Applications

Explore Inter-contrast between Videos via Composition for Weakly Supervised Temporal Sentence Grounding AAAI 2022 FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework ACL 2022 Flexible Visual Grounding ACL 2022 Grounding Answers for Visual Questions Asked by Visually Impaired People CVPR 2022 How Much Can CLIP Benefit Vision-and-Language Tasks? ICLR 2022 Learning the Dynamics of Visual Relational Reasoning via Reinforced Path Routing AAAI 2022 Maintaining Reasoning Consistency in Compositional Visual Question Answering CVPR 2022 Measuring CLEVRness: Black-box Testing of Visual Reasoning Models ICLR 2022 Measuring Compositional Consistency for Video Question Answering CVPR 2022 Multi-Modal Answer Validation for Knowledge-Based VQA AAAI 2022 Multi-VQG: Generating Engaging Questions for Multiple Images EMNLP 2022 MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding AAAI 2022 Mutual Information Divergence: A Unified Metric for Multimodal Generative Models NeurIPS 2022 Overview of the MedVidQA 2022 Shared Task on Medical Video Question-Answering ACL 2022 Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training EMNLP 2022 Query and Attention Augmentation for Knowledge-Based Explainable Reasoning CVPR 2022 ScanQA: 3D Question Answering for Spatial Scene Understanding CVPR 2022 SimVQA: Exploring Simulated Environments for Visual Question Answering CVPR 2022 SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering CVPR 2022 Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning EMNLP 2022 Towards Video Text Visual Question Answering: Benchmark and Baseline NeurIPS 2022 Transform-Retrieve-Generate: Natural Language-Centric Outside-Knowledge Visual Question Answering CVPR 2022 WebQA: Multihop and Multimodal QA CVPR 2022 xGQA: Cross-Lingual Visual Question Answering ACL 2022 Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions ACL 2021