{"total":109,"rows":[{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940,"area":"lr"},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559,"area":null},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525,"area":null},{"id":"2112.12143","title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","created":"2021-12-22","cited_by_count":473,"area":null},{"id":"2204.09817","title":"Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing","created":"2022-04-21","cited_by_count":339,"area":null},{"id":"1811.10092","title":"Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation","created":"2018-11-25","cited_by_count":305,"area":"offlinerl"},{"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":"2112.08879","title":"Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds","created":"2021-12-16","cited_by_count":128,"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":"2101.00529","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","created":"2021-01-02","cited_by_count":110,"area":"mllm"},{"id":"2207.08954","title":"Exploiting Unlabeled Data with Vision and Language Models for Object Detection","created":"2022-07-18","cited_by_count":97,"area":null},{"id":"2303.05657","title":"Tag2Text: Guiding Vision-Language Model via Image Tagging","created":"2023-03-10","cited_by_count":86,"area":"mllm"},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"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":"2201.12944","title":"Deep Learning Approaches on Image Captioning: A Review","created":"2022-01-31","cited_by_count":43,"area":"mllm"},{"id":"2312.08366","title":"See, Say, and Segment: Teaching LMMs to Overcome False Premises","created":"2023-12-13","cited_by_count":41,"area":"mllm"},{"id":"2106.14019","title":"UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning","created":"2021-06-26","cited_by_count":37,"area":null},{"id":"2405.05256","title":"THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models","created":"2024-05-08","cited_by_count":36,"area":"mllm"},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"id":"2303.11403","title":"eP-ALM: Efficient Perceptual Augmentation of Language Models","created":"2023-03-20","cited_by_count":34,"area":null},{"id":"2206.06930","title":"Comprehending and Ordering Semantics for Image Captioning","created":"2022-06-14","cited_by_count":33,"area":null},{"id":"2312.08078","title":"Fine-Grained Image-Text Alignment in Medical Imaging Enables Explainable Cyclic Image-Report Generation","created":"2023-12-13","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":"2502.14914","title":"CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness","created":"2025-02-19","cited_by_count":25,"area":"mllm"},{"id":"2107.09106","title":"Separating Skills and Concepts for Novel Visual Question Answering","created":"2021-07-19","cited_by_count":24,"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":"2309.13505","title":"Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation","created":"2023-09-24","cited_by_count":21,"area":"mllm"},{"id":"2105.13865","title":"Recursive Contour Saliency Blending Network for Accurate Salient Object Detection","created":"2021-05-28","cited_by_count":20,"area":null},{"id":"2205.11283","title":"SelfReformer: Self-Refined Network with Transformer for Salient Object Detection","created":"2022-05-23","cited_by_count":20,"area":null},{"id":"2209.13983","title":"Medical Image Captioning via Generative Pretrained Transformers","created":"2022-09-28","cited_by_count":20,"area":null},{"id":"2104.01894","title":"Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval","created":"2021-04-05","cited_by_count":19,"area":null},{"id":"2110.10596","title":"Look at What I'm Doing: Self-Supervised Spatial Grounding of Narrations in Instructional Videos","created":"2021-10-20","cited_by_count":18,"area":null},{"id":"2303.10396","title":"Towards Diverse Binary Segmentation via A Simple yet General Gated Network","created":"2023-03-18","cited_by_count":17,"area":null},{"id":"2312.04554","title":"Improved Visual Grounding through Self-Consistent Explanations","created":"2023-12-07","cited_by_count":17,"area":null},{"id":"2104.09829","title":"Detector-Free Weakly Supervised Grounding by Separation","created":"2021-04-20","cited_by_count":16,"area":null},{"id":"2104.12471","title":"Contextualized Keyword Representations for Multi-modal Retinal Image Captioning","created":"2021-04-26","cited_by_count":16,"area":null},{"id":"2105.14538","title":"Longer Version for \"Deep Context-Encoding Network for Retinal Image Captioning\"","created":"2021-05-30","cited_by_count":16,"area":null},{"id":"2305.12260","title":"Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment","created":"2023-05-20","cited_by_count":15,"area":null},{"id":"2105.12754","title":"Computer Vision and Conflicting Values: Describing People with Automated Alt Text","created":"2021-05-26","cited_by_count":14,"area":null},{"id":"2210.08908","title":"Cross-modal Semantic Enhanced Interaction for Image-Sentence Retrieval","created":"2022-10-17","cited_by_count":14,"area":null},{"id":"2211.12148","title":"Aligning Source Visual and Target Language Domains for Unpaired Video Captioning","created":"2022-11-22","cited_by_count":14,"area":null},{"id":"2109.00363","title":"ConRPG: Paraphrase Generation using Contexts as Regularizer","created":"2021-09-01","cited_by_count":13,"area":null},{"id":"2109.01949","title":"Improving Joint Learning of Chest X-Ray and Radiology Report by Word Region Alignment","created":"2021-09-04","cited_by_count":13,"area":null},{"id":"2208.09843","title":"CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval","created":"2022-08-21","cited_by_count":13,"area":null},{"id":"2110.10328","title":"R$^3$Net:Relation-embedded Representation Reconstruction Network for Change Captioning","created":"2021-10-20","cited_by_count":12,"area":null},{"id":"2203.04895","title":"Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction","created":"2022-03-09","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":"2206.09358","title":"What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs","created":"2022-06-19","cited_by_count":11,"area":null},{"id":"2504.10143","title":"On the Value of Cross-Modal Misalignment in Multimodal Representation Learning","created":"2025-04-14","cited_by_count":10,"area":null},{"id":"2304.03147","title":"Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions","created":"2023-04-06","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":"2106.15550","title":"Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue","created":"2021-06-29","cited_by_count":8,"area":null},{"id":"2208.04215","title":"Boosting Video-Text Retrieval with Explicit High-Level Semantics","created":"2022-08-08","cited_by_count":8,"area":null},{"id":"2103.12347","title":"Shared Latent Space of Font Shapes and Their Noisy Impressions","created":"2021-03-23","cited_by_count":7,"area":null},{"id":"2105.04780","title":"Cross-Modal Generative Augmentation for Visual Question Answering","created":"2021-05-11","cited_by_count":7,"area":null},{"id":"2212.05561","title":"Using Multiple Instance Learning to Build Multimodal Representations","created":"2022-12-11","cited_by_count":7,"area":null},{"id":"2308.01472","title":"Reverse Stable Diffusion: What prompt was used to generate this image?","created":"2023-08-02","cited_by_count":7,"area":"diffusion"},{"id":"2508.16292","title":"Do What? Teaching Vision-Language-Action Models to Reject the Impossible","created":"2025-08-22","cited_by_count":7,"area":"vla"},{"id":"2106.10658","title":"Exploring Semantic Relationships for Unpaired Image Captioning","created":"2021-06-20","cited_by_count":6,"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":"2503.16872","title":"Lie Detector: Unified Backdoor Detection via Cross-Examination Framework","created":"2025-03-21","cited_by_count":6,"area":null},{"id":"2509.21363","title":"A Mutual Learning Method for Salient Object Detection with intertwined Multi-Supervision--Revised","created":"2025-09-21","cited_by_count":6,"area":null},{"id":"2101.09915","title":"Weakly Supervised Thoracic Disease Localization via Disease Masks","created":"2021-01-25","cited_by_count":5,"area":null},{"id":"2103.14785","title":"A Comprehensive Review of the Video-to-Text Problem","created":"2021-03-27","cited_by_count":5,"area":null},{"id":"2209.01638","title":"Every picture tells a story: Image-grounded controllable stylistic story generation","created":"2022-09-04","cited_by_count":5,"area":null},{"id":"2407.19605","title":"Look Hear: Gaze Prediction for Speech-directed Human Attention","created":"2024-07-28","cited_by_count":5,"area":null},{"id":"2503.17211","title":"A Language Anchor-Guided Method for Robust Noisy Domain Generalization","created":"2025-03-21","cited_by_count":5,"area":null},{"id":"2105.06449","title":"Feature Interactions on Steroids: On the Composition of ML Models","created":"2021-05-13","cited_by_count":4,"area":null},{"id":"2210.16431","title":"DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention","created":"2022-10-28","cited_by_count":4,"area":null},{"id":"2312.15720","title":"Set Prediction Guided by Semantic Concepts for Diverse Video Captioning","created":"2023-12-25","cited_by_count":4,"area":null},{"id":"2510.04479","title":"VaseVQA-3D: Benchmarking 3D VLMs on Ancient Greek Pottery","created":"2025-10-06","cited_by_count":4,"area":"lr"},{"id":"2106.02257","title":"Visual Question Rewriting for Increasing Response Rate","created":"2021-06-04","cited_by_count":3,"area":null},{"id":"2210.08957","title":"Weakly Supervised Face Naming with Symmetry-Enhanced Contrastive Loss","created":"2022-10-17","cited_by_count":3,"area":null},{"id":"2305.05260","title":"Guided Focal Stack Refinement Network for Light Field Salient Object Detection","created":"2023-05-09","cited_by_count":3,"area":null},{"id":"2305.14779","title":"Alt-Text with Context: Improving Accessibility for Images on Twitter","created":"2023-05-24","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":"2309.03874","title":"Box-based Refinement for Weakly Supervised and Unsupervised Localization Tasks","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2104.12663","title":"CAGAN: Text-To-Image Generation with Combined Attention GANs","created":"2021-04-26","cited_by_count":2,"area":null},{"id":"2105.08573","title":"Dependent Multi-Task Learning with Causal Intervention for Image Captioning","created":"2021-05-18","cited_by_count":2,"area":null},{"id":"2111.03195","title":"Addressing Multiple Salient Object Detection via Dual-Space Long-Range Dependencies","created":"2021-11-04","cited_by_count":2,"area":null},{"id":"2112.01062","title":"Syntax Customized Video Captioning by Imitating Exemplar Sentences","created":"2021-12-02","cited_by_count":2,"area":null},{"id":"2204.07367","title":"On the Role of Pre-trained Language Models in Word Ordering: A Case Study with BART","created":"2022-04-15","cited_by_count":2,"area":null},{"id":"2207.01733","title":"Are metrics measuring what they should? An evaluation of image captioning task metrics","created":"2022-07-04","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":"2301.08784","title":"Visual Semantic Relatedness Dataset for Image Captioning","created":"2023-01-20","cited_by_count":2,"area":null},{"id":"2408.15566","title":"TagOOD: A Novel Approach to Out-of-Distribution Detection via Vision-Language Representations and Class Center Learning","created":"2024-08-28","cited_by_count":2,"area":null},{"id":"2508.17750","title":"From Global to Local: Social Bias Transfer in CLIP","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2604.17472","title":"UniMesh: Unifying 3D Mesh Understanding and Generation","created":"2026-04-19","cited_by_count":2,"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":"2303.16341","title":"Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding","created":"2023-03-28","cited_by_count":1,"area":null},{"id":"2312.09367","title":"Text-Guided Face Recognition using Multi-Granularity Cross-Modal Contrastive Learning","created":"2023-12-14","cited_by_count":1,"area":null},{"id":"2408.04909","title":"Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2505.24227","title":"Light as Deception: GPT-driven Natural Relighting Against Vision-Language Pre-training Models","created":"2025-05-30","cited_by_count":1,"area":"mllm"},{"id":"2507.08610","title":"Emergent Natural Language with Communication Games for Improving Image Captioning Capabilities without Additional Data","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2510.03252","title":"Universal Multi-Domain Translation via Diffusion Routers","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2605.17938","title":"Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew","created":"2026-05-18","cited_by_count":1,"area":"diffusion"},{"id":"2109.04993","title":"LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation","created":"2021-09-04","cited_by_count":0,"area":null},{"id":"2206.07986","title":"Image Captioning based on Feature Refinement and Reflective Decoding","created":"2022-06-16","cited_by_count":0,"area":null},{"id":"2209.12817","title":"Word to Sentence Visual Semantic Similarity for Caption Generation: Lessons Learned","created":"2022-09-26","cited_by_count":0,"area":null},{"id":"2302.04676","title":"Stacked Cross-modal Feature Consolidation Attention Networks for Image Captioning","created":"2023-02-08","cited_by_count":0,"area":null}],"next_cursor":"100"}