{"total":1135,"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":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540,"area":null},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274,"area":null},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230,"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":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156,"area":null},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991,"area":null},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849,"area":null},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819,"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":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745,"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":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649,"area":null},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640,"area":null},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622,"area":null},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616,"area":null},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559,"area":null},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"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":"2204.08387","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","created":"2022-04-18","cited_by_count":485,"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":"2303.11897","title":"TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering","created":"2023-03-21","cited_by_count":428,"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":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2402.07865","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","created":"2024-02-12","cited_by_count":339,"area":null},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329,"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":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","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":"2211.11158","title":"Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification","created":"2022-11-21","cited_by_count":312,"area":null},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311,"area":null},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294,"area":null},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291,"area":null},{"id":"2207.07285","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","created":"2022-07-15","cited_by_count":280,"area":null},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275,"area":null},{"id":"2110.13309","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","created":"2021-10-25","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":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267,"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":"2103.14586","title":"Understanding Robustness of Transformers for Image Classification","created":"2021-03-26","cited_by_count":249,"area":null},{"id":"2402.15852","title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","created":"2024-02-24","cited_by_count":233,"area":null},{"id":"2206.06522","title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","created":"2022-06-13","cited_by_count":230,"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":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224,"area":null},{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224,"area":null},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215,"area":null},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207,"area":null},{"id":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204,"area":null},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203,"area":null},{"id":"2308.02487","title":"Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP","created":"2023-08-04","cited_by_count":201,"area":null},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195,"area":null},{"id":"2112.03109","title":"General Facial Representation Learning in a Visual-Linguistic Manner","created":"2021-12-06","cited_by_count":195,"area":null},{"id":"2202.11742","title":"Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation","created":"2022-02-23","cited_by_count":193,"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":"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":"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":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183,"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":"2203.06486","title":"Chart-to-Text: A Large-Scale Benchmark for Chart Summarization","created":"2022-03-12","cited_by_count":169,"area":null},{"id":"2304.03047","title":"ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments","created":"2023-04-06","cited_by_count":169,"area":null},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166,"area":null},{"id":"2108.00946","title":"StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators","created":"2021-08-02","cited_by_count":164,"area":null},{"id":"2211.14813","title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","created":"2022-11-27","cited_by_count":164,"area":null},{"id":"2310.05694","title":"A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics","created":"2023-10-09","cited_by_count":163,"area":null},{"id":"2210.01055","title":"CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training","created":"2022-10-03","cited_by_count":160,"area":null},{"id":"2210.06044","title":"Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning","created":"2022-10-12","cited_by_count":159,"area":null},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154,"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":"2106.09785","title":"Efficient Self-supervised Vision Transformers for Representation Learning","created":"2021-06-17","cited_by_count":149,"area":null},{"id":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148,"area":null},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146,"area":null},{"id":"2106.03089","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","created":"2021-06-06","cited_by_count":143,"area":null},{"id":"2209.07526","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","created":"2022-09-15","cited_by_count":143,"area":null},{"id":"2212.02623","title":"Unifying Vision, Text, and Layout for Universal Document Processing","created":"2022-12-05","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":"2112.07566","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","created":"2021-12-14","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":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"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":"2308.12213","title":"CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No","created":"2023-08-23","cited_by_count":130,"area":null},{"id":"2108.05015","title":"VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows","created":"2021-08-11","cited_by_count":129,"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":"2112.01522","title":"Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks","created":"2021-12-02","cited_by_count":125,"area":null},{"id":"2104.12836","title":"Multimodal Contrastive Training for Visual Representation Learning","created":"2021-04-26","cited_by_count":124,"area":null},{"id":"2307.12907","title":"GridMM: Grid Memory Map for Vision-and-Language Navigation","created":"2023-07-24","cited_by_count":124,"area":null},{"id":"2212.04385","title":"BEVBert: Multimodal Map Pre-training for Language-guided Navigation","created":"2022-12-08","cited_by_count":122,"area":null},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120,"area":null},{"id":"2106.03331","title":"SelfDoc: Self-Supervised Document Representation Learning","created":"2021-06-07","cited_by_count":117,"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":"2307.15644","title":"Scaling Data Generation in Vision-and-Language Navigation","created":"2023-07-28","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}],"next_cursor":"100"}