{"list":"other","total":73,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"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},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2412.10302","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","created":"2024-12-13","cited_by_count":572},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"1904.10151","title":"REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments","created":"2019-04-23","cited_by_count":333},{"id":"1312.4659","title":"DeepPose: Human Pose Estimation via Deep Neural Networks","created":"2013-12-17","cited_by_count":305},{"id":"1811.12354","title":"Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments","created":"2018-11-29","cited_by_count":239},{"id":"2403.09611","title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","created":"2024-03-14","cited_by_count":232},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209},{"id":"2402.11684","title":"ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models","created":"2024-02-18","cited_by_count":205},{"id":"2003.08813","title":"Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation","created":"2020-03-19","cited_by_count":204},{"id":"1903.06473","title":"DeepHuman: 3D Human Reconstruction from a Single Image","created":"2019-03-15","cited_by_count":182},{"id":"2410.07073","title":"Pixtral 12B","created":"2024-10-09","cited_by_count":179},{"id":"2209.09407","title":"DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection","created":"2022-09-20","cited_by_count":176},{"id":"1704.01719","title":"Beyond triplet loss: a deep quadruplet network for person re-identification","created":"2017-04-06","cited_by_count":172},{"id":"2405.20797","title":"Ovis: Structural Embedding Alignment for Multimodal Large Language Model","created":"2024-05-31","cited_by_count":169},{"id":"1604.02531","title":"Person Re-identification in the Wild","created":"2016-04-09","cited_by_count":157},{"id":"2410.05993","title":"Aria: An Open Multimodal Native Mixture-of-Experts Model","created":"2024-10-08","cited_by_count":138},{"id":"2405.10300","title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","created":"2024-05-16","cited_by_count":122},{"id":"2302.13996","title":"Aligning Bag of Regions for Open-Vocabulary Object Detection","created":"2023-02-27","cited_by_count":119},{"id":"2404.13013","title":"Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models","created":"2024-04-19","cited_by_count":119},{"id":"2008.01187","title":"PhraseCut: Language-based Image Segmentation in the Wild","created":"2020-08-03","cited_by_count":116},{"id":"1611.08481","title":"GuessWhat?! Visual object discovery through multi-modal dialogue","created":"2016-11-23","cited_by_count":113},{"id":"1909.07072","title":"A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension","created":"2019-09-16","cited_by_count":111},{"id":"1909.08164","title":"Dynamic Graph Attention for Referring Expression Comprehension","created":"2019-09-18","cited_by_count":111},{"id":"2304.04269","title":"HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation","created":"2023-04-09","cited_by_count":105},{"id":"2310.12978","title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","created":"2023-10-19","cited_by_count":104},{"id":"2006.09920","title":"Contrastive Learning for Weakly Supervised Phrase Grounding","created":"2020-06-17","cited_by_count":102},{"id":"2404.07973","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","created":"2024-04-11","cited_by_count":97},{"id":"2303.17602","title":"Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks","created":"2023-03-30","cited_by_count":96},{"id":"2403.14610","title":"T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy","created":"2024-03-21","cited_by_count":94},{"id":"2411.14347","title":"DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding","created":"2024-11-21","cited_by_count":89},{"id":"2302.03665","title":"HumanMAC: Masked Motion Completion for Human Motion Prediction","created":"2023-02-07","cited_by_count":81},{"id":"2007.09554","title":"Referring Expression Comprehension: A Survey of Methods and Datasets","created":"2020-07-19","cited_by_count":79},{"id":"2409.20566","title":"MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning","created":"2024-09-30","cited_by_count":76},{"id":"1901.00850","title":"CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions","created":"2019-01-03","cited_by_count":73},{"id":"2501.14818","title":"Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models","created":"2025-01-20","cited_by_count":70},{"id":"2303.02760","title":"Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes","created":"2023-03-05","cited_by_count":68},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59},{"id":"2406.16866","title":"Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Models","created":"2024-06-24","cited_by_count":53},{"id":"1903.11649","title":"Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment","created":"2019-03-27","cited_by_count":51},{"id":"2003.00403","title":"Cops-Ref: A new Dataset and Task on Compositional Referring Expression Comprehension","created":"2020-03-01","cited_by_count":50},{"id":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38},{"id":"2311.14552","title":"Griffon: Spelling out All Object Locations at Any Granularity with Large Language Models","created":"2023-11-24","cited_by_count":31},{"id":"2411.18363","title":"ChatRex: Taming Multimodal LLM for Joint Perception and Understanding","created":"2024-11-27","cited_by_count":30},{"id":"2403.09333","title":"Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring","created":"2024-03-14","cited_by_count":29},{"id":"2206.08172","title":"RefCrowd: Grounding the Target in Crowd with Referring Expressions","created":"2022-06-16","cited_by_count":2}],"next_cursor":null}