Multimodal Learning

Grounding Language to Autonomously-Acquired Skills via Goal Generation ICLR 2021 HAIR: Hierarchical Visual-Semantic Relational Reasoning for Video Question Answering ICCV 2021 Home Action Genome: Cooperative Compositional Action Understanding CVPR 2021 HOTR: End-to-End Human-Object Interaction Detection With Transformers CVPR 2021 How2Sign: A Large-Scale Multimodal Dataset for Continuous American Sign Language CVPR 2021 How Human Centered AI Will Contribute Towards Intelligent Gaming Systems AAAI 2021 How to leverage the multimodal EHR data for better medical prediction? EMNLP 2021 Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text EMNLP 2021 Image Retrieval for Arguments Using Stance-Aware Query Expansion EMNLP 2021 Imagine, Reason and Write: Visual Storytelling with Graph Knowledge and Relational Reasoning AAAI 2021 IMENet: Joint 3D Semantic Scene Completion and 2D Semantic Segmentation through Iterative Mutual Enhancement IJCAI 2021 Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis EMNLP 2021 Improving OCR-Based Image Captioning by Incorporating Geometrical Relationship CVPR 2021 Improving Sign Language Translation With Monolingual Data by Sign Back-Translation CVPR 2021 Inflate and Shrink:Enriching and Reducing Interactions for Fast Text-Image Retrieval EMNLP 2021 Integrating Visuospatial, Linguistic, and Commonsense Structure into Story Visualization EMNLP 2021 Intentonomy: A Dataset and Study Towards Human Intent Understanding CVPR 2021 “I’ve Seen Things You People Wouldn’t Believe”: Hallucinating Entities in GuessWhat?! ACL 2021 Joint Color-irrelevant Consistency Learning and Identity-aware Modality Adaptation for Visible-infrared Cross Modality Person Re-identification AAAI 2021 Joint Multi-modal Aspect-Sentiment Analysis with Auxiliary Cross-modal Relation Detection EMNLP 2021 Journalistic Guidelines Aware News Image Captioning EMNLP 2021 Kaleido-BERT: Vision-Language Pre-Training on Fashion Domain CVPR 2021 KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation ACL 2021 KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA CVPR 2021 LaPred: Lane-Aware Prediction of Multi-Modal Future Trajectories of Dynamic Agents CVPR 2021