{"total":1502,"rows":[{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080,"area":null},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619,"area":null},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216,"area":null},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177,"area":null},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766,"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":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717,"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":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708,"area":null},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680,"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":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532,"area":null},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531,"area":null},{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512,"area":null},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501,"area":null},{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491,"area":null},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484,"area":null},{"id":"2102.09542","title":"SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering","created":"2021-02-18","cited_by_count":449,"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":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371,"area":null},{"id":"2102.01017","title":"Measuring and Improving Consistency in Pretrained Language Models","created":"2021-02-01","cited_by_count":364,"area":null},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346,"area":null},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321,"area":null},{"id":"2103.15679","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","created":"2021-03-29","cited_by_count":320,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"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":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","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":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297,"area":null},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294,"area":null},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291,"area":null},{"id":"2111.11326","title":"DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion","created":"2021-11-22","cited_by_count":291,"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":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275,"area":null},{"id":"2306.17107","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","created":"2023-06-29","cited_by_count":274,"area":null},{"id":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271,"area":null},{"id":"2111.02387","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","created":"2021-11-03","cited_by_count":271,"area":null},{"id":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267,"area":null},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267,"area":null},{"id":"2306.05425","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","created":"2023-06-08","cited_by_count":267,"area":null},{"id":"2203.15332","title":"Balanced Multimodal Learning via On-the-fly Gradient Modulation","created":"2022-03-29","cited_by_count":264,"area":null},{"id":"2305.14836","title":"NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario","created":"2023-05-24","cited_by_count":262,"area":null},{"id":"2108.04024","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","created":"2021-08-09","cited_by_count":251,"area":null},{"id":"2309.14181","title":"Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision","created":"2023-09-25","cited_by_count":249,"area":null},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229,"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":"2212.10450","title":"Is GPT-3 a Good Data Annotator?","created":"2022-12-20","cited_by_count":208,"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":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191,"area":null},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190,"area":null},{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189,"area":null},{"id":"2205.12005","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","created":"2022-05-24","cited_by_count":187,"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":"2303.15247","title":"Zero-Shot Composed Image Retrieval with Textual Inversion","created":"2023-03-27","cited_by_count":176,"area":null},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169,"area":null},{"id":"2307.04087","title":"SVIT: Scaling up Visual Instruction Tuning","created":"2023-07-09","cited_by_count":162,"area":null},{"id":"2311.17842","title":"Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning","created":"2023-11-29","cited_by_count":161,"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":"2303.02151","title":"Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners","created":"2023-03-03","cited_by_count":152,"area":null},{"id":"2311.06783","title":"Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models","created":"2023-11-12","cited_by_count":152,"area":null},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151,"area":null},{"id":"2403.09227","title":"BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation","created":"2024-03-14","cited_by_count":148,"area":null},{"id":"2411.00816","title":"CycleResearcher: Improving Automated Research via Automated Review","created":"2024-10-28","cited_by_count":148,"area":null},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146,"area":null},{"id":"2311.07574","title":"To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning","created":"2023-11-13","cited_by_count":144,"area":null},{"id":"2204.08790","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","created":"2022-04-19","cited_by_count":141,"area":null},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"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":"2108.09105","title":"Airbert: In-domain Pretraining for Vision-and-Language Navigation","created":"2021-08-20","cited_by_count":130,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2308.08769","title":"Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes","created":"2023-08-17","cited_by_count":129,"area":null},{"id":"2309.17428","title":"CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets","created":"2023-09-29","cited_by_count":129,"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":"2203.15086","title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval","created":"2022-03-28","cited_by_count":128,"area":null},{"id":"2112.08614","title":"KAT: A Knowledge Augmented Transformer for Vision-and-Language","created":"2021-12-16","cited_by_count":126,"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":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120,"area":null},{"id":"2108.03353","title":"Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning","created":"2021-08-07","cited_by_count":120,"area":null},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"area":null},{"id":"2205.10747","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","created":"2022-05-22","cited_by_count":117,"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":"2308.01907","title":"The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World","created":"2023-08-03","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":"2212.04994","title":"Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning","created":"2022-12-09","cited_by_count":115,"area":null},{"id":"2212.10846","title":"From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models","created":"2022-12-21","cited_by_count":115,"area":null},{"id":"2203.07190","title":"CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment","created":"2022-03-14","cited_by_count":113,"area":null},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113,"area":null},{"id":"2212.08037","title":"Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models","created":"2022-12-15","cited_by_count":112,"area":null},{"id":"2306.05179","title":"M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models","created":"2023-06-08","cited_by_count":110,"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":"2109.00590","title":"WebQA: Multihop and Multimodal QA","created":"2021-09-01","cited_by_count":109,"area":null},{"id":"2211.09699","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","created":"2022-11-15","cited_by_count":104,"area":null},{"id":"2310.09291","title":"Vision-by-Language for Training-Free Compositional Image Retrieval","created":"2023-10-13","cited_by_count":103,"area":null},{"id":"2312.11556","title":"StarVector: Generating Scalable Vector Graphics Code from Images and Text","created":"2023-12-17","cited_by_count":102,"area":null}],"next_cursor":"100"}