Vision-Language Models

VisToT: Vision-Augmented Table-to-Text Generation EMNLP 2022 Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning NeurIPS 2022 VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts NeurIPS 2022 Voxel-informed Language Grounding ACL 2022 When does CLIP generalize better than unimodal models? When judging human-centric concepts ACL 2022 Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality CVPR 2022 Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark NeurIPS 2022 Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP AAAI 2022 CLIPScore: A Reference-free Evaluation Metric for Image Captioning EMNLP 2021 Consensus Graph Representation Learning for Better Grounded Image Captioning AAAI 2021 Data Efficient Masked Language Modeling for Vision and Language EMNLP 2021 Does Vision-and-Language Pretraining Improve Lexical Grounding? EMNLP 2021 E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning ACL 2021 ERNIE-ViL: Knowledge Enhanced Vision-Language Representations through Scene Graphs AAAI 2021 Improving Pre-trained Vision-and-Language Embeddings for Phrase Grounding EMNLP 2021 Investigating Negation in Pre-trained Vision-and-language Models EMNLP 2021 Kaleido-BERT: Vision-Language Pre-Training on Fashion Domain CVPR 2021 MultiMET: A Multimodal Dataset for Metaphor Understanding ACL 2021 MURAL: Multimodal, Multitask Representations Across Languages EMNLP 2021 NICE: Neural Image Commenting with Empathy EMNLP 2021 Recognizing Multimodal Entailment ACL 2021 Scheduled Sampling in Vision-Language Pretraining with Decoupled Encoder-Decoder Network AAAI 2021 Seeing Out of the Box: End-to-End Pre-Training for Vision-Language Representation Learning CVPR 2021 Text2Mol: Cross-Modal Molecule Retrieval with Natural Language Queries EMNLP 2021 Topological Planning With Transformers for Vision-and-Language Navigation CVPR 2021