{"total":158,"rows":[{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661,"area":null},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656,"area":null},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"area":null},{"id":"2204.11817","title":"Translation between Molecules and Natural Language","created":"2022-04-25","cited_by_count":177,"area":null},{"id":"2211.16312","title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding","created":"2022-11-29","cited_by_count":177,"area":null},{"id":"2312.03818","title":"Alpha-CLIP: A CLIP Model Focusing on Wherever You Want","created":"2023-12-06","cited_by_count":151,"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":"2303.10323","title":"Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation","created":"2023-03-18","cited_by_count":118,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2310.10196","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","created":"2023-10-16","cited_by_count":110,"area":null},{"id":"2106.08503","title":"Understanding and Evaluating Racial Biases in Image Captioning","created":"2021-06-16","cited_by_count":108,"area":null},{"id":"2306.07303","title":"A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks","created":"2023-06-11","cited_by_count":71,"area":null},{"id":"2406.01326","title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","created":"2024-06-03","cited_by_count":71,"area":null},{"id":"2209.15179","title":"Physical Adversarial Attack meets Computer Vision: A Decade Survey","created":"2022-09-30","cited_by_count":67,"area":null},{"id":"2304.06488","title":"One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era","created":"2023-04-04","cited_by_count":55,"area":null},{"id":"2111.00418","title":"Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances","created":"2021-10-31","cited_by_count":54,"area":null},{"id":"2101.09983","title":"Adversarial Text-to-Image Synthesis: A Review","created":"2021-01-25","cited_by_count":52,"area":null},{"id":"2206.09191","title":"Gender Artifacts in Visual Datasets","created":"2022-06-18","cited_by_count":38,"area":null},{"id":"2204.07756","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","created":"2022-04-16","cited_by_count":37,"area":null},{"id":"2108.11092","title":"INVIGORATE: Interactive Visual Grounding and Grasping in Clutter","created":"2021-08-25","cited_by_count":32,"area":null},{"id":"2407.09777","title":"Graph Transformers: A Survey","created":"2024-07-13","cited_by_count":32,"area":null},{"id":"2312.00869","title":"Segment and Caption Anything","created":"2023-12-01","cited_by_count":30,"area":null},{"id":"2106.05386","title":"Artificial Intelligence in Drug Discovery: Applications and Techniques","created":"2021-06-09","cited_by_count":28,"area":null},{"id":"2105.12497","title":"Designing ECG Monitoring Healthcare System with Federated Transfer Learning and Explainable AI","created":"2021-05-26","cited_by_count":26,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2101.06013","title":"Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge","created":"2021-01-15","cited_by_count":24,"area":null},{"id":"2108.09003","title":"Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey","created":"2021-08-20","cited_by_count":24,"area":null},{"id":"2312.07622","title":"Mathematical Language Models: A Survey","created":"2023-12-12","cited_by_count":24,"area":null},{"id":"2205.13125","title":"Prompt-based Learning for Unpaired Image Captioning","created":"2022-05-26","cited_by_count":23,"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":"2107.03178","title":"Levels of explainable artificial intelligence for human-aligned conversational explanations","created":"2021-07-07","cited_by_count":21,"area":null},{"id":"2311.17048","title":"Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions","created":"2023-11-28","cited_by_count":21,"area":null},{"id":"2207.09542","title":"Controllable Data Generation by Deep Learning: A Review","created":"2022-07-19","cited_by_count":20,"area":null},{"id":"2302.13580","title":"Joint Task and Data Oriented Semantic Communications: A Deep Separate Source-channel Coding Scheme","created":"2023-02-27","cited_by_count":19,"area":null},{"id":"2304.01926","title":"High-Throughput Vector Similarity Search in Knowledge Graphs","created":"2023-04-04","cited_by_count":19,"area":null},{"id":"2308.09472","title":"Vision Relation Transformer for Unbiased Scene Graph Generation","created":"2023-08-18","cited_by_count":18,"area":null},{"id":"2103.16086","title":"Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking","created":"2021-03-30","cited_by_count":17,"area":null},{"id":"2110.01209","title":"Learning Structural Representations for Recipe Generation and Food Retrieval","created":"2021-10-04","cited_by_count":17,"area":null},{"id":"2305.15186","title":"SciReviewGen: A Large-scale Dataset for Automatic Literature Review Generation","created":"2023-05-24","cited_by_count":17,"area":null},{"id":"2112.04831","title":"Multimodal Fake News Detection","created":"2021-12-09","cited_by_count":14,"area":null},{"id":"2401.10185","title":"Transfer Learning in Human Activity Recognition: A Survey","created":"2024-01-18","cited_by_count":14,"area":null},{"id":"2408.03006","title":"Dual-path Collaborative Generation Network for Emotional Video Captioning","created":"2024-08-06","cited_by_count":14,"area":null},{"id":"2106.11229","title":"AOMD: An Analogy-aware Approach to Offensive Meme Detection on Social Media","created":"2021-06-21","cited_by_count":13,"area":null},{"id":"2206.01908","title":"Video-based Human-Object Interaction Detection from Tubelet Tokens","created":"2022-06-04","cited_by_count":13,"area":null},{"id":"2101.11911","title":"The Role of Syntactic Planning in Compositional Image Captioning","created":"2021-01-28","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":"2407.03386","title":"Visual Robustness Benchmark for Visual Question Answering (VQA)","created":"2024-07-03","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":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11,"area":null},{"id":"2409.19255","title":"DENEB: A Hallucination-Robust Automatic Evaluation Metric for Image Captioning","created":"2024-09-28","cited_by_count":11,"area":null},{"id":"2412.02071","title":"Progress-Aware Video Frame Captioning","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2501.00113","title":"AltGen: AI-Driven Alt Text Generation for Enhancing EPUB Accessibility","created":"2024-12-30","cited_by_count":11,"area":null},{"id":"2207.14227","title":"Visual Recognition by Request","created":"2022-07-28","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":"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":"2306.05642","title":"Customizing General-Purpose Foundation Models for Medical Report Generation","created":"2023-06-09","cited_by_count":9,"area":null},{"id":"2504.11786","title":"DART: Disease-aware Image-Text Alignment and Self-correcting Re-alignment for Trustworthy Radiology Report Generation","created":"2025-04-16","cited_by_count":9,"area":null},{"id":"2305.06472","title":"ChatGPT-Like Large-Scale Foundation Models for Prognostics and Health Management: A Survey and Roadmaps","created":"2023-05-10","cited_by_count":8,"area":null},{"id":"2108.11912","title":"Similar Scenes arouse Similar Emotions: Parallel Data Augmentation for Stylized Image Captioning","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2203.03195","title":"Unpaired Image Captioning by Image-level Weakly-Supervised Visual Concept Recognition","created":"2022-03-07","cited_by_count":7,"area":null},{"id":"2209.02574","title":"Cross Modal Compression: Towards Human-comprehensible Semantic Compression","created":"2022-09-06","cited_by_count":7,"area":null},{"id":"2212.12249","title":"Do DALL-E and Flamingo Understand Each Other?","created":"2022-12-23","cited_by_count":7,"area":null},{"id":"2307.16236","title":"Synaptic Plasticity Models and Bio-Inspired Unsupervised Deep Learning: A Survey","created":"2023-07-30","cited_by_count":7,"area":null},{"id":"2411.00970","title":"Incremental IVF Index Maintenance for Streaming Vector Search","created":"2024-11-01","cited_by_count":7,"area":null},{"id":"2101.07299","title":"Diagnostic Captioning: A Survey","created":"2021-01-18","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":"2205.09676","title":"Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search","created":"2022-05-19","cited_by_count":6,"area":null},{"id":"2211.15378","title":"Aesthetically Relevant Image Captioning","created":"2022-11-25","cited_by_count":6,"area":null},{"id":"2302.02978","title":"MuG: A Multimodal Classification Benchmark on Game Data with Tabular, Textual, and Visual Fields","created":"2023-02-06","cited_by_count":6,"area":null},{"id":"2307.04643","title":"MultiQG-TI: Towards Question Generation from Multi-modal Sources","created":"2023-07-07","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":"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":"2304.02016","title":"The Multimodal And Modular Ai Chef: Complex Recipe Generation From Imagery","created":"2023-03-20","cited_by_count":5,"area":null},{"id":"2312.04793","title":"User-Aware Prefix-Tuning is a Good Learner for Personalized Image Captioning","created":"2023-12-08","cited_by_count":5,"area":null},{"id":"2408.06662","title":"Bi-directional Contextual Attention for 3D Dense Captioning","created":"2024-08-13","cited_by_count":5,"area":null},{"id":"2501.07496","title":"Aligning First, Then Fusing: A Novel Weakly Supervised Multimodal Violence Detection Method","created":"2025-01-13","cited_by_count":5,"area":null},{"id":"2503.03651","title":"DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles","created":"2025-03-05","cited_by_count":5,"area":null},{"id":"2104.14721","title":"End-to-End Attention-based Image Captioning","created":"2021-04-30","cited_by_count":4,"area":null},{"id":"2107.13114","title":"A Thorough Review on Recent Deep Learning Methodologies for Image Captioning","created":"2021-07-28","cited_by_count":4,"area":null},{"id":"2201.05151","title":"Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning","created":"2022-01-13","cited_by_count":4,"area":null},{"id":"2211.05543","title":"Vis2Mus: Exploring Multimodal Representation Mapping for Controllable Music Generation","created":"2022-11-10","cited_by_count":4,"area":null},{"id":"2301.01224","title":"An Empirical Investigation into the Use of Image Captioning for Automated Software Documentation","created":"2023-01-03","cited_by_count":4,"area":null},{"id":"2309.07623","title":"SwitchGPT: Adapting Large Language Models for Non-Text Outputs","created":"2023-09-14","cited_by_count":4,"area":null},{"id":"2401.07553","title":"Safe Reinforcement Learning with Free-form Natural Language Constraints and Pre-Trained Language Models","created":"2024-01-15","cited_by_count":4,"area":null},{"id":"2405.12648","title":"Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency","created":"2024-05-21","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":"2512.05119","title":"RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering","created":"2025-10-11","cited_by_count":4,"area":null},{"id":"2102.11506","title":"Comparative evaluation of CNN architectures for Image Caption Generation","created":"2021-02-23","cited_by_count":3,"area":null},{"id":"2204.07374","title":"Image Captioning In the Transformer Age","created":"2022-04-15","cited_by_count":3,"area":null},{"id":"2208.02394","title":"End-to-end deep learning for directly estimating grape yield from ground-based imagery","created":"2022-08-04","cited_by_count":3,"area":null},{"id":"2211.14732","title":"Deep representation learning: Fundamentals, Perspectives, Applications, and Open Challenges","created":"2022-11-27","cited_by_count":3,"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":"2409.03945","title":"TropNNC: Structured Neural Network Compression Using Tropical Geometry","created":"2024-09-05","cited_by_count":3,"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":"2204.07476","title":"Guiding Attention using Partial-Order Relationships for Image Captioning","created":"2022-04-15","cited_by_count":2,"area":null},{"id":"2207.01772","title":"Vision-and-Language Pretraining","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2207.09083","title":"Relational Future Captioning Model for Explaining Likely Collisions in Daily Tasks","created":"2022-07-19","cited_by_count":2,"area":null},{"id":"2211.02423","title":"CLSE: Corpus of Linguistically Significant Entities","created":"2022-11-04","cited_by_count":2,"area":null},{"id":"2301.06024","title":"A data science and machine learning approach to continuous analysis of Shakespeare's plays","created":"2023-01-15","cited_by_count":2,"area":null},{"id":"2304.14986","title":"Interpreting Vision and Language Generative Models with Semantic Visual Priors","created":"2023-04-28","cited_by_count":2,"area":null}],"next_cursor":"100"}