{"list":"other","total":184,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"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":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"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":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"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":"1908.06391","title":"PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment","created":"2019-08-18","cited_by_count":449},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"1904.00607","title":"Video Object Segmentation using Space-Time Memory Networks","created":"2019-04-01","cited_by_count":438},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375},{"id":"2206.02647","title":"Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning","created":"2022-06-06","cited_by_count":359},{"id":"2003.09003","title":"MOT20: A benchmark for multi object tracking in crowded scenes","created":"2020-03-19","cited_by_count":357},{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"id":"1803.10464","title":"Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation","created":"2018-03-28","cited_by_count":321},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294},{"id":"1704.08545","title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","created":"2017-04-27","cited_by_count":261},{"id":"1611.05198","title":"One-Shot Video Object Segmentation","created":"2016-11-16","cited_by_count":235},{"id":"2111.15668","title":"AdaViT: Adaptive Vision Transformers for Efficient Image Recognition","created":"2021-11-30","cited_by_count":228},{"id":"1902.03604","title":"MOTS: Multi-Object Tracking and Segmentation","created":"2019-02-10","cited_by_count":223},{"id":"2106.05210","title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","created":"2021-06-09","cited_by_count":203},{"id":"2303.08131","title":"A Simple Framework for Open-Vocabulary Segmentation and Detection","created":"2023-03-14","cited_by_count":198},{"id":"2309.03903","title":"Tracking Anything with Decoupled Video Segmentation","created":"2023-09-07","cited_by_count":197},{"id":"2305.06558","title":"Segment and Track Anything","created":"2023-05-11","cited_by_count":193},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189},{"id":"2310.12982","title":"Putting the Object Back into Video Object Segmentation","created":"2023-10-19","cited_by_count":188},{"id":"1611.07715","title":"Deep Feature Flow for Video Recognition","created":"2016-11-23","cited_by_count":186},{"id":"1703.10025","title":"Flow-Guided Feature Aggregation for Video Object Detection","created":"2017-03-29","cited_by_count":177},{"id":"2005.08104","title":"Single-Stage Semantic Segmentation from Image Labels","created":"2020-05-16","cited_by_count":167},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166},{"id":"2103.08808","title":"Track to Detect and Segment: An Online Multi-Object Tracker","created":"2021-03-16","cited_by_count":156},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154},{"id":"2312.10103","title":"GSVA: Generalized Segmentation via Multimodal Large Language Models","created":"2023-12-15","cited_by_count":154},{"id":"2203.01502","title":"NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation","created":"2022-03-03","cited_by_count":153},{"id":"1612.02646","title":"Learning Video Object Segmentation from Static Images","created":"2016-12-08","cited_by_count":151},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148},{"id":"2003.08333","title":"Collaborative Video Object Segmentation by Foreground-Background Integration","created":"2020-03-18","cited_by_count":142},{"id":"2006.11339","title":"Video Panoptic Segmentation","created":"2020-06-19","cited_by_count":142},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136},{"id":"1812.01593","title":"Improving Semantic Segmentation via Video Propagation and Label Relaxation","created":"2018-12-04","cited_by_count":134},{"id":"2104.04691","title":"Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation","created":"2021-04-10","cited_by_count":133},{"id":"2107.01153","title":"A Survey on Deep Learning Technique for Video Segmentation","created":"2021-07-02","cited_by_count":132},{"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":"1912.04573","title":"Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation","created":"2019-12-10","cited_by_count":125},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124},{"id":"2003.08429","title":"STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos","created":"2020-03-18","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":"2007.07020","title":"Video Object Segmentation with Episodic Graph Memory Networks","created":"2020-07-14","cited_by_count":118},{"id":"2204.06986","title":"Cross-Image Relational Knowledge Distillation for Semantic Segmentation","created":"2022-04-14","cited_by_count":118},{"id":"2106.03299","title":"Video Instance Segmentation using Inter-Frame Communication Transformers","created":"2021-06-07","cited_by_count":105},{"id":"2409.19603","title":"One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos","created":"2024-09-29","cited_by_count":100},{"id":"2210.06366","title":"A Generalist Framework for Panoptic Segmentation of Images and Videos","created":"2022-10-12","cited_by_count":99},{"id":"2301.09121","title":"Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision","created":"2023-01-22","cited_by_count":99},{"id":"2112.08275","title":"SeqFormer: Sequential Transformer for Video Instance Segmentation","created":"2021-12-15","cited_by_count":98},{"id":"2207.10661","title":"In Defense of Online Models for Video Instance Segmentation","created":"2022-07-21","cited_by_count":97},{"id":"2012.05258","title":"ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation","created":"2020-12-09","cited_by_count":96},{"id":"2208.02245","title":"MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training","created":"2022-08-03","cited_by_count":94},{"id":"2111.01236","title":"Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation","created":"2021-11-01","cited_by_count":92},{"id":"1903.05612","title":"RVOS: End-to-End Recurrent Network for Video Object Segmentation","created":"2019-03-13","cited_by_count":88},{"id":"2103.10284","title":"SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation","created":"2021-03-18","cited_by_count":87},{"id":"2103.12934","title":"Efficient Regional Memory Network for Video Object Segmentation","created":"2021-03-24","cited_by_count":86},{"id":"2106.12011","title":"P2T: Pyramid Pooling Transformer for Scene Understanding","created":"2021-06-22","cited_by_count":84},{"id":"2206.02066","title":"PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers","created":"2022-06-04","cited_by_count":84},{"id":"2104.05970","title":"Crossover Learning for Fast Online Video Instance Segmentation","created":"2021-04-13","cited_by_count":83},{"id":"1807.09190","title":"PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation","created":"2018-07-24","cited_by_count":81},{"id":"2307.01197","title":"Segment Anything Meets Point Tracking","created":"2023-07-03","cited_by_count":81},{"id":"1811.10842","title":"CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation","created":"2018-11-27","cited_by_count":80},{"id":"2204.04656","title":"Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation","created":"2022-04-10","cited_by_count":79},{"id":"1807.06667","title":"Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video","created":"2018-07-17","cited_by_count":78},{"id":"2004.01800","title":"Temporally Distributed Networks for Fast Video Semantic Segmentation","created":"2020-04-03","cited_by_count":77},{"id":"2306.03413","title":"DVIS: Decoupled Video Instance Segmentation Framework","created":"2023-06-06","cited_by_count":77},{"id":"1612.08871","title":"Semantic Video Segmentation by Gated Recurrent Flow Propagation","created":"2016-12-28","cited_by_count":76}],"next_cursor":"100"}