{"total":49,"rows":[{"id":"2102.12219","title":"Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges","created":"2021-02-24","cited_by_count":204,"area":null},{"id":"2101.07396","title":"ArtEmis: Affective Language for Visual Art","created":"2021-01-19","cited_by_count":104,"area":null},{"id":"2107.07919","title":"A Survey on Bias in Visual Datasets","created":"2021-07-16","cited_by_count":84,"area":null},{"id":"2307.07961","title":"EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes","created":"2023-07-16","cited_by_count":82,"area":null},{"id":"2106.16125","title":"Affective Image Content Analysis: Two Decades Review and New Perspectives","created":"2021-06-30","cited_by_count":47,"area":null},{"id":"2302.09466","title":"RePrompt: Automatic Prompt Editing to Refine AI-Generative Art Towards Precise Expressions","created":"2023-02-19","cited_by_count":43,"area":null},{"id":"2404.16670","title":"EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning","created":"2024-04-25","cited_by_count":43,"area":null},{"id":"2312.04293","title":"GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognition","created":"2023-12-07","cited_by_count":38,"area":null},{"id":"2203.13443","title":"MDAN: Multi-level Dependent Attention Network for Visual Emotion Analysis","created":"2022-03-25","cited_by_count":29,"area":null},{"id":"2109.01812","title":"Stimuli-Aware Visual Emotion Analysis","created":"2021-09-04","cited_by_count":26,"area":null},{"id":"2210.01946","title":"Affection: Learning Affective Explanations for Real-World Visual Data","created":"2022-10-04","cited_by_count":19,"area":null},{"id":"2110.12334","title":"SOLVER: Scene-Object Interrelated Visual Emotion Reasoning Network","created":"2021-10-24","cited_by_count":18,"area":null},{"id":"2507.23372","title":"UniEmo: Unifying Emotional Understanding and Generation with Learnable Expert Queries","created":"2025-07-31","cited_by_count":18,"area":null},{"id":"2307.13463","title":"Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion","created":"2023-07-25","cited_by_count":12,"area":null},{"id":"2505.18699","title":"Affective Image Editing: Shaping Emotional Factors via Text Descriptions","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2107.12096","title":"Towards Unbiased Visual Emotion Recognition via Causal Intervention","created":"2021-07-26","cited_by_count":11,"area":null},{"id":"2102.08092","title":"An AutoML-based Approach to Multimodal Image Sentiment Analysis","created":"2021-02-16","cited_by_count":9,"area":null},{"id":"2511.12554","title":"EmoVerse: A MLLMs-Driven Emotion Representation Dataset for Interpretable Visual Emotion Analysis","created":"2025-11-16","cited_by_count":7,"area":null},{"id":"2103.10798","title":"Computational Emotion Analysis From Images: Recent Advances and Future Directions","created":"2021-03-19","cited_by_count":6,"area":null},{"id":"2106.08829","title":"A Fair and Comprehensive Comparison of Multimodal Tweet Sentiment Analysis Methods","created":"2021-06-16","cited_by_count":4,"area":null},{"id":"2308.16349","title":"Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations","created":"2023-08-30","cited_by_count":4,"area":null},{"id":"2503.21254","title":"Vision-to-Music Generation: A Survey","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2512.15528","title":"EmoCaliber: Advancing Reliable Visual Emotion Comprehension via Confidence Verbalization and Calibration","created":"2025-12-17","cited_by_count":4,"area":null},{"id":"2601.12326","title":"EmoKGEdit: Training-free Affective Injection via Visual Cue Transformation","created":"2026-01-18","cited_by_count":4,"area":null},{"id":"2602.01173","title":"EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment","created":"2026-02-01","cited_by_count":4,"area":null},{"id":"2201.11197","title":"Challenges and Opportunities for Machine Learning Classification of Behavior and Mental State from Images","created":"2022-01-26","cited_by_count":3,"area":null},{"id":"2206.13969","title":"MACSA: A Multimodal Aspect-Category Sentiment Analysis Dataset with Multimodal Fine-grained Aligned Annotations","created":"2022-06-28","cited_by_count":3,"area":null},{"id":"2310.10543","title":"ViPE: Visualise Pretty-much Everything","created":"2023-10-16","cited_by_count":3,"area":null},{"id":"2409.18877","title":"UniEmoX: Cross-modal Semantic-Guided Large-Scale Pretraining for Universal Scene Emotion Perception","created":"2024-09-27","cited_by_count":3,"area":null},{"id":"2501.15519","title":"Fuzzy-aware Loss for Source-free Domain Adaptation in Visual Emotion Recognition","created":"2025-01-26","cited_by_count":3,"area":null},{"id":"2208.11450","title":"VISTANet: VIsual Spoken Textual Additive Net for Interpretable Multimodal Emotion Recognition","created":"2022-08-24","cited_by_count":2,"area":null},{"id":"2208.11868","title":"Interpretable Multimodal Emotion Recognition using Hybrid Fusion of Speech and Image Data","created":"2022-08-25","cited_by_count":2,"area":null},{"id":"2304.14942","title":"The Emotions of the Crowd: Learning Image Sentiment from Tweets via Cross-modal Distillation","created":"2023-04-28","cited_by_count":2,"area":null},{"id":"2405.12150","title":"Bangladeshi Native Vehicle Detection in Wild","created":"2024-05-20","cited_by_count":2,"area":null},{"id":"2511.17103","title":"Bridging Visual Affective Gap: Borrowing Textual Knowledge by Learning from Noisy Image-Text Pairs","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2505.14660","title":"EmoGist: Efficient In-Context Learning for Visual Emotion Understanding","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2607.21061","title":"MVEI & EmObserver: Empowering MLLM-Oriented Visual Emotional Intelligence via Emotion Statement Judgement","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2609.02616","title":"AffectDelta: Beyond Emotion Labels for Image Editing","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2105.07135","title":"Analyzing Images for Music Recommendation","created":"2021-05-15","cited_by_count":0,"area":null},{"id":"2109.07509","title":"Learning to Aggregate and Refine Noisy Labels for Visual Sentiment Analysis","created":"2021-09-15","cited_by_count":0,"area":null},{"id":"2112.02953","title":"The artificial synesthete: Image-melody translations with variational autoencoders","created":"2021-12-06","cited_by_count":0,"area":null},{"id":"2409.10297","title":"On Synthetic Texture Datasets: Challenges, Creation, and Curation","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2412.05558","title":"WavFusion: Towards wav2vec 2.0 Multimodal Speech Emotion Recognition","created":"2024-12-07","cited_by_count":0,"area":null},{"id":"2502.15322","title":"SentiFormer: Metadata Enhanced Transformer for Image Sentiment Analysis","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2509.22378","title":"Zero-Effort Image-to-Music Generation: An Interpretable RAG-based VLM Approach","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2511.23115","title":"Analyzing Image Beyond Visual Aspect: Image Emotion Classification via Multiple-Affective Captioning","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2512.14665","title":"Enhancing Visual Sentiment Analysis via Semiotic Isotopy-Guided Dataset Construction","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2604.12568","title":"Evolution-Inspired Sample Competition for Deep Neural Network Optimization","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2606.02171","title":"InsightVQA: High-Dimensional Emotion-Cognitive Visual Question Answering Benchmark","created":"2026-06-01","cited_by_count":0,"area":null}],"next_cursor":null}