{"total":544,"rows":[{"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":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540,"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":"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":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614,"area":null},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613,"area":null},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2211.13227","title":"Paint by Example: Exemplar-based Image Editing with Diffusion Models","created":"2022-11-23","cited_by_count":489,"area":"diffusion"},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482,"area":null},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410,"area":null},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381,"area":null},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380,"area":null},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349,"area":null},{"id":"2306.09683","title":"Scaling Open-Vocabulary Object Detection","created":"2023-06-16","cited_by_count":343,"area":"mllm"},{"id":"2301.07525","title":"OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation","created":"2023-01-18","cited_by_count":326,"area":null},{"id":"2302.10663","title":"RealFusion: 360{\\deg} Reconstruction of Any Object from a Single Image","created":"2023-02-21","cited_by_count":306,"area":null},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305,"area":null},{"id":"2202.01197","title":"VOS: Learning What You Don't Know by Virtual Outlier Synthesis","created":"2022-02-02","cited_by_count":300,"area":null},{"id":"2111.08276","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","created":"2021-11-16","cited_by_count":256,"area":"mllm"},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253,"area":null},{"id":"2212.06909","title":"Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting","created":"2022-12-13","cited_by_count":233,"area":"diffusion"},{"id":"2405.01483","title":"MANTIS: Interleaved Multi-Image Instruction Tuning","created":"2024-05-02","cited_by_count":216,"area":"mllm"},{"id":"2307.11410","title":"Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning","created":"2023-07-21","cited_by_count":191,"area":"diffusion"},{"id":"2301.11320","title":"Cut and Learn for Unsupervised Object Detection and Instance Segmentation","created":"2023-01-26","cited_by_count":187,"area":null},{"id":"2209.09407","title":"DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection","created":"2022-09-20","cited_by_count":176,"area":null},{"id":"2204.01075","title":"Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI","created":"2022-04-03","cited_by_count":171,"area":null},{"id":"2309.02591","title":"Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning","created":"2023-09-05","cited_by_count":170,"area":"mllm"},{"id":"2309.03895","title":"InstructDiffusion: A Generalist Modeling Interface for Vision Tasks","created":"2023-09-07","cited_by_count":164,"area":null},{"id":"2102.06583","title":"Reviving Iterative Training with Mask Guidance for Interactive Segmentation","created":"2021-02-12","cited_by_count":163,"area":null},{"id":"2202.06675","title":"Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?","created":"2022-02-14","cited_by_count":155,"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":"2207.03482","title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection","created":"2022-07-07","cited_by_count":146,"area":null},{"id":"2301.01795","title":"PACO: Parts and Attributes of Common Objects","created":"2023-01-04","cited_by_count":146,"area":null},{"id":"2211.06956","title":"Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding","created":"2022-11-13","cited_by_count":144,"area":"diffusion"},{"id":"2402.05935","title":"SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models","created":"2024-02-08","cited_by_count":131,"area":"mllm"},{"id":"2111.12085","title":"UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling","created":"2021-11-23","cited_by_count":122,"area":"mllm"},{"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":"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":"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":"2106.09788","title":"Guided Integrated Gradients: An Adaptive Path Method for Removing Noise","created":"2021-06-17","cited_by_count":102,"area":null},{"id":"2206.09541","title":"DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations","created":"2022-06-20","cited_by_count":102,"area":null},{"id":"2305.18279","title":"Contextual Object Detection with Multimodal Large Language Models","created":"2023-05-29","cited_by_count":100,"area":"mllm"},{"id":"2104.11892","title":"A Survey of Modern Deep Learning based Object Detection Models","created":"2021-04-24","cited_by_count":98,"area":null},{"id":"2203.15143","title":"Towards End-to-End Unified Scene Text Detection and Layout Analysis","created":"2022-03-28","cited_by_count":97,"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":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96,"area":null},{"id":"2204.01694","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","created":"2022-04-04","cited_by_count":95,"area":null},{"id":"2211.05776","title":"High-Quality Entity Segmentation","created":"2022-11-10","cited_by_count":93,"area":null},{"id":"2301.02280","title":"Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training","created":"2023-01-05","cited_by_count":91,"area":"mllm"},{"id":"2207.10062","title":"DataPerf: Benchmarks for Data-Centric AI Development","created":"2022-07-20","cited_by_count":90,"area":null},{"id":"2201.05078","title":"CLIP-Event: Connecting Text and Images with Event Structures","created":"2022-01-13","cited_by_count":86,"area":"mllm"},{"id":"2303.05657","title":"Tag2Text: Guiding Vision-Language Model via Image Tagging","created":"2023-03-10","cited_by_count":86,"area":"mllm"},{"id":"2111.11430","title":"Class-agnostic Object Detection with Multi-modal Transformer","created":"2021-11-22","cited_by_count":85,"area":null},{"id":"2307.07961","title":"EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes","created":"2023-07-16","cited_by_count":82,"area":null},{"id":"2107.00420","title":"CBNet: A Composite Backbone Network Architecture for Object Detection","created":"2021-07-01","cited_by_count":77,"area":null},{"id":"2112.10961","title":"Nonlinear Transform Source-Channel Coding for Semantic Communications","created":"2021-12-21","cited_by_count":76,"area":null},{"id":"2205.13775","title":"A Survey on Long-Tailed Visual Recognition","created":"2022-05-27","cited_by_count":75,"area":null},{"id":"2208.13753","title":"Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis","created":"2022-08-29","cited_by_count":75,"area":"diffusion"},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73,"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":"2210.07688","title":"Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training","created":"2022-10-14","cited_by_count":72,"area":"mllm"},{"id":"2310.15200","title":"Open-Set Image Tagging with Multi-Grained Text Supervision","created":"2023-10-23","cited_by_count":67,"area":null},{"id":"2209.12118","title":"BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video","created":"2022-09-25","cited_by_count":66,"area":null},{"id":"2109.02227","title":"Learning to Generate Scene Graph from Natural Language Supervision","created":"2021-09-06","cited_by_count":64,"area":null},{"id":"2106.14490","title":"Making Images Real Again: A Comprehensive Survey on Deep Image Composition","created":"2021-06-28","cited_by_count":63,"area":null},{"id":"2303.11749","title":"Detecting Everything in the Open World: Towards Universal Object Detection","created":"2023-03-21","cited_by_count":62,"area":null},{"id":"2212.00653","title":"Hyperbolic Contrastive Learning for Visual Representations beyond Objects","created":"2022-12-01","cited_by_count":61,"area":null},{"id":"2308.04657","title":"Which Tokens to Use? Investigating Token Reduction in Vision Transformers","created":"2023-08-09","cited_by_count":60,"area":"inference"},{"id":"2203.03860","title":"Weakly Supervised Semantic Segmentation using Out-of-Distribution Data","created":"2022-03-08","cited_by_count":58,"area":null},{"id":"2309.00035","title":"FACET: Fairness in Computer Vision Evaluation Benchmark","created":"2023-08-31","cited_by_count":58,"area":null},{"id":"2104.12673","title":"Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data","created":"2021-04-26","cited_by_count":55,"area":null},{"id":"2209.01814","title":"RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection","created":"2022-09-05","cited_by_count":55,"area":null},{"id":"2103.13318","title":"Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types","created":"2021-03-24","cited_by_count":54,"area":null},{"id":"2206.06363","title":"Discovering Object Masks with Transformers for Unsupervised Semantic Segmentation","created":"2022-06-13","cited_by_count":54,"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":"2109.13228","title":"PASS: An ImageNet replacement for self-supervised pretraining without humans","created":"2021-09-27","cited_by_count":51,"area":null},{"id":"2106.05967","title":"Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations","created":"2021-06-10","cited_by_count":48,"area":null},{"id":"2405.14828","title":"Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Models","created":"2024-05-23","cited_by_count":48,"area":"diffusion"},{"id":"2412.09596","title":"InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions","created":"2024-12-12","cited_by_count":48,"area":"mllm"},{"id":"2201.02593","title":"Equalized Focal Loss for Dense Long-Tailed Object Detection","created":"2022-01-07","cited_by_count":46,"area":null},{"id":"2305.11019","title":"Annotation-free Audio-Visual Segmentation","created":"2023-05-18","cited_by_count":46,"area":null},{"id":"2104.07787","title":"Rethinking Text Line Recognition Models","created":"2021-04-15","cited_by_count":45,"area":null},{"id":"2106.00168","title":"Rethinking Pseudo Labels for Semi-Supervised Object Detection","created":"2021-06-01","cited_by_count":45,"area":null},{"id":"2307.08723","title":"Revisiting Scene Text Recognition: A Data Perspective","created":"2023-07-17","cited_by_count":45,"area":null},{"id":"2308.09351","title":"RLIPv2: Fast Scaling of Relational Language-Image Pre-training","created":"2023-08-18","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":"2201.12944","title":"Deep Learning Approaches on Image Captioning: A Review","created":"2022-01-31","cited_by_count":43,"area":"mllm"},{"id":"2308.10040","title":"ControlCom: Controllable Image Composition using Diffusion Model","created":"2023-08-19","cited_by_count":43,"area":"diffusion"},{"id":"2112.05230","title":"Injecting Semantic Concepts into End-to-End Image Captioning","created":"2021-12-09","cited_by_count":41,"area":null},{"id":"2210.17400","title":"Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation","created":"2022-10-31","cited_by_count":41,"area":null},{"id":"2306.00956","title":"The ObjectFolder Benchmark: Multisensory Learning with Neural and Real Objects","created":"2023-06-01","cited_by_count":41,"area":null},{"id":"2203.07436","title":"SuperAnimal pretrained pose estimation models for behavioral analysis","created":"2022-03-14","cited_by_count":39,"area":null},{"id":"2206.04055","title":"Gradient Obfuscation Gives a False Sense of Security in Federated Learning","created":"2022-06-08","cited_by_count":39,"area":null},{"id":"2206.09191","title":"Gender Artifacts in Visual Datasets","created":"2022-06-18","cited_by_count":38,"area":null},{"id":"2309.03696","title":"Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory","created":"2023-09-07","cited_by_count":38,"area":null},{"id":"2312.15540","title":"Amodal Completion via Progressive Mixed Context Diffusion","created":"2023-12-24","cited_by_count":38,"area":null},{"id":"2406.01920","title":"CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models","created":"2024-06-04","cited_by_count":38,"area":"mllm"},{"id":"2505.00788","title":"SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models","created":"2025-05-01","cited_by_count":38,"area":"lr"}],"next_cursor":"100"}