{"total":85,"rows":[{"id":"2102.10407","title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","created":"2021-02-20","cited_by_count":191,"area":null},{"id":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138,"area":null},{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82,"area":null},{"id":"2303.12112","title":"Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation","created":"2023-03-21","cited_by_count":78,"area":null},{"id":"2309.06597","title":"Rank2Tell: A Multimodal Driving Dataset for Joint Importance Ranking and Reasoning","created":"2023-09-12","cited_by_count":63,"area":null},{"id":"2203.15205","title":"SPAct: Self-supervised Privacy Preservation for Action Recognition","created":"2022-03-29","cited_by_count":47,"area":null},{"id":"2106.01625","title":"Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech","created":"2021-06-03","cited_by_count":42,"area":null},{"id":"2103.12204","title":"Human-like Controllable Image Captioning with Verb-specific Semantic Roles","created":"2021-03-22","cited_by_count":41,"area":null},{"id":"2206.04055","title":"Gradient Obfuscation Gives a False Sense of Security in Federated Learning","created":"2022-06-08","cited_by_count":39,"area":null},{"id":"2301.13838","title":"Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression","created":"2023-01-31","cited_by_count":39,"area":null},{"id":"2206.07173","title":"Measuring Representational Harms in Image Captioning","created":"2022-06-14","cited_by_count":36,"area":null},{"id":"2103.05271","title":"Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation","created":"2021-03-09","cited_by_count":35,"area":null},{"id":"2310.04900","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","created":"2023-10-07","cited_by_count":34,"area":null},{"id":"2302.10909","title":"Multi-modal Machine Learning in Engineering Design: A Review and Future Directions","created":"2023-02-14","cited_by_count":27,"area":null},{"id":"2211.15103","title":"VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning","created":"2022-11-28","cited_by_count":25,"area":null},{"id":"2305.12140","title":"Movie101: A New Movie Understanding Benchmark","created":"2023-05-20","cited_by_count":25,"area":null},{"id":"2308.11072","title":"TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detection","created":"2023-08-21","cited_by_count":23,"area":null},{"id":"2105.14477","title":"Towards Diverse Paragraph Captioning for Untrimmed Videos","created":"2021-05-30","cited_by_count":22,"area":null},{"id":"2302.01328","title":"IC3: Image Captioning by Committee Consensus","created":"2023-02-02","cited_by_count":20,"area":null},{"id":"2206.12972","title":"VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning","created":"2022-06-26","cited_by_count":19,"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":"2206.03891","title":"PrivHAR: Recognizing Human Actions From Privacy-preserving Lens","created":"2022-06-08","cited_by_count":16,"area":null},{"id":"2208.02459","title":"Privacy-Preserving Action Recognition via Motion Difference Quantization","created":"2022-08-04","cited_by_count":14,"area":null},{"id":"2209.08231","title":"Learning Distinct and Representative Styles for Image Captioning","created":"2022-09-17","cited_by_count":12,"area":null},{"id":"2204.12974","title":"CapOnImage: Context-driven Dense-Captioning on Image","created":"2022-04-27","cited_by_count":11,"area":null},{"id":"2305.07021","title":"Simple Token-Level Confidence Improves Caption Correctness","created":"2023-05-11","cited_by_count":11,"area":null},{"id":"2111.13244","title":"Going Grayscale: The Road to Understanding and Improving Unlearnable Examples","created":"2021-11-25","cited_by_count":10,"area":null},{"id":"2209.10474","title":"Show, Interpret and Tell: Entity-aware Contextualised Image Captioning in Wikipedia","created":"2022-09-21","cited_by_count":10,"area":null},{"id":"2207.11118","title":"Rethinking the Reference-based Distinctive Image Captioning","created":"2022-07-22","cited_by_count":8,"area":null},{"id":"2108.03662","title":"Discriminative Latent Semantic Graph for Video Captioning","created":"2021-08-08","cited_by_count":7,"area":null},{"id":"2204.03938","title":"On Distinctive Image Captioning via Comparing and Reweighting","created":"2022-04-08","cited_by_count":7,"area":null},{"id":"2208.04254","title":"Distinctive Image Captioning via CLIP Guided Group Optimization","created":"2022-08-08","cited_by_count":6,"area":null},{"id":"2303.10435","title":"Modeling the Trade-off of Privacy Preservation and Activity Recognition on Low-Resolution Images","created":"2023-03-18","cited_by_count":6,"area":null},{"id":"2210.09904","title":"MaSS: Multi-attribute Selective Suppression","created":"2022-10-18","cited_by_count":5,"area":null},{"id":"2211.09371","title":"CapEnrich: Enriching Caption Semantics for Web Images via Cross-modal Pre-trained Knowledge","created":"2022-11-17","cited_by_count":5,"area":null},{"id":"2212.06206","title":"Contextual Explainable Video Representation: Human Perception-based Understanding","created":"2022-12-12","cited_by_count":5,"area":null},{"id":"2407.18243","title":"BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairments","created":"2024-07-25","cited_by_count":5,"area":null},{"id":"2507.13981","title":"Evaluation of Human Visual Privacy Protection: A Three-Dimensional Framework and Benchmark Dataset","created":"2025-07-18","cited_by_count":5,"area":null},{"id":"2203.09121","title":"DRAG: Dynamic Region-Aware GCN for Privacy-Leaking Image Detection","created":"2022-03-17","cited_by_count":4,"area":null},{"id":"2210.11169","title":"Content-based Graph Privacy Advisor","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2306.14259","title":"Improving Reference-based Distinctive Image Captioning with Contrastive Rewards","created":"2023-06-25","cited_by_count":4,"area":null},{"id":"2409.18674","title":"Image-guided topic modeling for interpretable privacy classification","created":"2024-09-27","cited_by_count":4,"area":null},{"id":"2411.15413","title":"FG-CXR: A Radiologist-Aligned Gaze Dataset for Enhancing Interpretability in Chest X-Ray Report Generation","created":"2024-11-23","cited_by_count":4,"area":null},{"id":"2506.12258","title":"EgoPrivacy: What Your First-Person Camera Says About You?","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2509.23525","title":"Privy: Envisioning and Mitigating Privacy Risks for Consumer-facing AI Product Concepts","created":"2025-09-27","cited_by_count":4,"area":null},{"id":"2212.02033","title":"Towards Generating Diverse Audio Captions via Adversarial Training","created":"2022-12-05","cited_by_count":3,"area":null},{"id":"2405.01646","title":"Explaining models relating objects and privacy","created":"2024-05-02","cited_by_count":3,"area":null},{"id":"2503.02132","title":"Video-DPRP: A Differentially Private Approach for Visual Privacy-Preserving Video Human Activity Recognition","created":"2025-03-03","cited_by_count":3,"area":null},{"id":"2503.10997","title":"RONA: Pragmatically Diverse Image Captioning with Coherence Relations","created":"2025-03-14","cited_by_count":3,"area":null},{"id":"2209.08163","title":"Belief Revision based Caption Re-ranker with Visual Semantic Information","created":"2022-09-16","cited_by_count":2,"area":null},{"id":"2301.02079","title":"PEAK: Explainable Privacy Assistant through Automated Knowledge Extraction","created":"2023-01-05","cited_by_count":2,"area":null},{"id":"2301.08784","title":"Visual Semantic Relatedness Dataset for Image Captioning","created":"2023-01-20","cited_by_count":2,"area":null},{"id":"2304.05135","title":"RecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy Defense","created":"2023-04-11","cited_by_count":2,"area":null},{"id":"2310.15848","title":"On Responsible Machine Learning Datasets with Fairness, Privacy, and Regulatory Norms","created":"2023-10-24","cited_by_count":2,"area":null},{"id":"2401.12419","title":"Multi-modal News Understanding with Professionally Labelled Videos (ReutersViLNews)","created":"2024-01-23","cited_by_count":2,"area":null},{"id":"2404.10054","title":"AIGeN: An Adversarial Approach for Instruction Generation in VLN","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2503.12464","title":"Learning Privacy from Visual Entities","created":"2025-03-16","cited_by_count":2,"area":null},{"id":"2603.21573","title":"Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2110.09756","title":"A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images Generation","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2311.04480","title":"CLearViD: Curriculum Learning for Video Description","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2404.02696","title":"Deep Privacy Funnel Model: From a Discriminative to a Generative Approach with an Application to Face Recognition","created":"2024-04-03","cited_by_count":1,"area":null},{"id":"2412.00696","title":"Intermediate Outputs Are More Sensitive Than You Think","created":"2024-12-01","cited_by_count":1,"area":null},{"id":"2511.00252","title":"Merlin L48 Spectrogram Dataset","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2511.08666","title":"Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2512.07166","title":"When Privacy Meets Recovery: The Overlooked Half of Surrogate-Driven Privacy Preservation for MLLM Editing","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2512.12586","title":"StegaVAR: Privacy-Preserving Video Action Recognition via Steganographic Domain Analysis","created":"2025-12-14","cited_by_count":1,"area":null},{"id":"2603.27817","title":"Towards Context-Aware Image Anonymization with Multi-Agent Reasoning","created":"2026-03-29","cited_by_count":1,"area":null},{"id":"2603.28605","title":"Unsafe2Safe: Controllable Image Anonymization for Downstream Utility","created":"2026-03-30","cited_by_count":1,"area":null},{"id":"2606.12666","title":"CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2106.15312","title":"Contrastive Semantic Similarity Learning for Image Captioning Evaluation with Intrinsic Auto-encoder","created":"2021-06-29","cited_by_count":0,"area":null},{"id":"2110.01676","title":"Deep Learning Approach Protecting Privacy in Camera-Based Critical Applications","created":"2021-10-04","cited_by_count":0,"area":null},{"id":"2205.14458","title":"Variational Transformer: A Framework Beyond the Trade-off between Accuracy and Diversity for Image Captioning","created":"2022-05-28","cited_by_count":0,"area":null},{"id":"2205.14751","title":"A Generative Adversarial Network-based Selective Ensemble Characteristic-to-Expression Synthesis (SE-CTES) Approach and Its Applications in Healthcare","created":"2022-05-29","cited_by_count":0,"area":null},{"id":"2402.14241","title":"A Self-supervised Pressure Map human keypoint Detection Approch: Optimizing Generalization and Computational Efficiency Across Datasets","created":"2024-02-22","cited_by_count":0,"area":null},{"id":"2410.09377","title":"GEM-VPC: A dual Graph-Enhanced Multimodal integration for Video Paragraph Captioning","created":"2024-10-12","cited_by_count":0,"area":null},{"id":"2410.18717","title":"Low-Latency Video Anonymization for Crowd Anomaly Detection: Privacy Versus Performance","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2502.18734","title":"Beyond RNNs: Benchmarking Attention-Based Image Captioning Models","created":"2025-02-26","cited_by_count":0,"area":null},{"id":"2509.00661","title":"Automatic Identification and Description of Jewelry Through Computer Vision and Neural Networks for Translators and Interpreters","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2510.07976","title":"The impact of abstract and object tags on image privacy classification","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2510.19418","title":"From See to Shield: ML-Assisted Fine-Grained Access Control for Visual Data","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2512.09309","title":"A Distributed Framework for Privacy-Enhanced Vision Transformers on the Edge","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2512.18864","title":"Cross-modal Counterfactual Explanations: Uncovering Decision Factors and Dataset Biases in Subjective Classification","created":"2025-12-21","cited_by_count":0,"area":null},{"id":"2601.09449","title":"PrivLEX: Detecting legal concepts in images through Vision-Language Models","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2607.25926","title":"Face De-Identification: A Domain-Centric Survey from Capture to Processing","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.29489","title":"SpatialTrust: A Benchmark for Environmental Risk Recognition in Secure Authentication","created":"2026-08-30","cited_by_count":0,"area":null}],"next_cursor":null}