{"list":"other","total":60,"rows":[{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"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":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"2308.16512","title":"MVDream: Multi-view Diffusion for 3D Generation","created":"2023-08-31","cited_by_count":938},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512},{"id":"2305.07015","title":"Exploiting Diffusion Prior for Real-World Image Super-Resolution","created":"2023-05-11","cited_by_count":489},{"id":"2302.12242","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","created":"2023-02-23","cited_by_count":300},{"id":"1802.10062","title":"CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes","created":"2018-02-27","cited_by_count":267},{"id":"2112.14757","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","created":"2021-12-29","cited_by_count":223},{"id":"1808.01050","title":"Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds","created":"2018-08-02","cited_by_count":186},{"id":"2307.14460","title":"MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation","created":"2023-07-26","cited_by_count":174},{"id":"1910.06278","title":"Distribution-Aware Coordinate Representation for Human Pose Estimation","created":"2019-10-14","cited_by_count":165},{"id":"2211.14813","title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","created":"2022-11-27","cited_by_count":164},{"id":"1707.05972","title":"Drone-based Object Counting by Spatially Regularized Regional Proposal Network","created":"2017-07-19","cited_by_count":156},{"id":"2204.05088","title":"M$^2$BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation","created":"2022-04-11","cited_by_count":156},{"id":"2107.12746","title":"Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework","created":"2021-07-27","cited_by_count":152},{"id":"2001.03360","title":"NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization","created":"2020-01-10","cited_by_count":151},{"id":"2104.08391","title":"Learning To Count Everything","created":"2021-04-16","cited_by_count":150},{"id":"2308.13164","title":"Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Model","created":"2023-08-25","cited_by_count":118},{"id":"2004.03597","title":"JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method","created":"2020-04-07","cited_by_count":109},{"id":"1811.00472","title":"Class-Agnostic Counting","created":"2018-11-01","cited_by_count":85},{"id":"2305.07304","title":"CLIP-Count: Towards Text-Guided Zero-Shot Object Counting","created":"2023-05-12","cited_by_count":83},{"id":"2203.08354","title":"Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting","created":"2022-03-16","cited_by_count":80},{"id":"2304.06022","title":"SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anything","created":"2023-04-12","cited_by_count":75},{"id":"2201.08959","title":"Few-shot Object Counting with Similarity-Aware Feature Enhancement","created":"2022-01-22","cited_by_count":62},{"id":"2303.02001","title":"Zero-shot Object Counting","created":"2023-03-03","cited_by_count":57},{"id":"1610.01465","title":"Visual Question Answering: Datasets, Algorithms, and Future Challenges","created":"2016-10-05","cited_by_count":56},{"id":"2206.05253","title":"Rethinking Spatial Invariance of Convolutional Networks for Object Counting","created":"2022-06-10","cited_by_count":54},{"id":"2202.01993","title":"Grounding Answers for Visual Questions Asked by Visually Impaired People","created":"2022-02-04","cited_by_count":47},{"id":"2304.04231","title":"CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model","created":"2023-04-09","cited_by_count":47},{"id":"2308.10468","title":"STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning","created":"2023-08-21","cited_by_count":41},{"id":"2308.13814","title":"Point-Query Quadtree for Crowd Counting, Localization, and More","created":"2023-08-26","cited_by_count":40},{"id":"2311.12386","title":"Point, Segment and Count: A Generalized Framework for Object Counting","created":"2023-11-21","cited_by_count":39},{"id":"1903.02494","title":"Object Counting and Instance Segmentation with Image-level Supervision","created":"2019-03-06","cited_by_count":36},{"id":"1909.07057","title":"Learning Spatial Awareness to Improve Crowd Counting","created":"2019-09-16","cited_by_count":36},{"id":"1604.03505","title":"Counting Everyday Objects in Everyday Scenes","created":"2016-04-12","cited_by_count":34},{"id":"2307.00038","title":"Training-free Object Counting with Prompts","created":"2023-06-30","cited_by_count":34},{"id":"1903.12206","title":"Counting with Focus for Free","created":"2019-03-28","cited_by_count":33},{"id":"1910.12384","title":"Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method","created":"2019-10-28","cited_by_count":32},{"id":"2205.14212","title":"Exemplar Free Class Agnostic Counting","created":"2022-05-27","cited_by_count":32},{"id":"1807.10587","title":"Finding any Waldo: zero-shot invariant and efficient visual search","created":"2018-07-18","cited_by_count":28},{"id":"1711.05187","title":"Dynamic Zoom-in Network for Fast Object Detection in Large Images","created":"2017-11-14","cited_by_count":23},{"id":"2308.09887","title":"Calibrating Uncertainty for Semi-Supervised Crowd Counting","created":"2023-08-19","cited_by_count":22},{"id":"2312.01711","title":"Regressor-Segmenter Mutual Prompt Learning for Crowd Counting","created":"2023-12-04","cited_by_count":16},{"id":"1909.07608","title":"Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting","created":"2019-09-17","cited_by_count":15},{"id":"2306.01209","title":"Counting Crowds in Bad Weather","created":"2023-06-02","cited_by_count":14},{"id":"2106.02953","title":"Visual Search Asymmetry: Deep Nets and Humans Share Similar Inherent Biases","created":"2021-06-05","cited_by_count":12},{"id":"2312.12273","title":"VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering","created":"2023-12-19","cited_by_count":11},{"id":"1912.06448","title":"Towards Partial Supervision for Generic Object Counting in Natural Scenes","created":"2019-12-13","cited_by_count":9},{"id":"2309.13097","title":"Zero-Shot Object Counting with Language-Vision Models","created":"2023-09-22","cited_by_count":9},{"id":"2101.01611","title":"Look Twice: A Generalist Computational Model Predicts Return Fixations across Tasks and Species","created":"2021-01-05","cited_by_count":8},{"id":"2306.05129","title":"Focus for Free in Density-Based Counting","created":"2023-06-08","cited_by_count":8}],"next_cursor":null}