{"list":"other","total":89,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"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":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"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":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"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":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"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":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"1907.11922","title":"MaskGAN: Towards Diverse and Interactive Facial Image Manipulation","created":"2019-07-27","cited_by_count":628},{"id":"1711.10398","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","created":"2017-11-28","cited_by_count":623},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"2302.12242","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","created":"2023-02-23","cited_by_count":300},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294},{"id":"1912.04488","title":"SOLO: Segmenting Objects by Locations","created":"2019-12-10","cited_by_count":289},{"id":"2306.00968","title":"GRES: Generalized Referring Expression Segmentation","created":"2023-06-01","cited_by_count":254},{"id":"1608.00525","title":"Modeling Context Between Objects for Referring Expression Understanding","created":"2016-08-01","cited_by_count":251},{"id":"2312.02228","title":"PixelLM: Pixel Reasoning with Large Multimodal Model","created":"2023-12-04","cited_by_count":222},{"id":"1803.11365","title":"Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation","created":"2018-03-30","cited_by_count":218},{"id":"2112.10764","title":"Mask2Former for Video Instance Segmentation","created":"2021-12-20","cited_by_count":171},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166},{"id":"1907.12347","title":"FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation","created":"2019-07-29","cited_by_count":160},{"id":"2312.10103","title":"GSVA: Generalized Segmentation via Multimodal Large Language Models","created":"2023-12-15","cited_by_count":154},{"id":"2104.04691","title":"Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation","created":"2021-04-10","cited_by_count":133},{"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":"2307.08581","title":"BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs","created":"2023-07-17","cited_by_count":114},{"id":"2203.03041","title":"Highly Accurate Dichotomous Image Segmentation","created":"2022-03-06","cited_by_count":110},{"id":"1703.05446","title":"Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing","created":"2017-03-16","cited_by_count":109},{"id":"1810.08705","title":"Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing","created":"2018-10-19","cited_by_count":106},{"id":"1509.01329","title":"Semantic Amodal Segmentation","created":"2015-09-04","cited_by_count":103},{"id":"2112.08275","title":"SeqFormer: Sequential Transformer for Video Instance Segmentation","created":"2021-12-15","cited_by_count":98},{"id":"2206.04403","title":"VITA: Video Instance Segmentation via Object Token Association","created":"2022-06-09","cited_by_count":94},{"id":"2211.05776","title":"High-Quality Entity Segmentation","created":"2022-11-10","cited_by_count":93},{"id":"1807.02257","title":"Dynamic Multimodal Instance Segmentation guided by natural language queries","created":"2018-07-06","cited_by_count":83},{"id":"2107.14228","title":"Open-World Entity Segmentation","created":"2021-07-29","cited_by_count":74},{"id":"2312.07661","title":"CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor","created":"2023-12-12","cited_by_count":69},{"id":"1804.03287","title":"Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing","created":"2018-04-10","cited_by_count":60},{"id":"1902.01626","title":"EasyLabel: A Semi-Automatic Pixel-wise Object Annotation Tool for Creating Robotic RGB-D Datasets","created":"2019-02-05","cited_by_count":58},{"id":"2303.11324","title":"Open-vocabulary Panoptic Segmentation with Embedding Modulation","created":"2023-03-20","cited_by_count":39},{"id":"2108.07682","title":"Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision","created":"2021-08-17","cited_by_count":31},{"id":"2109.04988","title":"Panoptic Narrative Grounding","created":"2021-09-10","cited_by_count":27},{"id":"2109.06875","title":"Multi-Scale Aligned Distillation for Low-Resolution Detection","created":"2021-09-14","cited_by_count":24},{"id":"2103.17123","title":"Camouflaged Instance Segmentation In-The-Wild: Dataset, Method, and Benchmark Suite","created":"2021-03-31","cited_by_count":16},{"id":"2204.04428","title":"ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise Semantic Alignment and Generation","created":"2022-04-09","cited_by_count":13},{"id":"2208.05647","title":"PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding","created":"2022-08-11","cited_by_count":12},{"id":"2310.10975","title":"NICE: Improving Panoptic Narrative Detection and Segmentation with Cascading Collaborative Learning","created":"2023-10-17","cited_by_count":8},{"id":"2212.07603","title":"Text-Guided Mask-free Local Image Retouching","created":"2022-12-15","cited_by_count":6},{"id":"2305.17768","title":"AIMS: All-Inclusive Multi-Level Segmentation","created":"2023-05-28","cited_by_count":6},{"id":"2311.01091","title":"Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Grounding","created":"2023-11-02","cited_by_count":6},{"id":"2302.11383","title":"Entity-Level Text-Guided Image Manipulation","created":"2023-02-22","cited_by_count":3}],"next_cursor":null}