{"total":1065,"rows":[{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332,"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":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819,"area":null},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804,"area":null},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781,"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":"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":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511,"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":"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":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437,"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":"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":"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":"2106.02636","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":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275,"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":"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":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203,"area":null},{"id":"2305.08275","title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","created":"2023-05-14","cited_by_count":202,"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":"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":"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":"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":"2204.13258","title":"Cross-modal Memory Networks for Radiology Report Generation","created":"2022-04-28","cited_by_count":185,"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":"2104.06039","title":"MultiModalQA: Complex Question Answering over Text, Tables and Images","created":"2021-04-13","cited_by_count":179,"area":null},{"id":"2103.15025","title":"On Hallucination and Predictive Uncertainty in Conditional Language Generation","created":"2021-03-28","cited_by_count":176,"area":null},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","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":"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":"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":"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":"2101.01368","title":"Similarity Reasoning and Filtration for Image-Text Matching","created":"2021-01-05","cited_by_count":121,"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":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"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":"2108.08728","title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","created":"2021-08-19","cited_by_count":114,"area":null},{"id":"2110.14378","title":"Towards artificial general intelligence via a multimodal foundation model","created":"2021-10-27","cited_by_count":112,"area":null},{"id":"2307.05356","title":"VisText: A Benchmark for Semantically Rich Chart Captioning","created":"2023-06-28","cited_by_count":112,"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":"2101.07396","title":"ArtEmis: Affective Language for Visual Art","created":"2021-01-19","cited_by_count":104,"area":null},{"id":"2105.13381","title":"Recent advances and clinical applications of deep learning in medical image analysis","created":"2021-05-27","cited_by_count":104,"area":null},{"id":"2304.02211","title":"METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens","created":"2023-04-05","cited_by_count":101,"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":"2306.08640","title":"AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn","created":"2023-06-14","cited_by_count":97,"area":null},{"id":"2106.09707","title":"Learning to Predict Visual Attributes in the Wild","created":"2021-06-17","cited_by_count":96,"area":null},{"id":"2107.12309","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","created":"2021-07-26","cited_by_count":96,"area":null},{"id":"2202.05306","title":"Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks","created":"2022-02-10","cited_by_count":95,"area":null},{"id":"2111.10056","title":"Medical Visual Question Answering: A Survey","created":"2021-11-19","cited_by_count":93,"area":null},{"id":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91,"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":"2304.04514","title":"DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment","created":"2023-04-10","cited_by_count":90,"area":null},{"id":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89,"area":null},{"id":"2108.02388","title":"TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding","created":"2021-08-05","cited_by_count":86,"area":null},{"id":"2401.07314","title":"MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigation","created":"2024-01-14","cited_by_count":86,"area":null},{"id":"2211.08545","title":"MapQA: A Dataset for Question Answering on Choropleth Maps","created":"2022-11-15","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":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84,"area":null},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84,"area":null},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"2209.15323","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","created":"2022-09-30","cited_by_count":82,"area":null},{"id":"2301.02508","title":"End-to-End 3D Dense Captioning with Vote2Cap-DETR","created":"2023-01-06","cited_by_count":78,"area":null},{"id":"2303.12112","title":"Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation","created":"2023-03-21","cited_by_count":78,"area":null},{"id":"2204.09868","title":"Exploring a Fine-Grained Multiscale Method for Cross-Modal Remote Sensing Image Retrieval","created":"2022-04-21","cited_by_count":77,"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":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2209.01540","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","created":"2022-09-04","cited_by_count":74,"area":null},{"id":"2109.04448","title":"Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers","created":"2021-09-09","cited_by_count":72,"area":null},{"id":"2109.06082","title":"xGQA: Cross-Lingual Visual Question Answering","created":"2021-09-13","cited_by_count":72,"area":null},{"id":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2101.06462","title":"Dual-Level Collaborative Transformer for Image Captioning","created":"2021-01-16","cited_by_count":71,"area":null},{"id":"2104.03149","title":"Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering","created":"2021-04-07","cited_by_count":71,"area":null},{"id":"2101.11796","title":"DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents","created":"2021-01-28","cited_by_count":70,"area":null},{"id":"2106.07876","title":"Vision-Language Navigation with Random Environmental Mixup","created":"2021-06-15","cited_by_count":70,"area":null},{"id":"2205.13115","title":"Fine-grained Image Captioning with CLIP Reward","created":"2022-05-26","cited_by_count":69,"area":null},{"id":"2104.03059","title":"Differentiable Patch Selection for Image Recognition","created":"2021-04-07","cited_by_count":68,"area":null},{"id":"2112.06197","title":"Video as Conditional Graph Hierarchy for Multi-Granular Question Answering","created":"2021-12-12","cited_by_count":68,"area":null},{"id":"2112.15009","title":"Knowledge Matters: Radiology Report Generation with General and Specific Knowledge","created":"2021-12-30","cited_by_count":68,"area":null},{"id":"2304.01816","title":"Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation","created":"2023-04-04","cited_by_count":68,"area":null},{"id":"2305.16103","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","created":"2023-05-25","cited_by_count":66,"area":null},{"id":"2205.01883","title":"All You May Need for VQA are Image Captions","created":"2022-05-04","cited_by_count":65,"area":null},{"id":"2102.00529","title":"Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers","created":"2021-01-31","cited_by_count":64,"area":null},{"id":"2111.12872","title":"Less is More: Generating Grounded Navigation Instructions from Landmarks","created":"2021-11-25","cited_by_count":64,"area":null},{"id":"2203.14263","title":"A General Survey on Attention Mechanisms in Deep Learning","created":"2022-03-27","cited_by_count":64,"area":null},{"id":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63,"area":null},{"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":"2107.02331","title":"Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering","created":"2021-07-06","cited_by_count":62,"area":null},{"id":"2306.11345","title":"KiUT: Knowledge-injected U-Transformer for Radiology Report Generation","created":"2023-06-20","cited_by_count":62,"area":null}],"next_cursor":"100"}