Core AI

Bridging the Gap between Expression and Scene Text for Referring Expression Comprehension (Student Abstract) AAAI 2022 Bridging the Gap between Recognition-level Pre-training and Commonsensical Vision-language Tasks ACL 2022 CAESAR: An Embodied Simulator for Generating Multimodal Referring Expression Datasets NeurIPS 2022 CapOnImage: Context-driven Dense-Captioning on Image EMNLP 2022 Carbink: Fault-Tolerant Far Memory OSDI 2022 Certified Patch Robustness via Smoothed Vision Transformers CVPR 2022 Channel Importance Matters in Few-Shot Image Classification ICML 2022 ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning ACL 2022 Clean Text and Full-Body Transformer: Microsoft’s Submission to the WMT22 Shared Task on Sign Language Translation EMNLP 2022 Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-Based Super-resolution AAAI 2022 COGMEN: COntextualized GNN based Multimodal Emotion recognitioN NAACL 2022 Colar: Effective and Efficient Online Action Detection by Consulting Exemplars CVPR 2022 Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs ICML 2022 Comprehensive Multi-Modal Interactions for Referring Image Segmentation ACL 2022 Contextualized Spatio-Temporal Contrastive Learning With Self-Supervision CVPR 2022 Contrastive Regression for Domain Adaptation on Gaze Estimation CVPR 2022 Convolution of Convolution: Let Kernels Spatially Collaborate CVPR 2022 CoSIm: Commonsense Reasoning for Counterfactual Scene Imagination NAACL 2022 Could Giant Pre-trained Image Models Extract Universal Representations? NeurIPS 2022 CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation AAAI 2022 Crafting Better Contrastive Views for Siamese Representation Learning CVPR 2022 Cross Aggregation Transformer for Image Restoration NeurIPS 2022 Cross-Modal Mutual Learning for Audio-Visual Speech Recognition and Manipulation AAAI 2022 Cross-Modal Object Tracking: Modality-Aware Representations and a Unified Benchmark AAAI 2022 Cross-Modal Transferable Adversarial Attacks From Images to Videos CVPR 2022