{"total":215,"rows":[{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559,"area":null},{"id":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196,"area":"mllm"},{"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":"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":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2103.03493","title":"Causal Attention for Vision-Language Tasks","created":"2021-03-05","cited_by_count":111,"area":"mllm"},{"id":"2304.04514","title":"DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment","created":"2023-04-10","cited_by_count":90,"area":null},{"id":"2101.06462","title":"Dual-Level Collaborative Transformer for Image Captioning","created":"2021-01-16","cited_by_count":71,"area":null},{"id":"2107.02112","title":"Recovering the Unbiased Scene Graphs from the Biased Ones","created":"2021-07-05","cited_by_count":71,"area":null},{"id":"2203.00843","title":"X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning","created":"2022-03-02","cited_by_count":70,"area":"distill"},{"id":"2108.09668","title":"Learning of Visual Relations: The Devil is in the Tails","created":"2021-08-22","cited_by_count":65,"area":null},{"id":"2109.02227","title":"Learning to Generate Scene Graph from Natural Language Supervision","created":"2021-09-06","cited_by_count":64,"area":null},{"id":"2103.16083","title":"Fully Convolutional Scene Graph Generation","created":"2021-03-30","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":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","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":"2209.01814","title":"RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection","created":"2022-09-05","cited_by_count":55,"area":null},{"id":"2208.08165","title":"Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuning","created":"2022-08-17","cited_by_count":54,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2206.06291","title":"Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection","created":"2022-06-13","cited_by_count":47,"area":null},{"id":"2203.05203","title":"MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes","created":"2022-03-10","cited_by_count":46,"area":null},{"id":"2308.09351","title":"RLIPv2: Fast Scaling of Relational Language-Image Pre-training","created":"2023-08-18","cited_by_count":45,"area":null},{"id":"2403.09766","title":"An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models","created":"2024-03-14","cited_by_count":45,"area":"mllm"},{"id":"2106.10815","title":"Structured Sparse R-CNN for Direct Scene Graph Generation","created":"2021-06-21","cited_by_count":44,"area":null},{"id":"2201.12944","title":"Deep Learning Approaches on Image Captioning: A Review","created":"2022-01-31","cited_by_count":43,"area":"mllm"},{"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":"2110.09753","title":"Unifying Multimodal Transformer for Bi-directional Image and Text Generation","created":"2021-10-19","cited_by_count":41,"area":null},{"id":"2112.05230","title":"Injecting Semantic Concepts into End-to-End Image Captioning","created":"2021-12-09","cited_by_count":41,"area":null},{"id":"2307.11986","title":"Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answering","created":"2023-07-22","cited_by_count":41,"area":"mllm"},{"id":"2203.15350","title":"End-to-End Transformer Based Model for Image Captioning","created":"2022-03-29","cited_by_count":38,"area":null},{"id":"2207.13162","title":"Retrieval-Augmented Transformer for Image Captioning","created":"2022-07-26","cited_by_count":38,"area":"rag"},{"id":"2212.03099","title":"Semantic-Conditional Diffusion Networks for Image Captioning","created":"2022-12-06","cited_by_count":38,"area":"diffusion"},{"id":"2304.04997","title":"Relational Context Learning for Human-Object Interaction Detection","created":"2023-04-11","cited_by_count":36,"area":null},{"id":"2403.03715","title":"MeaCap: Memory-Augmented Zero-shot Image Captioning","created":"2024-03-06","cited_by_count":35,"area":null},{"id":"2206.06930","title":"Comprehending and Ordering Semantics for Image Captioning","created":"2022-06-14","cited_by_count":33,"area":null},{"id":"2303.02437","title":"ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing","created":"2023-03-04","cited_by_count":33,"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":"2107.11970","title":"Boosting Entity-aware Image Captioning with Multi-modal Knowledge Graph","created":"2021-07-26","cited_by_count":31,"area":null},{"id":"2108.07073","title":"ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration","created":"2021-08-16","cited_by_count":31,"area":null},{"id":"2112.09828","title":"Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs","created":"2021-12-18","cited_by_count":31,"area":null},{"id":"2408.09429","title":"Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models","created":"2024-08-18","cited_by_count":30,"area":"mllm"},{"id":"2109.08039","title":"A Survey on Temporal Sentence Grounding in Videos","created":"2021-09-16","cited_by_count":29,"area":null},{"id":"2302.08268","title":"Retrieval-augmented Image Captioning","created":"2023-02-16","cited_by_count":29,"area":"rag"},{"id":"2112.00974","title":"Consensus Graph Representation Learning for Better Grounded Image Captioning","created":"2021-12-02","cited_by_count":28,"area":null},{"id":"2407.07844","title":"OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion","created":"2024-07-10","cited_by_count":28,"area":null},{"id":"2410.23904","title":"EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection","created":"2024-10-31","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":"2112.06558","title":"MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioning","created":"2021-12-13","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":"2110.02526","title":"Coarse-to-Fine Reasoning for Visual Question Answering","created":"2021-10-06","cited_by_count":25,"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":"2207.11100","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","created":"2022-07-22","cited_by_count":25,"area":null},{"id":"2209.10326","title":"Toward 3D Spatial Reasoning for Human-like Text-based Visual Question Answering","created":"2022-09-21","cited_by_count":25,"area":"lr"},{"id":"2108.05067","title":"Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning","created":"2021-08-11","cited_by_count":24,"area":null},{"id":"2107.14178","title":"ReFormer: The Relational Transformer for Image Captioning","created":"2021-07-29","cited_by_count":23,"area":null},{"id":"2205.13125","title":"Prompt-based Learning for Unpaired Image Captioning","created":"2022-05-26","cited_by_count":23,"area":null},{"id":"2202.00259","title":"Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics","created":"2022-02-01","cited_by_count":22,"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":"2301.09017","title":"Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models?","created":"2023-01-21","cited_by_count":21,"area":null},{"id":"2108.11636","title":"SketchLattice: Latticed Representation for Sketch Manipulation","created":"2021-08-26","cited_by_count":19,"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":"2101.11562","title":"Scheduled Sampling in Vision-Language Pretraining with Decoupled Encoder-Decoder Network","created":"2021-01-27","cited_by_count":17,"area":"mllm"},{"id":"2103.13361","title":"Structured Co-reference Graph Attention for Video-grounded Dialogue","created":"2021-03-24","cited_by_count":17,"area":null},{"id":"2302.09636","title":"Interpretable Medical Image Visual Question Answering via Multi-Modal Relationship Graph Learning","created":"2023-02-19","cited_by_count":17,"area":null},{"id":"2406.00644","title":"Ultrasound Report Generation with Cross-Modality Feature Alignment via Unsupervised Guidance","created":"2024-06-02","cited_by_count":17,"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":"2211.11694","title":"Exploring Discrete Diffusion Models for Image Captioning","created":"2022-11-21","cited_by_count":16,"area":"diffusion"},{"id":"2305.02177","title":"Transforming Visual Scene Graphs to Image Captions","created":"2023-05-03","cited_by_count":15,"area":"moe"},{"id":"2202.10492","title":"CaMEL: Mean Teacher Learning for Image Captioning","created":"2022-02-21","cited_by_count":14,"area":null},{"id":"2306.17469","title":"Manga109Dialog: A Large-scale Dialogue Dataset for Comics Speaker Detection","created":"2023-06-30","cited_by_count":14,"area":null},{"id":"2109.08475","title":"GoG: Relation-aware Graph-over-Graph Network for Visual Dialog","created":"2021-09-17","cited_by_count":13,"area":null},{"id":"2112.11739","title":"A Survey of Natural Language Generation","created":"2021-12-22","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":"2104.01703","title":"FixMyPose: Pose Correctional Captioning and Retrieval","created":"2021-04-04","cited_by_count":12,"area":null},{"id":"2106.09436","title":"Semi-Autoregressive Transformer for Image Captioning","created":"2021-06-17","cited_by_count":12,"area":null},{"id":"2108.08421","title":"Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenes","created":"2021-08-19","cited_by_count":12,"area":null},{"id":"2108.08600","title":"Semantic Compositional Learning for Low-shot Scene Graph Generation","created":"2021-08-19","cited_by_count":12,"area":null},{"id":"2201.12723","title":"A Frustratingly Simple Approach for End-to-End Image Captioning","created":"2022-01-30","cited_by_count":12,"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":"2401.02347","title":"Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training","created":"2024-01-04","cited_by_count":12,"area":null},{"id":"2505.19503","title":"Locality-Aware Zero-Shot Human-Object Interaction Detection","created":"2025-05-26","cited_by_count":12,"area":"mllm"},{"id":"2109.04047","title":"ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection","created":"2021-09-09","cited_by_count":11,"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":"2107.11576","title":"X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering","created":"2021-07-24","cited_by_count":10,"area":null},{"id":"2108.08217","title":"X-modaler: A Versatile and High-performance Codebase for Cross-modal Analytics","created":"2021-08-18","cited_by_count":10,"area":null},{"id":"2110.05342","title":"Semi-Autoregressive Image Captioning","created":"2021-10-11","cited_by_count":10,"area":null},{"id":"2112.11628","title":"SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks","created":"2021-12-22","cited_by_count":10,"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":"2305.00581","title":"Multimodal Graph Transformer for Multimodal Question Answering","created":"2023-04-30","cited_by_count":10,"area":null},{"id":"2308.12045","title":"CgT-GAN: CLIP-guided Text GAN for Image Captioning","created":"2023-08-23","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":"2104.11934","title":"RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition","created":"2021-04-24","cited_by_count":9,"area":null},{"id":"2106.05047","title":"Salient Object Ranking with Position-Preserved Attention","created":"2021-06-09","cited_by_count":9,"area":null},{"id":"2107.03824","title":"Instance-Level Relative Saliency Ranking with Graph Reasoning","created":"2021-07-08","cited_by_count":9,"area":null},{"id":"2505.19510","title":"LLM Meets Scene Graph: Can Large Language Models Understand and Generate Scene Graphs? A Benchmark and Empirical Study","created":"2025-05-26","cited_by_count":9,"area":null}],"next_cursor":"100"}