{"total":176,"rows":[{"id":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302,"area":null},{"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":"2308.12964","title":"Dense Text-to-Image Generation with Attention Modulation","created":"2023-08-24","cited_by_count":163,"area":"diffusion"},{"id":"2304.08295","title":"Interactive and Explainable Region-guided Radiology Report Generation","created":"2023-04-17","cited_by_count":140,"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":"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":"2209.10767","title":"DRAMA: Joint Risk Localization and Captioning in Driving","created":"2022-09-22","cited_by_count":126,"area":null},{"id":"2212.00280","title":"GRiT: A Generative Region-to-text Transformer for Object Understanding","created":"2022-12-01","cited_by_count":121,"area":null},{"id":"2305.02677","title":"Caption Anything: Interactive Image Description with Diverse Multimodal Controls","created":"2023-05-04","cited_by_count":99,"area":null},{"id":"2111.10265","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","created":"2021-11-19","cited_by_count":93,"area":null},{"id":"2205.02655","title":"Language Models Can See: Plugging Visual Controls in Text Generation","created":"2022-05-05","cited_by_count":90,"area":null},{"id":"2304.06720","title":"Expressive Text-to-Image Generation with Rich Text","created":"2023-04-13","cited_by_count":89,"area":null},{"id":"2211.13319","title":"Make-A-Story: Visual Memory Conditioned Consistent Story Generation","created":"2022-11-23","cited_by_count":76,"area":null},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76,"area":"mllm"},{"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":"2402.03226","title":"FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion","created":"2024-02-05","cited_by_count":68,"area":"moe"},{"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":"2304.04565","title":"SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries","created":"2023-04-10","cited_by_count":57,"area":null},{"id":"2110.10834","title":"Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization","created":"2021-10-21","cited_by_count":52,"area":null},{"id":"2112.01551","title":"D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding","created":"2021-12-02","cited_by_count":52,"area":null},{"id":"2404.09216","title":"DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection","created":"2024-04-14","cited_by_count":48,"area":null},{"id":"2311.01477","title":"FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Models","created":"2023-11-02","cited_by_count":46,"area":"mllm"},{"id":"2104.05845","title":"Visual Goal-Step Inference using wikiHow","created":"2021-04-12","cited_by_count":43,"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":"2406.07502","title":"Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions","created":"2024-06-11","cited_by_count":43,"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":"2202.04800","title":"The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning","created":"2022-02-10","cited_by_count":38,"area":"lr"},{"id":"2111.13424","title":"ContIG: Self-supervised Multimodal Contrastive Learning for Medical Imaging with Genetics","created":"2021-11-26","cited_by_count":36,"area":null},{"id":"2403.19596","title":"LocCa: Visual Pretraining with Location-aware Captioners","created":"2024-03-28","cited_by_count":35,"area":null},{"id":"2305.17718","title":"FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions","created":"2023-05-28","cited_by_count":33,"area":"mllm"},{"id":"2108.11092","title":"INVIGORATE: Interactive Visual Grounding and Grasping in Clutter","created":"2021-08-25","cited_by_count":32,"area":null},{"id":"2308.07918","title":"Helping Hands: An Object-Aware Ego-Centric Video Recognition Model","created":"2023-08-15","cited_by_count":31,"area":null},{"id":"2312.00869","title":"Segment and Caption Anything","created":"2023-12-01","cited_by_count":30,"area":null},{"id":"2403.10191","title":"Generative Region-Language Pretraining for Open-Ended Object Detection","created":"2024-03-15","cited_by_count":29,"area":null},{"id":"2104.03236","title":"Multimodal Entity Linking for Tweets","created":"2021-04-07","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":"2109.09920","title":"Survey: Transformer based Video-Language Pre-training","created":"2021-09-21","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":"2411.15411","title":"FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity","created":"2024-11-23","cited_by_count":27,"area":"mllm"},{"id":"2101.04741","title":"CityFlow-NL: Tracking and Retrieval of Vehicles at City Scale by Natural Language Descriptions","created":"2021-01-12","cited_by_count":26,"area":null},{"id":"2303.02489","title":"CapDet: Unifying Dense Captioning and Open-World Detection Pretraining","created":"2023-03-04","cited_by_count":26,"area":"mllm"},{"id":"2410.00255","title":"Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning","created":"2024-09-30","cited_by_count":26,"area":null},{"id":"2105.03236","title":"Towards Accurate Text-based Image Captioning with Content Diversity Exploration","created":"2021-04-23","cited_by_count":25,"area":null},{"id":"2109.08029","title":"Image Captioning for Effective Use of Language Models in Knowledge-Based Visual Question Answering","created":"2021-09-15","cited_by_count":25,"area":null},{"id":"2207.10075","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","created":"2022-07-20","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":"2303.15932","title":"Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report Generation","created":"2023-03-28","cited_by_count":23,"area":null},{"id":"2309.17093","title":"Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval","created":"2023-09-29","cited_by_count":23,"area":null},{"id":"2109.13701","title":"CIDEr-R: Robust Consensus-based Image Description Evaluation","created":"2021-09-28","cited_by_count":22,"area":null},{"id":"2203.15269","title":"Vision Transformers in Medical Computer Vision -- A Contemplative Retrospection","created":"2022-03-29","cited_by_count":22,"area":null},{"id":"2102.08094","title":"Composing Pick-and-Place Tasks By Grounding Language","created":"2021-02-16","cited_by_count":20,"area":null},{"id":"2204.08058","title":"MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration","created":"2022-04-17","cited_by_count":20,"area":null},{"id":"2302.01328","title":"IC3: Image Captioning by Committee Consensus","created":"2023-02-02","cited_by_count":20,"area":null},{"id":"2407.08521","title":"Emergent Visual-Semantic Hierarchies in Image-Text Representations","created":"2024-07-11","cited_by_count":19,"area":null},{"id":"2106.04605","title":"Check It Again: Progressive Visual Question Answering via Visual Entailment","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2210.03925","title":"Contextual Modeling for 3D Dense Captioning on Point Clouds","created":"2022-10-08","cited_by_count":18,"area":null},{"id":"2312.09237","title":"Pixel Aligned Language Models","created":"2023-12-14","cited_by_count":17,"area":"mllm"},{"id":"2510.22391","title":"Top-Down Semantic Refinement for Image Captioning","created":"2025-10-25","cited_by_count":16,"area":"mllm"},{"id":"2401.06167","title":"Enhancing Multimodal Understanding with CLIP-Based Image-to-Text Transformation","created":"2024-01-02","cited_by_count":15,"area":null},{"id":"2103.04037","title":"Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision","created":"2021-03-06","cited_by_count":14,"area":null},{"id":"2109.02865","title":"Journalistic Guidelines Aware News Image Captioning","created":"2021-09-07","cited_by_count":14,"area":null},{"id":"2110.13606","title":"AUTO-DISCERN: Autonomous Driving Using Common Sense Reasoning","created":"2021-10-17","cited_by_count":14,"area":null},{"id":"2407.01942","title":"Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness","created":"2024-07-02","cited_by_count":14,"area":null},{"id":"2603.03985","title":"RIVER: A Real-Time Interaction Benchmark for Video LLMs","created":"2026-03-04","cited_by_count":14,"area":"mllm"},{"id":"2105.05964","title":"Connecting What to Say With Where to Look by Modeling Human Attention Traces","created":"2021-05-12","cited_by_count":13,"area":null},{"id":"2401.17910","title":"ControlCap: Controllable Region-level Captioning","created":"2024-01-31","cited_by_count":13,"area":null},{"id":"2407.10947","title":"Can Textual Semantics Mitigate Sounding Object Segmentation Preference?","created":"2024-07-15","cited_by_count":13,"area":null},{"id":"2504.09083","title":"Using Vision Language Models for Safety Hazard Identification in Construction","created":"2025-04-12","cited_by_count":13,"area":"mllm"},{"id":"2104.01703","title":"FixMyPose: Pose Correctional Captioning and Retrieval","created":"2021-04-04","cited_by_count":12,"area":null},{"id":"2312.02142","title":"Object Recognition as Next Token Prediction","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2312.04837","title":"Localized Symbolic Knowledge Distillation for Visual Commonsense Models","created":"2023-12-08","cited_by_count":12,"area":"distill"},{"id":"2105.04047","title":"Analyzing Online Political Advertisements","created":"2021-05-09","cited_by_count":11,"area":null},{"id":"2204.12974","title":"CapOnImage: Context-driven Dense-Captioning on Image","created":"2022-04-27","cited_by_count":11,"area":null},{"id":"2409.04388","title":"Question-Answering Dense Video Events","created":"2024-09-06","cited_by_count":11,"area":null},{"id":"2212.00843","title":"Focus! Relevant and Sufficient Context Selection for News Image Captioning","created":"2022-12-01","cited_by_count":10,"area":null},{"id":"2306.11729","title":"Dense Video Object Captioning from Disjoint Supervision","created":"2023-06-20","cited_by_count":10,"area":null},{"id":"2312.02520","title":"Towards More Unified In-context Visual Understanding","created":"2023-12-05","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":"2505.05804","title":"Describe Anything in Medical Images","created":"2025-05-09","cited_by_count":10,"area":"mllm"},{"id":"2107.03050","title":"Controlled Caption Generation for Images Through Adversarial Attacks","created":"2021-07-07","cited_by_count":9,"area":null},{"id":"2112.00969","title":"Object-Centric Unsupervised Image Captioning","created":"2021-12-02","cited_by_count":9,"area":null},{"id":"2404.10763","title":"LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?","created":"2024-04-16","cited_by_count":9,"area":"diffusion"},{"id":"2207.11118","title":"Rethinking the Reference-based Distinctive Image Captioning","created":"2022-07-22","cited_by_count":8,"area":null},{"id":"2111.11099","title":"Talk-to-Resolve: Combining scene understanding and spatial dialogue to resolve granular task ambiguity for a collocated robot","created":"2021-11-22","cited_by_count":7,"area":null},{"id":"2206.08792","title":"FD-CAM: Improving Faithfulness and Discriminability of Visual Explanation for CNNs","created":"2022-06-17","cited_by_count":7,"area":null},{"id":"2403.12026","title":"FlexCap: Describe Anything in Images in Controllable Detail","created":"2024-03-18","cited_by_count":7,"area":"mllm"},{"id":"2406.09988","title":"Details Make a Difference: Object State-Sensitive Neurorobotic Task Planning","created":"2024-06-14","cited_by_count":7,"area":null},{"id":"2102.07192","title":"Improved Bengali Image Captioning via deep convolutional neural network based encoder-decoder model","created":"2021-02-14","cited_by_count":6,"area":null},{"id":"2106.04232","title":"Giving Commands to a Self-Driving Car: How to Deal with Uncertain Situations?","created":"2021-06-08","cited_by_count":6,"area":null},{"id":"2110.10906","title":"Single-Modal Entropy based Active Learning for Visual Question Answering","created":"2021-10-21","cited_by_count":6,"area":null},{"id":"2210.13076","title":"Towards Unifying Reference Expression Generation and Comprehension","created":"2022-10-24","cited_by_count":6,"area":null},{"id":"2312.15162","title":"Cycle-Consistency Learning for Captioning and Grounding","created":"2023-12-23","cited_by_count":6,"area":null},{"id":"2403.08049","title":"TutoAI: A Cross-domain Framework for AI-assisted Mixed-media Tutorial Creation on Physical Tasks","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2408.10499","title":"ProgramAlly: Creating Custom Visual Access Programs via Multi-Modal End-User Programming","created":"2024-08-20","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":"2310.18804","title":"Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting","created":"2023-10-28","cited_by_count":5,"area":null},{"id":"2310.19516","title":"Generating Context-Aware Natural Answers for Questions in 3D Scenes","created":"2023-10-30","cited_by_count":5,"area":null},{"id":"2402.11940","title":"AICAttack: Adversarial Image Captioning Attack with Attention-Based Optimization","created":"2024-02-19","cited_by_count":5,"area":null}],"next_cursor":"100"}