{"total":68,"rows":[{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710,"area":null},{"id":"2112.11561","title":"Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions","created":"2021-12-21","cited_by_count":73,"area":"driving"},{"id":"2305.14724","title":"I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors","created":"2023-05-24","cited_by_count":31,"area":"diffusion"},{"id":"2212.09898","title":"MetaCLUE: Towards Comprehensive Visual Metaphors Research","created":"2022-12-19","cited_by_count":28,"area":null},{"id":"2410.11538","title":"MCTBench: Multimodal Cognition towards Text-Rich Visual Scenes Benchmark","created":"2024-10-15","cited_by_count":26,"area":"mllm"},{"id":"2110.01890","title":"De-rendering Stylized Texts","created":"2021-10-05","cited_by_count":24,"area":null},{"id":"2502.14801","title":"AVD2: Accident Video Diffusion for Accident Video Description","created":"2025-02-20","cited_by_count":20,"area":null},{"id":"2309.14623","title":"Text-to-Image Generation for Abstract Concepts","created":"2023-09-26","cited_by_count":18,"area":null},{"id":"2103.06541","title":"Affect2MM: Affective Analysis of Multimedia Content Using Emotion Causality","created":"2021-03-11","cited_by_count":17,"area":null},{"id":"2212.09877","title":"LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer","created":"2022-12-19","cited_by_count":15,"area":null},{"id":"2203.15349","title":"LDKP: A Dataset for Identifying Keyphrases from Long Scientific Documents","created":"2022-03-29","cited_by_count":13,"area":null},{"id":"2509.08621","title":"AdsQA: Towards Advertisement Video Understanding","created":"2025-09-10","cited_by_count":13,"area":null},{"id":"2104.07767","title":"Exploring Visual Engagement Signals for Representation Learning","created":"2021-04-15","cited_by_count":12,"area":null},{"id":"2209.06416","title":"ImageArg: A Multi-modal Tweet Dataset for Image Persuasiveness Mining","created":"2022-09-14","cited_by_count":12,"area":null},{"id":"2103.02937","title":"Visual Question Answering: which investigated applications?","created":"2021-03-04","cited_by_count":11,"area":null},{"id":"2105.04047","title":"Analyzing Online Political Advertisements","created":"2021-05-09","cited_by_count":11,"area":null},{"id":"2305.09758","title":"A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot","created":"2023-05-16","cited_by_count":11,"area":null},{"id":"2309.00359","title":"Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior","created":"2023-09-01","cited_by_count":9,"area":null},{"id":"2308.14052","title":"MM-AU:Towards Multimodal Understanding of Advertisement Videos","created":"2023-08-27","cited_by_count":8,"area":null},{"id":"2307.15326","title":"Staging E-Commerce Products for Online Advertising using Retrieval Assisted Image Generation","created":"2023-07-28","cited_by_count":7,"area":null},{"id":"2406.04886","title":"Unveiling the Invisible: Captioning Videos with Metaphors","created":"2024-06-07","cited_by_count":7,"area":null},{"id":"2412.15677","title":"AI-generated Image Quality Assessment in Visual Communication","created":"2024-12-20","cited_by_count":7,"area":null},{"id":"2305.13623","title":"Validating Multimedia Content Moderation Software via Semantic Fusion","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2409.10719","title":"Benchmarking VLMs' Reasoning About Persuasive Atypical Images","created":"2024-09-16","cited_by_count":5,"area":"lr"},{"id":"2412.10426","title":"CAP: Evaluation of Persuasive and Creative Image Generation","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2108.08226","title":"TSI: an Ad Text Strength Indicator using Text-to-CTR and Semantic-Ad-Similarity","created":"2021-08-18","cited_by_count":4,"area":null},{"id":"2209.05723","title":"A Capsule Network for Hierarchical Multi-Label Image Classification","created":"2022-09-13","cited_by_count":4,"area":null},{"id":"2308.10562","title":"Seeing the Intangible: Survey of Image Classification into High-Level and Abstract Categories","created":"2023-08-21","cited_by_count":4,"area":null},{"id":"2310.12172","title":"Overview of ImageArg-2023: The First Shared Task in Multimodal Argument Mining","created":"2023-10-15","cited_by_count":4,"area":null},{"id":"2401.13296","title":"Visual Objectification in Films: Towards a New AI Task for Video Interpretation","created":"2024-01-24","cited_by_count":4,"area":null},{"id":"2506.00481","title":"PVP: An Image Dataset for Personalized Visual Persuasion with Persuasion Strategies, Viewer Characteristics, and Persuasiveness Ratings","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2206.04863","title":"Symbolic image detection using scene and knowledge graphs","created":"2022-06-10","cited_by_count":3,"area":null},{"id":"2506.07811","title":"Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2508.20765","title":"Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2510.26006","title":"CAVE: Detecting and Explaining Commonsense Anomalies in Visual Environments","created":"2025-10-29","cited_by_count":3,"area":null},{"id":"2208.09626","title":"Persuasion Strategies in Advertisements","created":"2022-08-20","cited_by_count":2,"area":null},{"id":"2405.00942","title":"Teaching Human Behavior Improves Content Understanding Abilities Of LLMs","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2405.20846","title":"Don't Buy it! Reassessing the Ad Understanding Abilities of Contrastive Multimodal Models","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2502.10154","title":"Video Soundtrack Generation by Aligning Emotions and Temporal Boundaries","created":"2025-02-14","cited_by_count":2,"area":null},{"id":"2602.07625","title":"AD-MIR: Bridging the Gap from Perception to Persuasion in Advertising Video Understanding via Structured Reasoning","created":"2026-02-07","cited_by_count":2,"area":null},{"id":"2604.20511","title":"CHASM: Unveiling Covert Advertisements on Chinese Social Media","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2402.19339","title":"Stitching Gaps: Fusing Situated Perceptual Knowledge with Vision Transformers for High-Level Image Classification","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2407.03268","title":"For a semiotic AI: Bridging computer vision and visual semiotics for computational observation of large scale facial image archives","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2410.22648","title":"SimpsonsVQA: Enhancing Inquiry-Based Learning with a Tailored Dataset","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2509.15241","title":"M-PACE: Mother Child Framework for Multimodal Compliance","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2510.22768","title":"Seeing is Believing? Evaluating Vision-Language Model Susceptibility in Agent-to-Agent Multimodal Persuasion","created":"2025-10-26","cited_by_count":1,"area":"mllm"},{"id":"2606.24797","title":"EG-VQA: Benchmarking Verifiable Video Question Answering with Grounded Temporal Evidence","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2108.02572","title":"SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysis","created":"2021-08-03","cited_by_count":0,"area":null},{"id":"2108.02725","title":"VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Search","created":"2021-08-05","cited_by_count":0,"area":null},{"id":"2108.09717","title":"EKTVQA: Generalized use of External Knowledge to empower Scene Text in Text-VQA","created":"2021-08-22","cited_by_count":0,"area":null},{"id":"2109.05778","title":"Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generation","created":"2021-09-13","cited_by_count":0,"area":null},{"id":"2202.02830","title":"Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectors","created":"2022-02-06","cited_by_count":0,"area":null},{"id":"2203.11011","title":"Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networks","created":"2022-03-08","cited_by_count":0,"area":null},{"id":"2205.08335","title":"Explanation-Guided Fairness Testing through Genetic Algorithm","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2207.14648","title":"Using Graph Neural Networks for Program Termination","created":"2022-07-28","cited_by_count":0,"area":null},{"id":"2303.09664","title":"Tribe or Not? Critical Inspection of Group Differences Using TribalGram","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2305.02360","title":"Fashionpedia-Ads: Do Your Favorite Advertisements Reveal Your Fashion Taste?","created":"2023-05-03","cited_by_count":0,"area":null},{"id":"2503.00046","title":"Leveraging Large Models to Evaluate Novel Content: A Case Study on Advertisement Creativity","created":"2025-02-26","cited_by_count":0,"area":null},{"id":"2504.18785","title":"ALF: Advertiser Large Foundation Model for Multi-Modal Advertiser Understanding","created":"2025-04-26","cited_by_count":0,"area":null},{"id":"2505.00975","title":"Generating Animated Layouts as Structured Text Representations","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2507.17050","title":"Toward Scalable Video Narration: A Training-free Approach Using Multimodal Large Language Models","created":"2025-07-22","cited_by_count":0,"area":"mllm"},{"id":"2510.15240","title":"The Face of Persuasion: Analyzing Bias and Generating Culture-Aware Ads","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2511.01550","title":"Analyzing Sustainability Messaging in Large-Scale Corporate Social Media","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2603.02137","title":"NextAds: Towards Next-generation Personalized Video Advertising","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2606.16198","title":"GRACE: Boosting Video MLLMs with Grounded Action-Centric Evidence for Viewer Sentiment Prediction","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.25314","title":"Sense it with your eyes: Sensation Generation and Understanding for Advertisements","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2610.01383","title":"PRISM: A Category-Theoretic Framework for Measuring and Refining Multimodal Analogies","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.03099","title":"Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}