{"list":"other","total":58,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"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":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"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},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2003.12462","title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","created":"2020-03-24","cited_by_count":400},{"id":"2212.09689","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","created":"2022-12-19","cited_by_count":397},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227},{"id":"2305.20088","title":"Improving CLIP Training with Language Rewrites","created":"2023-05-31","cited_by_count":217},{"id":"1505.00855","title":"Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature","created":"2015-05-05","cited_by_count":182},{"id":"2307.04087","title":"SVIT: Scaling up Visual Instruction Tuning","created":"2023-07-09","cited_by_count":162},{"id":"2311.07574","title":"To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning","created":"2023-11-13","cited_by_count":144},{"id":"1808.00157","title":"Instance-level Human Parsing via Part Grouping Network","created":"2018-08-01","cited_by_count":134},{"id":"2311.16103","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","created":"2023-11-27","cited_by_count":107},{"id":"2309.07918","title":"Unified Human-Scene Interaction via Prompted Chain-of-Contacts","created":"2023-09-14","cited_by_count":94},{"id":"2307.10350","title":"Improving Multimodal Datasets with Image Captioning","created":"2023-07-19","cited_by_count":93},{"id":"2310.20550","title":"CapsFusion: Rethinking Image-Text Data at Scale","created":"2023-10-31","cited_by_count":90},{"id":"1803.00455","title":"LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images","created":"2018-03-01","cited_by_count":88},{"id":"2207.12824","title":"Compositional Human-Scene Interaction Synthesis with Semantic Control","created":"2022-07-26","cited_by_count":83},{"id":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83},{"id":"2311.04498","title":"NExT-Chat: An LMM for Chat, Detection and Segmentation","created":"2023-11-08","cited_by_count":80},{"id":"1804.01984","title":"Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmark","created":"2018-04-05","cited_by_count":79},{"id":"1711.06475","title":"AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding","created":"2017-11-17","cited_by_count":73},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59},{"id":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38},{"id":"2106.12733","title":"Feature Completion for Occluded Person Re-Identification","created":"2021-06-24","cited_by_count":30},{"id":"2203.13815","title":"Versatile Multi-Modal Pre-Training for Human-Centric Perception","created":"2022-03-25","cited_by_count":26},{"id":"2312.14828","title":"Plan, Posture and Go: Towards Open-World Text-to-Motion Generation","created":"2023-12-22","cited_by_count":26},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22},{"id":"2301.07702","title":"Learning 3D-aware Image Synthesis with Unknown Pose Distribution","created":"2023-01-18","cited_by_count":14},{"id":"2311.14580","title":"Large Language Models as Automated Aligners for benchmarking Vision-Language Models","created":"2023-11-24","cited_by_count":10},{"id":"2311.16475","title":"Enhancing HOI Detection with Contextual Cues from Large Vision-Language Models","created":"2023-11-26","cited_by_count":3}],"next_cursor":null}