{"total":142,"rows":[{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2204.11817","title":"Translation between Molecules and Natural Language","created":"2022-04-25","cited_by_count":177,"area":null},{"id":"2210.08964","title":"PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting","created":"2022-09-20","cited_by_count":172,"area":null},{"id":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150,"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":"2302.07257","title":"ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Models","created":"2023-02-14","cited_by_count":116,"area":null},{"id":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91,"area":null},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"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":"2101.06462","title":"Dual-Level Collaborative Transformer for Image Captioning","created":"2021-01-16","cited_by_count":71,"area":null},{"id":"2306.11345","title":"KiUT: Knowledge-injected U-Transformer for Radiology Report Generation","created":"2023-06-20","cited_by_count":62,"area":null},{"id":"2109.15163","title":"HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning","created":"2021-09-30","cited_by_count":57,"area":null},{"id":"2207.09666","title":"GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features","created":"2022-07-20","cited_by_count":56,"area":null},{"id":"2101.10804","title":"CPTR: Full Transformer Network for Image Captioning","created":"2021-01-26","cited_by_count":55,"area":null},{"id":"2112.01683","title":"TransZero: Attribute-guided Transformer for Zero-Shot Learning","created":"2021-12-03","cited_by_count":54,"area":null},{"id":"2103.14146","title":"Describing and Localizing Multiple Changes with Transformers","created":"2021-03-25","cited_by_count":47,"area":null},{"id":"2206.00923","title":"Modeling Image Composition for Complex Scene Generation","created":"2022-06-02","cited_by_count":43,"area":null},{"id":"2103.11897","title":"Context-Aware Layout to Image Generation with Enhanced Object Appearance","created":"2021-03-22","cited_by_count":41,"area":null},{"id":"2112.15283","title":"ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generation","created":"2021-12-31","cited_by_count":41,"area":null},{"id":"2204.10688","title":"Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds","created":"2022-04-22","cited_by_count":40,"area":null},{"id":"2309.08480","title":"PoseFix: Correcting 3D Human Poses with Natural Language","created":"2023-09-15","cited_by_count":40,"area":null},{"id":"2203.15350","title":"End-to-End Transformer Based Model for Image Captioning","created":"2022-03-29","cited_by_count":38,"area":null},{"id":"2304.04997","title":"Relational Context Learning for Human-Object Interaction Detection","created":"2023-04-11","cited_by_count":36,"area":null},{"id":"2206.06930","title":"Comprehending and Ordering Semantics for Image Captioning","created":"2022-06-14","cited_by_count":33,"area":null},{"id":"2101.06635","title":"Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification","created":"2021-01-17","cited_by_count":31,"area":null},{"id":"2112.08643","title":"TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning","created":"2021-12-16","cited_by_count":28,"area":null},{"id":"2203.01922","title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","created":"2022-03-03","cited_by_count":28,"area":null},{"id":"2108.02366","title":"Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioning","created":"2021-08-05","cited_by_count":27,"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":"2302.06098","title":"Towards Local Visual Modeling for Image Captioning","created":"2023-02-13","cited_by_count":26,"area":null},{"id":"2205.04363","title":"Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning","created":"2022-05-09","cited_by_count":25,"area":null},{"id":"2107.14178","title":"ReFormer: The Relational Transformer for Image Captioning","created":"2021-07-29","cited_by_count":23,"area":null},{"id":"2110.11767","title":"Exploiting Cross-Modal Prediction and Relation Consistency for Semi-Supervised Image Captioning","created":"2021-10-22","cited_by_count":23,"area":null},{"id":"2212.13563","title":"Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning","created":"2022-12-27","cited_by_count":22,"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":"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":"2308.12383","title":"With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning","created":"2023-08-23","cited_by_count":18,"area":null},{"id":"2404.08589","title":"Enhancing Visual Question Answering through Question-Driven Image Captions as Prompts","created":"2024-04-12","cited_by_count":18,"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":"2111.11133","title":"L-Verse: Bidirectional Generation Between Image and Text","created":"2021-11-22","cited_by_count":15,"area":null},{"id":"2202.10492","title":"CaMEL: Mean Teacher Learning for Image Captioning","created":"2022-02-21","cited_by_count":14,"area":null},{"id":"2207.12926","title":"A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance","created":"2022-07-26","cited_by_count":14,"area":null},{"id":"2111.02331","title":"LTD: Low Temperature Distillation for Gradient Masking-free Adversarial Training","created":"2021-11-03","cited_by_count":13,"area":null},{"id":"2311.08223","title":"Improving Image Captioning via Predicting Structured Concepts","created":"2023-11-14","cited_by_count":13,"area":null},{"id":"2407.20341","title":"BRIDGE: Bridging Gaps in Image Captioning Evaluation with Stronger Visual Cues","created":"2024-07-29","cited_by_count":13,"area":null},{"id":"2102.04310","title":"The Singleton Fallacy: Why Current Critiques of Language Models Miss the Point","created":"2021-02-08","cited_by_count":12,"area":null},{"id":"2111.15015","title":"Neural Attention for Image Captioning: Review of Outstanding Methods","created":"2021-11-29","cited_by_count":11,"area":null},{"id":"2210.10914","title":"Prophet Attention: Predicting Attention with Future Attention for Image Captioning","created":"2022-10-19","cited_by_count":10,"area":null},{"id":"2303.03761","title":"Graph Neural Networks in Vision-Language Image Understanding: A Survey","created":"2023-03-07","cited_by_count":10,"area":null},{"id":"2305.16295","title":"HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning","created":"2023-05-25","cited_by_count":10,"area":null},{"id":"2403.07469","title":"A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes","created":"2024-03-12","cited_by_count":10,"area":null},{"id":"2106.10887","title":"Trust It or Not: Confidence-Guided Automatic Radiology Report Generation","created":"2021-06-21","cited_by_count":9,"area":null},{"id":"2108.02059","title":"Question-controlled Text-aware Image Captioning","created":"2021-08-04","cited_by_count":9,"area":null},{"id":"2106.10936","title":"TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning","created":"2021-06-21","cited_by_count":8,"area":null},{"id":"2107.00372","title":"Egocentric Image Captioning for Privacy-Preserved Passive Dietary Intake Monitoring","created":"2021-07-01","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":"2210.11109","title":"Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2311.04192","title":"JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models","created":"2023-11-07","cited_by_count":6,"area":null},{"id":"2505.16334","title":"Panoptic Captioning: An Equivalence Bridge for Image and Text","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2106.12154","title":"Neural Fashion Image Captioning : Accounting for Data Diversity","created":"2021-06-23","cited_by_count":5,"area":null},{"id":"2109.05218","title":"Bornon: Bengali Image Captioning with Transformer-based Deep learning approach","created":"2021-09-11","cited_by_count":5,"area":null},{"id":"2110.00335","title":"Geometry Attention Transformer with Position-aware LSTMs for Image Captioning","created":"2021-10-01","cited_by_count":5,"area":null},{"id":"2207.10897","title":"Efficient Modeling of Future Context for Image Captioning","created":"2022-07-22","cited_by_count":5,"area":null},{"id":"2107.00789","title":"Case Relation Transformer: A Crossmodal Language Generation Model for Fetching Instructions","created":"2021-07-02","cited_by_count":4,"area":null},{"id":"2207.05418","title":"A Baseline for Detecting Out-of-Distribution Examples in Image Captioning","created":"2022-07-12","cited_by_count":4,"area":null},{"id":"2211.14835","title":"CLID: Controlled-Length Image Descriptions with Limited Data","created":"2022-11-27","cited_by_count":4,"area":null},{"id":"2306.07490","title":"Top-Down Framework for Weakly-supervised Grounded Image Captioning","created":"2023-06-13","cited_by_count":4,"area":null},{"id":"2407.14242","title":"Continual Panoptic Perception: Towards Multi-modal Incremental Interpretation of Remote Sensing Images","created":"2024-07-19","cited_by_count":4,"area":null},{"id":"2101.06634","title":"Regional Attention Network (RAN) for Head Pose and Fine-grained Gesture Recognition","created":"2021-01-17","cited_by_count":3,"area":null},{"id":"2106.01424","title":"Learning to Select: A Fully Attentive Approach for Novel Object Captioning","created":"2021-06-02","cited_by_count":3,"area":null},{"id":"2106.10153","title":"All You Can Embed: Natural Language based Vehicle Retrieval with Spatio-Temporal Transformers","created":"2021-06-18","cited_by_count":3,"area":null},{"id":"2109.07799","title":"Label-Attention Transformer with Geometrically Coherent Objects for Image Captioning","created":"2021-09-16","cited_by_count":3,"area":null},{"id":"2110.05731","title":"Topic Scene Graph Generation by Attention Distillation from Caption","created":"2021-10-12","cited_by_count":3,"area":null},{"id":"2204.09276","title":"Situational Perception Guided Image Matting","created":"2022-04-20","cited_by_count":3,"area":null},{"id":"2306.15111","title":"Self-Supervised Image Captioning with CLIP","created":"2023-06-26","cited_by_count":3,"area":null},{"id":"2308.03767","title":"Enhancing image captioning with depth information using a Transformer-based framework","created":"2023-07-24","cited_by_count":3,"area":null},{"id":"2406.00334","title":"Image Captioning via Dynamic Path Customization","created":"2024-06-01","cited_by_count":3,"area":null},{"id":"2406.13129","title":"M3T: Multi-Modal Medical Transformer to bridge Clinical Context with Visual Insights for Retinal Image Medical Description Generation","created":"2024-06-19","cited_by_count":3,"area":null},{"id":"2101.09865","title":"ECOL-R: Encouraging Copying in Novel Object Captioning with Reinforcement Learning","created":"2021-01-25","cited_by_count":2,"area":null},{"id":"2103.05103","title":"Image Captioning using Multiple Transformers for Self-Attention Mechanism","created":"2021-02-14","cited_by_count":2,"area":null},{"id":"2110.03298","title":"End-to-End Supermask Pruning: Learning to Prune Image Captioning Models","created":"2021-10-07","cited_by_count":2,"area":null},{"id":"2110.12442","title":"Bangla Image Caption Generation through CNN-Transformer based Encoder-Decoder Network","created":"2021-10-24","cited_by_count":2,"area":null},{"id":"2204.07476","title":"Guiding Attention using Partial-Order Relationships for Image Captioning","created":"2022-04-15","cited_by_count":2,"area":null},{"id":"2207.03327","title":"Exploring the sequence length bottleneck in the Transformer for Image Captioning","created":"2022-07-07","cited_by_count":2,"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":"2210.01338","title":"Learning to Collocate Visual-Linguistic Neural Modules for Image Captioning","created":"2022-10-04","cited_by_count":2,"area":null},{"id":"2305.04166","title":"UIT-OpenViIC: A Novel Benchmark for Evaluating Image Captioning in Vietnamese","created":"2023-05-07","cited_by_count":2,"area":null},{"id":"2305.12254","title":"A request for clarity over the End of Sequence token in the Self-Critical Sequence Training","created":"2023-05-20","cited_by_count":2,"area":null},{"id":"2311.05726","title":"Neural Network Methods for Radiation Detectors and Imaging","created":"2023-11-09","cited_by_count":2,"area":null},{"id":"2503.23453","title":"Semantic-Spatial Feature Fusion with Dynamic Graph Refinement for Remote Sensing Image Captioning","created":"2025-03-30","cited_by_count":2,"area":null},{"id":"2507.10419","title":"Multiple Choice Learning of Low-Rank Adapters for Language Modeling","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2101.09698","title":"Fast Sequence Generation with Multi-Agent Reinforcement Learning","created":"2021-01-24","cited_by_count":1,"area":null},{"id":"2109.14137","title":"Geometry-Entangled Visual Semantic Transformer for Image Captioning","created":"2021-09-29","cited_by_count":1,"area":null},{"id":"2203.00116","title":"Enhancing Satellite Imagery using Deep Learning for the Sensor To Shooter Timeline","created":"2022-02-28","cited_by_count":1,"area":null},{"id":"2203.04076","title":"Semantic Distillation Guided Salient Object Detection","created":"2022-03-08","cited_by_count":1,"area":null},{"id":"2303.09956","title":"GNNFormer: A Graph-based Framework for Cytopathology Report Generation","created":"2023-03-17","cited_by_count":1,"area":null},{"id":"2305.17433","title":"A Unified Framework for Slot based Response Generation in a Multimodal Dialogue System","created":"2023-05-27","cited_by_count":1,"area":null},{"id":"2307.09915","title":"Embedded Heterogeneous Attention Transformer for Cross-lingual Image Captioning","created":"2023-07-19","cited_by_count":1,"area":null},{"id":"2308.02833","title":"A Comprehensive Analysis of Real-World Image Captioning and Scene Identification","created":"2023-08-05","cited_by_count":1,"area":null}],"next_cursor":"100"}