{"total":316,"rows":[{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601,"area":null},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744,"area":null},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710,"area":null},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577,"area":null},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531,"area":null},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518,"area":null},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421,"area":null},{"id":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412,"area":null},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311,"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":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2109.05014","title":"An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA","created":"2021-09-10","cited_by_count":301,"area":null},{"id":"2103.01913","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","created":"2021-03-02","cited_by_count":287,"area":null},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2204.03610","title":"Unified Contrastive Learning in Image-Text-Label Space","created":"2022-04-07","cited_by_count":194,"area":null},{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189,"area":null},{"id":"2111.12681","title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","created":"2021-11-24","cited_by_count":188,"area":null},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184,"area":null},{"id":"2111.11431","title":"RedCaps: web-curated image-text data created by the people, for the people","created":"2021-11-22","cited_by_count":180,"area":null},{"id":"2104.06039","title":"MultiModalQA: Complex Question Answering over Text, Tables and Images","created":"2021-04-13","cited_by_count":179,"area":null},{"id":"2203.07303","title":"All in One: Exploring Unified Video-Language Pre-training","created":"2022-03-14","cited_by_count":171,"area":null},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146,"area":null},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2201.11114","title":"Natural Language Descriptions of Deep Visual Features","created":"2022-01-26","cited_by_count":137,"area":null},{"id":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133,"area":null},{"id":"2111.13792","title":"LAFITE: Towards Language-Free Training for Text-to-Image Generation","created":"2021-11-27","cited_by_count":128,"area":null},{"id":"2102.12060","title":"Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing","created":"2021-02-24","cited_by_count":126,"area":null},{"id":"2306.04387","title":"M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning","created":"2023-06-07","cited_by_count":126,"area":null},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120,"area":null},{"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":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114,"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":"2212.10773","title":"MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning","created":"2022-12-21","cited_by_count":109,"area":null},{"id":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106,"area":null},{"id":"2402.19474","title":"The All-Seeing Project V2: Towards General Relation Comprehension of the Open World","created":"2024-02-29","cited_by_count":90,"area":null},{"id":"2401.08743","title":"MMToM-QA: Multimodal Theory of Mind Question Answering","created":"2024-01-16","cited_by_count":85,"area":null},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85,"area":null},{"id":"2105.03761","title":"e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks","created":"2021-05-08","cited_by_count":84,"area":null},{"id":"2101.05307","title":"Explainability of deep vision-based autonomous driving systems: Review and challenges","created":"2021-01-13","cited_by_count":80,"area":null},{"id":"2102.03315","title":"Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge","created":"2021-02-05","cited_by_count":80,"area":null},{"id":"2303.07274","title":"Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images","created":"2023-03-13","cited_by_count":80,"area":null},{"id":"2106.00245","title":"Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models","created":"2021-06-01","cited_by_count":75,"area":null},{"id":"2206.07160","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","created":"2022-06-14","cited_by_count":73,"area":null},{"id":"2112.00061","title":"Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources","created":"2021-11-30","cited_by_count":71,"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":"2206.09059","title":"CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks","created":"2022-06-18","cited_by_count":68,"area":null},{"id":"2402.00126","title":"Common Sense Reasoning for Deepfake Detection","created":"2024-01-31","cited_by_count":65,"area":null},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62,"area":null},{"id":"2104.04167","title":"The Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation","created":"2021-04-09","cited_by_count":61,"area":null},{"id":"2203.05081","title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","created":"2022-03-09","cited_by_count":60,"area":null},{"id":"2308.12305","title":"FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning","created":"2023-08-21","cited_by_count":60,"area":null},{"id":"2109.06860","title":"Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning","created":"2021-09-14","cited_by_count":59,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"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":"2203.17247","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","created":"2022-03-30","cited_by_count":53,"area":null},{"id":"2104.08666","title":"Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models","created":"2021-04-18","cited_by_count":52,"area":null},{"id":"2401.01523","title":"GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse","created":"2024-01-03","cited_by_count":52,"area":null},{"id":"2406.07546","title":"Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?","created":"2024-06-11","cited_by_count":52,"area":null},{"id":"2302.10307","title":"ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency","created":"2023-01-31","cited_by_count":51,"area":null},{"id":"2106.00188","title":"PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World","created":"2021-06-01","cited_by_count":47,"area":null},{"id":"2104.00743","title":"Towards General Purpose Vision Systems","created":"2021-04-01","cited_by_count":46,"area":null},{"id":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46,"area":null},{"id":"2104.11832","title":"Playing Lottery Tickets with Vision and Language","created":"2021-04-23","cited_by_count":45,"area":null},{"id":"2205.15509","title":"ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts","created":"2022-05-31","cited_by_count":45,"area":null},{"id":"2108.01453","title":"PhotoChat: A Human-Human Dialogue Dataset with Photo Sharing Behavior for Joint Image-Text Modeling","created":"2021-07-06","cited_by_count":43,"area":null},{"id":"2104.12871","title":"Why AI is Harder Than We Think","created":"2021-04-26","cited_by_count":41,"area":null},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"id":"2210.10045","title":"SafeText: A Benchmark for Exploring Physical Safety in Language Models","created":"2022-10-18","cited_by_count":41,"area":null},{"id":"2205.01850","title":"Visual Commonsense in Pretrained Unimodal and Multimodal Models","created":"2022-05-04","cited_by_count":39,"area":null},{"id":"2410.05352","title":"Recent Advances of Multimodal Continual Learning: A Comprehensive Survey","created":"2024-10-07","cited_by_count":39,"area":null},{"id":"2201.12438","title":"Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey","created":"2022-01-28","cited_by_count":38,"area":null},{"id":"2111.08919","title":"EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching","created":"2021-11-17","cited_by_count":36,"area":null},{"id":"2203.16531","title":"Understanding 3D Object Articulation in Internet Videos","created":"2022-03-30","cited_by_count":36,"area":null},{"id":"2212.03954","title":"Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning","created":"2022-12-07","cited_by_count":36,"area":null},{"id":"2409.10917","title":"AMEGO: Active Memory from long EGOcentric videos","created":"2024-09-17","cited_by_count":36,"area":null},{"id":"2103.12989","title":"Relation-aware Instance Refinement for Weakly Supervised Visual Grounding","created":"2021-03-24","cited_by_count":35,"area":null},{"id":"2108.11544","title":"Vision-Language Navigation: A Survey and Taxonomy","created":"2021-08-26","cited_by_count":34,"area":null},{"id":"2112.05136","title":"PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning","created":"2021-12-09","cited_by_count":34,"area":null},{"id":"2203.08481","title":"Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding","created":"2022-03-16","cited_by_count":33,"area":null},{"id":"2406.07544","title":"Situational Awareness Matters in 3D Vision Language Reasoning","created":"2024-06-11","cited_by_count":33,"area":null},{"id":"2109.02401","title":"Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization","created":"2021-09-06","cited_by_count":32,"area":null},{"id":"2201.05729","title":"CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks","created":"2022-01-15","cited_by_count":32,"area":null},{"id":"2207.08150","title":"FashionViL: Fashion-Focused Vision-and-Language Representation Learning","created":"2022-07-17","cited_by_count":32,"area":null},{"id":"2302.12248","title":"Learning Visual Representations via Language-Guided Sampling","created":"2023-02-23","cited_by_count":32,"area":null},{"id":"2601.09668","title":"STEP3-VL-10B Technical Report","created":"2026-01-14","cited_by_count":32,"area":null},{"id":"2103.11072","title":"Local Interpretations for Explainable Natural Language Processing: A Survey","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2110.08020","title":"Multimodal Emotion-Cause Pair Extraction in Conversations","created":"2021-10-15","cited_by_count":31,"area":null},{"id":"2101.04640","title":"Dimensions of Commonsense Knowledge","created":"2021-01-12","cited_by_count":29,"area":null},{"id":"2212.06202","title":"Doubly Right Object Recognition: A Why Prompt for Visual Rationales","created":"2022-12-12","cited_by_count":29,"area":null},{"id":"2312.16602","title":"Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey","created":"2023-12-27","cited_by_count":29,"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":"2312.09818","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","created":"2023-12-15","cited_by_count":28,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2202.02838","title":"Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment","created":"2022-02-06","cited_by_count":27,"area":null},{"id":"2204.08121","title":"End-to-end Dense Video Captioning as Sequence Generation","created":"2022-04-18","cited_by_count":27,"area":null},{"id":"2106.10446","title":"Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering","created":"2021-06-19","cited_by_count":26,"area":null}],"next_cursor":"100"}