{"total":213,"rows":[{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619,"area":null},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156,"area":null},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819,"area":null},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781,"area":null},{"id":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412,"area":null},{"id":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267,"area":null},{"id":"2305.14836","title":"NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario","created":"2023-05-24","cited_by_count":262,"area":null},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2308.12213","title":"CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No","created":"2023-08-23","cited_by_count":130,"area":null},{"id":"2103.02221","title":"Energy-Based Learning for Scene Graph Generation","created":"2021-03-03","cited_by_count":104,"area":null},{"id":"2209.07098","title":"Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training","created":"2022-09-15","cited_by_count":104,"area":null},{"id":"2206.09541","title":"DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations","created":"2022-06-20","cited_by_count":102,"area":null},{"id":"2111.10056","title":"Medical Visual Question Answering: A Survey","created":"2021-11-19","cited_by_count":93,"area":null},{"id":"2112.13906","title":"Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?","created":"2021-12-27","cited_by_count":85,"area":null},{"id":"2103.12248","title":"Multi-Modal Answer Validation for Knowledge-Based VQA","created":"2021-03-23","cited_by_count":79,"area":null},{"id":"2111.12933","title":"ML-Decoder: Scalable and Versatile Classification Head","created":"2021-11-25","cited_by_count":79,"area":null},{"id":"2106.06965","title":"Contrastive Attention for Automatic Chest X-ray Report Generation","created":"2021-06-13","cited_by_count":71,"area":null},{"id":"2105.08913","title":"Multiple Meta-model Quantifying for Medical Visual Question Answering","created":"2021-05-19","cited_by_count":54,"area":null},{"id":"2106.03798","title":"DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Reconstruction and Rendering","created":"2021-06-07","cited_by_count":52,"area":null},{"id":"2312.12222","title":"EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering","created":"2023-12-19","cited_by_count":52,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2209.07118","title":"Align, Reason and Learn: Enhancing Medical Vision-and-Language Pre-training with Knowledge","created":"2022-09-15","cited_by_count":51,"area":null},{"id":"2207.01076","title":"Divert More Attention to Vision-Language Tracking","created":"2022-07-03","cited_by_count":47,"area":null},{"id":"2205.08148","title":"Gender and Racial Bias in Visual Question Answering Datasets","created":"2022-05-17","cited_by_count":39,"area":null},{"id":"2208.02194","title":"Interpretable bilinear attention network with domain adaptation improves drug-target prediction","created":"2022-08-03","cited_by_count":39,"area":null},{"id":"2105.08336","title":"Exemplar-Based Open-Set Panoptic Segmentation Network","created":"2021-05-18","cited_by_count":38,"area":null},{"id":"2204.02285","title":"SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering","created":"2022-04-05","cited_by_count":38,"area":null},{"id":"2208.08988","title":"The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs","created":"2022-08-18","cited_by_count":38,"area":null},{"id":"2107.05348","title":"Zero-shot Visual Question Answering using Knowledge Graph","created":"2021-07-12","cited_by_count":37,"area":null},{"id":"2203.09138","title":"MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering","created":"2022-03-17","cited_by_count":36,"area":null},{"id":"2110.14375","title":"Perceptual Score: What Data Modalities Does Your Model Perceive?","created":"2021-10-27","cited_by_count":35,"area":null},{"id":"2107.12651","title":"Greedy Gradient Ensemble for Robust Visual Question Answering","created":"2021-07-27","cited_by_count":34,"area":null},{"id":"2304.01611","title":"Q2ATransformer: Improving Medical VQA via an Answer Querying Decoder","created":"2023-04-04","cited_by_count":31,"area":null},{"id":"2210.04692","title":"Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA","created":"2022-10-10","cited_by_count":30,"area":null},{"id":"2106.04067","title":"LocalTrans: A Multiscale Local Transformer Network for Cross-Resolution Homography Estimation","created":"2021-06-08","cited_by_count":28,"area":null},{"id":"2207.12622","title":"Multi-Attention Network for Compressed Video Referring Object Segmentation","created":"2022-07-26","cited_by_count":28,"area":null},{"id":"2108.09301","title":"Discriminative Region-based Multi-Label Zero-Shot Learning","created":"2021-08-20","cited_by_count":27,"area":null},{"id":"2106.10446","title":"Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering","created":"2021-06-19","cited_by_count":26,"area":null},{"id":"2110.02526","title":"Coarse-to-Fine Reasoning for Visual Question Answering","created":"2021-10-06","cited_by_count":25,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2101.06013","title":"Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge","created":"2021-01-15","cited_by_count":24,"area":null},{"id":"2105.05926","title":"Semantic Diversity Learning for Zero-Shot Multi-label Classification","created":"2021-05-12","cited_by_count":24,"area":null},{"id":"2107.09106","title":"Separating Skills and Concepts for Novel Visual Question Answering","created":"2021-07-19","cited_by_count":24,"area":null},{"id":"2111.04566","title":"RF-Net: a Unified Meta-learning Framework for RF-enabled One-shot Human Activity Recognition","created":"2021-10-29","cited_by_count":24,"area":null},{"id":"2211.15516","title":"DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding","created":"2022-11-28","cited_by_count":24,"area":null},{"id":"2307.11471","title":"Robust Visual Question Answering: Datasets, Methods, and Future Challenges","created":"2023-07-21","cited_by_count":23,"area":null},{"id":"2110.01013","title":"Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering","created":"2021-10-03","cited_by_count":22,"area":null},{"id":"2205.11501","title":"VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering","created":"2022-05-23","cited_by_count":22,"area":null},{"id":"2308.01890","title":"DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotations","created":"2023-08-03","cited_by_count":22,"area":null},{"id":"2104.07916","title":"Augmenting Deep Classifiers with Polynomial Neural Networks","created":"2021-04-16","cited_by_count":21,"area":null},{"id":"2203.03483","title":"Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention","created":"2022-03-07","cited_by_count":21,"area":null},{"id":"2204.07780","title":"Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks","created":"2022-04-16","cited_by_count":21,"area":null},{"id":"2301.09460","title":"HRVQA: A Visual Question Answering Benchmark for High-Resolution Aerial Images","created":"2023-01-23","cited_by_count":21,"area":null},{"id":"2303.01903","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","created":"2023-03-03","cited_by_count":21,"area":null},{"id":"2305.11033","title":"Visual Question Answering: A Survey on Techniques and Common Trends in Recent Literature","created":"2023-05-18","cited_by_count":21,"area":null},{"id":"2405.14974","title":"LOVA3: Learning to Visual Question Answering, Asking and Assessment","created":"2024-05-23","cited_by_count":21,"area":null},{"id":"2410.20327","title":"R-LLaVA: Improving Med-VQA Understanding through Visual Region of Interest","created":"2024-10-27","cited_by_count":21,"area":null},{"id":"2112.01194","title":"Video-Text Pre-training with Learned Regions","created":"2021-12-02","cited_by_count":20,"area":null},{"id":"2101.11606","title":"Generative Multi-Label Zero-Shot Learning","created":"2021-01-27","cited_by_count":19,"area":null},{"id":"2204.01208","title":"Attribute Prototype Network for Any-Shot Learning","created":"2022-04-04","cited_by_count":19,"area":null},{"id":"2106.04630","title":"PAM: Understanding Product Images in Cross Product Category Attribute Extraction","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2206.14989","title":"A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA","created":"2022-06-30","cited_by_count":18,"area":null},{"id":"2207.11850","title":"Visual Perturbation-aware Collaborative Learning for Overcoming the Language Prior Problem","created":"2022-07-24","cited_by_count":18,"area":null},{"id":"2207.12888","title":"LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection","created":"2022-07-26","cited_by_count":18,"area":null},{"id":"2208.06551","title":"Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning","created":"2022-08-13","cited_by_count":18,"area":null},{"id":"2105.14300","title":"LPF: A Language-Prior Feedback Objective Function for De-biased Visual Question Answering","created":"2021-05-29","cited_by_count":17,"area":null},{"id":"2110.08797","title":"Towards Language-guided Visual Recognition via Dynamic Convolutions","created":"2021-10-17","cited_by_count":17,"area":null},{"id":"2104.03656","title":"How Transferable are Reasoning Patterns in VQA?","created":"2021-04-08","cited_by_count":16,"area":null},{"id":"2108.10568","title":"Auto-Parsing Network for Image Captioning and Visual Question Answering","created":"2021-08-24","cited_by_count":16,"area":null},{"id":"2109.13116","title":"VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering","created":"2021-09-27","cited_by_count":16,"area":null},{"id":"2310.17914","title":"3D-Aware Visual Question Answering about Parts, Poses and Occlusions","created":"2023-10-27","cited_by_count":16,"area":null},{"id":"2402.12728","title":"Modality-Aware Integration with Large Language Models for Knowledge-based Visual Question Answering","created":"2024-02-20","cited_by_count":16,"area":null},{"id":"2106.04484","title":"Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions","created":"2021-06-08","cited_by_count":15,"area":null},{"id":"2405.07500","title":"PromptLink: Leveraging Large Language Models for Cross-Source Biomedical Concept Linking","created":"2024-05-13","cited_by_count":15,"area":null},{"id":"2110.00519","title":"Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images","created":"2021-10-01","cited_by_count":14,"area":null},{"id":"2209.13171","title":"RepsNet: Combining Vision with Language for Automated Medical Reports","created":"2022-09-27","cited_by_count":14,"area":null},{"id":"2211.15028","title":"Joint Multimodal Entity-Relation Extraction Based on Edge-enhanced Graph Alignment Network and Word-pair Relation Tagging","created":"2022-11-28","cited_by_count":14,"area":null},{"id":"2304.13649","title":"A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2107.06325","title":"Graphhopper: Multi-Hop Scene Graph Reasoning for Visual Question Answering","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2201.05299","title":"A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering","created":"2022-01-14","cited_by_count":13,"area":null},{"id":"2307.07362","title":"A scoping review on multimodal deep learning in biomedical images and texts","created":"2023-07-14","cited_by_count":13,"area":null},{"id":"2109.01934","title":"Weakly Supervised Relative Spatial Reasoning for Visual Question Answering","created":"2021-09-04","cited_by_count":12,"area":null},{"id":"2203.06107","title":"REX: Reasoning-aware and Grounded Explanation","created":"2022-03-11","cited_by_count":12,"area":null},{"id":"2208.00690","title":"Generative Bias for Robust Visual Question Answering","created":"2022-08-01","cited_by_count":12,"area":null},{"id":"2404.13039","title":"LaPA: Latent Prompt Assist Model For Medical Visual Question Answering","created":"2024-04-19","cited_by_count":12,"area":null},{"id":"2109.08890","title":"Towards Joint Intent Detection and Slot Filling via Higher-order Attention","created":"2021-09-18","cited_by_count":11,"area":null},{"id":"2203.07613","title":"CARETS: A Consistency And Robustness Evaluative Test Suite for VQA","created":"2022-03-15","cited_by_count":11,"area":null},{"id":"2304.14204","title":"Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining","created":"2023-04-26","cited_by_count":11,"area":null},{"id":"2305.15913","title":"MEMEX: Detecting Explanatory Evidence for Memes via Knowledge-Enriched Contextualization","created":"2023-05-25","cited_by_count":11,"area":null},{"id":"2307.10046","title":"Divert More Attention to Vision-Language Object Tracking","created":"2023-07-19","cited_by_count":11,"area":null},{"id":"2411.12195","title":"A Survey of Medical Vision-and-Language Applications and Their Techniques","created":"2024-11-19","cited_by_count":11,"area":null},{"id":"2107.11576","title":"X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering","created":"2021-07-24","cited_by_count":10,"area":null},{"id":"2108.08217","title":"X-modaler: A Versatile and High-performance Codebase for Cross-modal Analytics","created":"2021-08-18","cited_by_count":10,"area":null},{"id":"2110.11298","title":"Video and Text Matching with Conditioned Embeddings","created":"2021-10-21","cited_by_count":10,"area":null},{"id":"2207.07913","title":"Dual-branch Hybrid Learning Network for Unbiased Scene Graph Generation","created":"2022-07-16","cited_by_count":10,"area":null},{"id":"2208.04060","title":"GRIT-VLP: Grouped Mini-batch Sampling for Efficient Vision and Language Pre-training","created":"2022-08-08","cited_by_count":10,"area":null},{"id":"2305.00581","title":"Multimodal Graph Transformer for Multimodal Question Answering","created":"2023-04-30","cited_by_count":10,"area":null},{"id":"2210.04563","title":"Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning","created":"2022-10-10","cited_by_count":9,"area":null},{"id":"2305.06407","title":"Combo of Thinking and Observing for Outside-Knowledge VQA","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2410.02182","title":"BadCM: Invisible Backdoor Attack Against Cross-Modal Learning","created":"2024-10-03","cited_by_count":9,"area":null}],"next_cursor":"100"}