 2022 CPL: Counterfactual Prompt Learning for Vision and Language Models EMNLP 2022 Cross-modal Transfer Between Vision and Language for Protest Detection EMNLP 2022 CyCLIP: Cyclic Contrastive Language-Image Pretraining NeurIPS 2022 DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models EMNLP 2022 Distilled Dual-Encoder Model for Vision-Language Understanding EMNLP 2022 Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies? EMNLP 2022 DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training ACL 2022 ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models NeurIPS 2022 Exploring Compositional Image Retrieval with Hybrid Compositional Learning and Heuristic Negative Mining EMNLP 2022 Focus! Relevant and Sufficient Context Selection for News Image Captioning EMNLP 2022 GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection CVPR 2022 How Much Can CLIP Benefit Vision-and-Language Tasks? ICLR 2022 Image Segmentation Using Text and Image Prompts CVPR 2022 LAION-5B: An open large-scale dataset for training next generation image-text models NeurIPS 2022