Unshuffling Data for Improved Generalization in Visual Question Answering Jan 1, 2021 Out-of-Distribution Generalization Question Answering
— Unverified Linguistically Routing Capsule Network for Out-of-Distribution Visual Question Answering Jan 1, 2021 Novel Concepts Question Answering
— Unverified Erasure for Advancing: Dynamic Self-Supervised Learning for Commonsense Reasoning Jan 1, 2021 Question Answering Self-Supervised Learning
— Unverified Differentiable End-to-End Program Executor for Sample and Computationally Efficient VQA Jan 1, 2021 Question Answering Visual Question Answering
— Unverified Seeing is Knowing! Fact-based Visual Question Answering using Knowledge Graph Embeddings Dec 31, 2020 Common Sense Reasoning Knowledge Graph Embeddings
— Unverified Detecting Hate Speech in Multi-modal Memes Dec 29, 2020 Binary Classification Hate Speech Detection
Code Code Available LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding Dec 29, 2020 Document Image Classification Document Layout Analysis
Code Code Available Learning content and context with language bias for Visual Question Answering Dec 21, 2020 Question Answering Visual Question Answering
Code Code Available Object-Centric Diagnosis of Visual Reasoning Dec 21, 2020 Diagnostic Object
— Unverified KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA Dec 20, 2020 Visual Question Answering (VQA)
— Unverified Trying Bilinear Pooling in Video-QA Dec 18, 2020 Question Answering Video Question Answering
— Unverified On Modality Bias in the TVQA Dataset Dec 18, 2020 Question Answering Video Question Answering
Code Code Available Overcoming Language Priors with Self-supervised Learning for Visual Question Answering Dec 17, 2020 Question Answering Self-Supervised Learning
Code Code Available Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding Dec 14, 2020 Question Answering Visual Question Answering
Code Code Available KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual Commonsense Reasoning Dec 13, 2020 Sentence Visual Commonsense Reasoning
— Unverified Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps Dec 9, 2020 Decoder Image Captioning
— Unverified Study on the Assessment of the Quality of Experience of Streaming Video Dec 8, 2020 regression Video Quality Assessment
Code Code Available TAP: Text-Aware Pre-training for Text-VQA and Text-Caption Dec 8, 2020 Caption Generation Language Modeling
Code Code Available CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractions Dec 8, 2020 counterfactual Descriptive
Code Code Available FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding Dec 5, 2020 image-classification Image Classification
Code Code Available WeaQA: Weak Supervision via Captions for Visual Question Answering Dec 4, 2020 Question Answering Visual Question Answering
— Unverified Understanding Guided Image Captioning Performance across Domains Dec 4, 2020 Descriptive Image Captioning
Code Code Available Towards Knowledge-Augmented Visual Question Answering Dec 1, 2020 General Knowledge Graph Attention
Code Code Available A Unified Framework for Multilingual and Code-Mixed Visual Question Answering Dec 1, 2020 Question Answering Visual Question Answering
— Unverified Open-Ended Multi-Modal Relational Reasoning for Video Question Answering Dec 1, 2020 Question Answering Relational Reasoning
Code Code Available Just Ask: Learning to Answer Questions from Millions of Narrated Videos Dec 1, 2020 Question Answering Question Generation
Code Code Available Multimodal Graph Networks for Compositional Generalization in Visual Question Answering Dec 1, 2020 Graph Neural Network Question Answering
— Unverified Patch-VQ: 'Patching Up' the Video Quality Problem Nov 27, 2020 Video Quality Assessment Visual Question Answering (VQA)
Code Code Available Point and Ask: Incorporating Pointing into Visual Question Answering Nov 27, 2020 Question Answering Visual Question Answering
Code Code Available Learning from Lexical Perturbations for Consistent Visual Question Answering Nov 26, 2020 Question Answering Visual Question Answering
Code Code Available Transformation Driven Visual Reasoning Nov 26, 2020 Attribute Triplet
Code Code Available Siamese Tracking with Lingual Object Constraints Nov 23, 2020 Object Object Tracking
Code Code Available Large Scale Multimodal Classification Using an Ensemble of Transformer Models and Co-Attention Nov 23, 2020 Classification General Classification
Code Code Available Interpretable Visual Reasoning via Induced Symbolic Space Nov 23, 2020 Visual Question Answering (VQA) Visual Reasoning
Code Code Available Modular Graph Attention Network for Complex Visual Relational Reasoning Nov 22, 2020 Graph Attention Question Answering
— Unverified LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering Nov 21, 2020 Answer Generation Question Answering
Code Code Available Logically Consistent Loss for Visual Question Answering Nov 19, 2020 Multi-Task Learning Question Answering
— Unverified Generating Natural Questions from Images for Multimodal Assistants Nov 17, 2020 Common Sense Reasoning Natural Questions
— Unverified CapWAP: Captioning with a Purpose Nov 9, 2020 Image Captioning Question Answering
— Unverified Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles Nov 7, 2020 Natural Language Inference Question Answering
Code Code Available Disentangling 3D Prototypical Networks For Few-Shot Concept Learning Nov 6, 2020 3D geometry 3D Object Detection
Code Code Available An Improved Attention for Visual Question Answering Nov 4, 2020 Decoder Question Answering
Code Code Available Reasoning Over History: Context Aware Visual Dialog Nov 2, 2020 coreference-resolution Coreference Resolution
— Unverified Can Pre-training help VQA with Lexical Variations? Nov 1, 2020 Question Answering Visual Question Answering
— Unverified Representation, Learning and Reasoning on Spatial Language for Downstream NLP Tasks Nov 1, 2020 Common Sense Reasoning Question Answering
— Unverified ConceptBert: Concept-Aware Representation for Visual Question Answering Nov 1, 2020 Common Sense Reasoning Question Answering
Code Code Available ISAAQ - Mastering Textbook Questions with Pre-trained Transformers and Bottom-Up and Top-Down Attention Nov 1, 2020 Multiple-choice Question Answering
— Unverified CapWAP: Image Captioning with a Purpose Nov 1, 2020 Image Captioning Question Answering
— Unverified Learning to Contrast the Counterfactual Samples for Robust Visual Question Answering Nov 1, 2020 Contrastive Learning counterfactual
Code Code Available STL-CQA: Structure-based Transformers with Localization and Encoding for Chart Question Answering Nov 1, 2020 Chart Question Answering Question Answering
— Unverified 