{"total":39,"rows":[{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191,"area":null},{"id":"2102.04990","title":"In Defense of Scene Graphs for Image Captioning","created":"2021-02-09","cited_by_count":31,"area":null},{"id":"2103.15059","title":"A Benchmark and Comprehensive Survey on Knowledge Graph Entity Alignment via Representation Learning","created":"2021-03-28","cited_by_count":31,"area":null},{"id":"2109.05743","title":"Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation","created":"2021-09-13","cited_by_count":30,"area":null},{"id":"2106.04128","title":"Conversational Fashion Image Retrieval via Multiturn Natural Language Feedback","created":"2021-06-08","cited_by_count":29,"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":"2307.11471","title":"Robust Visual Question Answering: Datasets, Methods, and Future Challenges","created":"2023-07-21","cited_by_count":23,"area":null},{"id":"2207.08386","title":"Entity-enhanced Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding","created":"2022-07-18","cited_by_count":22,"area":null},{"id":"2106.04053","title":"Discriminative Triad Matching and Reconstruction for Weakly Referring Expression Grounding","created":"2021-06-08","cited_by_count":21,"area":null},{"id":"2107.05080","title":"Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration","created":"2021-07-11","cited_by_count":21,"area":null},{"id":"2212.00715","title":"What do you MEME? Generating Explanations for Visual Semantic Role Labelling in Memes","created":"2022-12-01","cited_by_count":18,"area":null},{"id":"2210.08908","title":"Cross-modal Semantic Enhanced Interaction for Image-Sentence Retrieval","created":"2022-10-17","cited_by_count":14,"area":null},{"id":"2307.13368","title":"Kefa: A Knowledge Enhanced and Fine-grained Aligned Speaker for Navigation Instruction Generation","created":"2023-07-25","cited_by_count":12,"area":null},{"id":"2405.11215","title":"MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing","created":"2024-05-18","cited_by_count":12,"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":"2402.02503","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","created":"2024-02-04","cited_by_count":9,"area":null},{"id":"2404.18397","title":"ViOCRVQA: Novel Benchmark Dataset and Vision Reader for Visual Question Answering by Understanding Vietnamese Text in Images","created":"2024-04-29","cited_by_count":8,"area":null},{"id":"2411.11150","title":"A Comprehensive Survey on Visual Question Answering Datasets and Algorithms","created":"2024-11-17","cited_by_count":8,"area":null},{"id":"2307.11772","title":"AutoAlign: Fully Automatic and Effective Knowledge Graph Alignment enabled by Large Language Models","created":"2023-07-18","cited_by_count":7,"area":null},{"id":"2202.05451","title":"ACORT: A Compact Object Relation Transformer for Parameter Efficient Image Captioning","created":"2022-02-11","cited_by_count":6,"area":null},{"id":"2301.02736","title":"Using External Off-Policy Speech-To-Text Mappings in Contextual End-To-End Automated Speech Recognition","created":"2023-01-06","cited_by_count":5,"area":null},{"id":"2408.04879","title":"On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey","created":"2024-08-09","cited_by_count":5,"area":null},{"id":"2107.03216","title":"MuVAM: A Multi-View Attention-based Model for Medical Visual Question Answering","created":"2021-07-07","cited_by_count":4,"area":null},{"id":"2109.06148","title":"DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection","created":"2021-09-13","cited_by_count":4,"area":null},{"id":"2311.16782","title":"The curse of language biases in remote sensing VQA: the role of spatial attributes, language diversity, and the need for clear evaluation","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2412.20541","title":"SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes","created":"2024-12-29","cited_by_count":4,"area":null},{"id":"2107.07927","title":"A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets","created":"2021-07-16","cited_by_count":3,"area":null},{"id":"2210.04806","title":"Generating image captions with external encyclopedic knowledge","created":"2022-10-10","cited_by_count":3,"area":null},{"id":"2304.10622","title":"Enhancing object detection robustness: A synthetic and natural perturbation approach","created":"2023-04-20","cited_by_count":3,"area":null},{"id":"2504.16516","title":"Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2211.00901","title":"A survey on the development status and application prospects of knowledge graph in smart grids","created":"2022-11-02","cited_by_count":2,"area":null},{"id":"2211.12054","title":"Visually Grounded Commonsense Knowledge Acquisition","created":"2022-11-22","cited_by_count":1,"area":null},{"id":"2407.05100","title":"Ask Questions with Double Hints: Visual Question Generation with Answer-awareness and Region-reference","created":"2024-07-06","cited_by_count":1,"area":null},{"id":"2111.13233","title":"Look at here : Utilizing supervision to attend subtle key regions","created":"2021-11-25","cited_by_count":0,"area":null},{"id":"2206.07986","title":"Image Captioning based on Feature Refinement and Reflective Decoding","created":"2022-06-16","cited_by_count":0,"area":null},{"id":"2210.08540","title":"TransAlign: Fully Automatic and Effective Entity Alignment for Knowledge Graphs","created":"2022-10-16","cited_by_count":0,"area":null},{"id":"2305.06483","title":"Towards L-System Captioning for Tree Reconstruction","created":"2023-05-10","cited_by_count":0,"area":null},{"id":"2403.08004","title":"Leveraging LLMs for On-the-Fly Instruction Guided Image Editing","created":"2024-03-12","cited_by_count":0,"area":null},{"id":"2406.18579","title":"Hire: Hybrid-modal Interaction with Multiple Relational Enhancements for Image-Text Matching","created":"2024-06-05","cited_by_count":0,"area":null}],"next_cursor":null}