{"list":"other","total":81,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"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":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"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},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"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},{"id":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455},{"id":"1908.06066","title":"Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training","created":"2019-08-16","cited_by_count":451},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"2006.06195","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","created":"2020-06-11","cited_by_count":327},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302},{"id":"2305.04790","title":"MultiModal-GPT: A Vision and Language Model for Dialogue with Humans","created":"2023-05-08","cited_by_count":255},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"2306.07207","title":"Valley: Video Assistant with Large Language model Enhanced abilitY","created":"2023-06-12","cited_by_count":234},{"id":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"id":"2006.16934","title":"ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph","created":"2020-06-30","cited_by_count":211},{"id":"2304.06939","title":"Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text","created":"2023-04-14","cited_by_count":208},{"id":"2312.00784","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","created":"2023-12-01","cited_by_count":161},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154},{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153},{"id":"2408.15998","title":"Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders","created":"2024-08-28","cited_by_count":139},{"id":"2406.19389","title":"OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding","created":"2024-06-27","cited_by_count":127},{"id":"2407.11325","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","created":"2024-07-16","cited_by_count":127},{"id":"2407.15841","title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","created":"2024-07-22","cited_by_count":125},{"id":"2212.00280","title":"GRiT: A Generative Region-to-text Transformer for Object Understanding","created":"2022-12-01","cited_by_count":121},{"id":"2404.13013","title":"Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models","created":"2024-04-19","cited_by_count":119},{"id":"2001.06891","title":"Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences","created":"2020-01-19","cited_by_count":118},{"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},{"id":"2401.06071","title":"GroundingGPT:Language Enhanced Multi-modal Grounding Model","created":"2024-01-11","cited_by_count":101},{"id":"2402.19474","title":"The All-Seeing Project V2: Towards General Relation Comprehension of the Open World","created":"2024-02-29","cited_by_count":90},{"id":"2011.05049","title":"Human-centric Spatio-Temporal Video Grounding With Visual Transformers","created":"2020-11-10","cited_by_count":85},{"id":"2005.00214","title":"The AVA-Kinetics Localized Human Actions Video Dataset","created":"2020-05-01","cited_by_count":82},{"id":"2304.03752","title":"V3Det: Vast Vocabulary Visual Detection Dataset","created":"2023-04-07","cited_by_count":81},{"id":"2311.11860","title":"LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge","created":"2023-11-20","cited_by_count":81},{"id":"1812.06587","title":"Grounded Video Description","created":"2018-12-17","cited_by_count":78},{"id":"1612.09542","title":"A Joint Speaker-Listener-Reinforcer Model for Referring Expressions","created":"2016-12-30","cited_by_count":74},{"id":"2403.02330","title":"RegionGPT: Towards Region Understanding Vision Language Model","created":"2024-03-04","cited_by_count":71},{"id":"2402.14683","title":"Visual Hallucinations of Multi-modal Large Language Models","created":"2024-02-22","cited_by_count":68},{"id":"2307.09474","title":"ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning","created":"2023-07-18","cited_by_count":65},{"id":"2403.02325","title":"Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training","created":"2024-03-04","cited_by_count":64},{"id":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63},{"id":"2312.12423","title":"Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model","created":"2023-12-19","cited_by_count":53},{"id":"2205.14895","title":"From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering","created":"2022-05-30","cited_by_count":51},{"id":"2312.00589","title":"Merlin:Empowering Multimodal LLMs with Foresight Minds","created":"2023-11-30","cited_by_count":46},{"id":"2304.01715","title":"Towards Open-Vocabulary Video Instance Segmentation","created":"2023-04-04","cited_by_count":45},{"id":"2403.02969","title":"Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception","created":"2024-03-05","cited_by_count":39},{"id":"2404.19752","title":"Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation","created":"2024-04-30","cited_by_count":28},{"id":"2308.02299","title":"RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension","created":"2023-08-03","cited_by_count":27},{"id":"2402.11248","title":"CoLLaVO: Crayon Large Language and Vision mOdel","created":"2024-02-17","cited_by_count":26},{"id":"2401.13307","title":"ChatterBox: Multi-round Multimodal Referring and Grounding","created":"2024-01-24","cited_by_count":24},{"id":"2307.12058","title":"Discovering Spatio-Temporal Rationales for Video Question Answering","created":"2023-07-22","cited_by_count":21},{"id":"2403.05021","title":"Beyond MOT: Semantic Multi-Object Tracking","created":"2024-03-08","cited_by_count":12},{"id":"2406.13912","title":"From Descriptive Richness to Bias: Unveiling the Dark Side of Generative Image Caption Enrichment","created":"2024-06-20","cited_by_count":8}],"next_cursor":null}