{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"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":"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":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"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":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"2203.14940","title":"Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model","created":"2022-03-28","cited_by_count":317},{"id":"2306.12156","title":"Fast Segment Anything","created":"2023-06-21","cited_by_count":290},{"id":"2207.10666","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","created":"2022-07-21","cited_by_count":234},{"id":"2007.10732","title":"Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images","created":"2020-07-21","cited_by_count":152},{"id":"2104.13188","title":"Rethinking BiSeNet For Real-time Semantic Segmentation","created":"2021-04-27","cited_by_count":124},{"id":"2301.09121","title":"Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision","created":"2023-01-22","cited_by_count":99},{"id":"2003.08440","title":"Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation","created":"2020-03-18","cited_by_count":96},{"id":"2106.12011","title":"P2T: Pyramid Pooling Transformer for Scene Understanding","created":"2021-06-22","cited_by_count":84},{"id":"2003.12058","title":"Grounded Situation Recognition","created":"2020-03-26","cited_by_count":78},{"id":"2210.15138","title":"Open-vocabulary Semantic Segmentation with Frozen Vision-Language Models","created":"2022-10-27","cited_by_count":39},{"id":"1708.04320","title":"Situation Recognition with Graph Neural Networks","created":"2017-08-14","cited_by_count":34},{"id":"2107.03172","title":"Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World","created":"2021-07-07","cited_by_count":30},{"id":"2112.00484","title":"Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding","created":"2021-12-01","cited_by_count":26},{"id":"2107.00346","title":"MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understanding","created":"2021-07-01","cited_by_count":22},{"id":"2208.08965","title":"GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement","created":"2022-08-18","cited_by_count":20},{"id":"2203.16518","title":"Collaborative Transformers for Grounded Situation Recognition","created":"2022-03-30","cited_by_count":19},{"id":"2202.13393","title":"TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation","created":"2022-02-27","cited_by_count":17},{"id":"2112.05375","title":"Rethinking the Two-Stage Framework for Grounded Situation Recognition","created":"2021-12-10","cited_by_count":16},{"id":"2111.10135","title":"Grounded Situation Recognition with Transformers","created":"2021-11-19","cited_by_count":14},{"id":"2201.01073","title":"Towards Unsupervised Open World Semantic Segmentation","created":"2022-01-04","cited_by_count":13},{"id":"1908.03364","title":"Deep Learning based Wearable Assistive System for Visually Impaired People","created":"2019-08-09","cited_by_count":12},{"id":"2207.11810","title":"VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairments","created":"2022-07-24","cited_by_count":11},{"id":"2107.03180","title":"HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor","created":"2021-07-07","cited_by_count":9},{"id":"2302.14595","title":"MateRobot: Material Recognition in Wearable Robotics for People with Visual Impairments","created":"2023-02-28","cited_by_count":9},{"id":"2206.04879","title":"Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion","created":"2022-06-10","cited_by_count":8},{"id":"2301.05323","title":"Salient Object Detection for Images Taken by People With Vision Impairments","created":"2023-01-12","cited_by_count":7},{"id":"2101.02047","title":"Unified Learning Approach for Egocentric Hand Gesture Recognition and Fingertip Detection","created":"2021-01-06","cited_by_count":6},{"id":"2302.03481","title":"\"I am the follower, also the boss\": Exploring Different Levels of Autonomy and Machine Forms of Guiding Robots for the Visually Impaired","created":"2023-02-07","cited_by_count":6},{"id":"2203.01368","title":"Conditional Reconstruction for Open-set Semantic Segmentation","created":"2022-03-02","cited_by_count":3}],"next_cursor":null}