{"list":"other","total":65,"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"1710.03463","title":"Learning to Generalize: Meta-Learning for Domain Generalization","created":"2017-10-10","cited_by_count":763},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2302.10174","title":"Towards Universal Fake Image Detectors that Generalize Across Generative Models","created":"2023-02-20","cited_by_count":490},{"id":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388},{"id":"1807.09441","title":"Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net","created":"2018-07-25","cited_by_count":364},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267},{"id":"2103.15597","title":"RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening","created":"2021-03-29","cited_by_count":215},{"id":"2302.12066","title":"Teaching CLIP to Count to Ten","created":"2023-02-23","cited_by_count":198},{"id":"2104.08391","title":"Learning To Count Everything","created":"2021-04-16","cited_by_count":150},{"id":"1903.03303","title":"Learning from Synthetic Data for Crowd Counting in the Wild","created":"2019-03-08","cited_by_count":148},{"id":"2207.03482","title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection","created":"2022-07-07","cited_by_count":146},{"id":"2405.10300","title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","created":"2024-05-16","cited_by_count":122},{"id":"2407.12442","title":"ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference","created":"2024-07-17","cited_by_count":113},{"id":"1812.11806","title":"An introduction to domain adaptation and transfer learning","created":"2018-12-31","cited_by_count":112},{"id":"1904.09739","title":"Switchable Whitening for Deep Representation Learning","created":"2019-04-22","cited_by_count":106},{"id":"2405.18415","title":"Why are Visually-Grounded Language Models Bad at Image Classification?","created":"2024-05-28","cited_by_count":102},{"id":"2403.14610","title":"T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy","created":"2024-03-21","cited_by_count":94},{"id":"2307.12732","title":"CLIP-KD: An Empirical Study of CLIP Model Distillation","created":"2023-07-24","cited_by_count":87},{"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":"2208.13721","title":"CounTR: Transformer-based Generalised Visual Counting","created":"2022-08-29","cited_by_count":79},{"id":"2204.12997","title":"DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers","created":"2022-04-27","cited_by_count":65},{"id":"2211.08217","title":"A Low-Shot Object Counting Network With Iterative Prototype Adaptation","created":"2022-11-15","cited_by_count":65},{"id":"2201.08959","title":"Few-shot Object Counting with Similarity-Aware Feature Enhancement","created":"2022-01-22","cited_by_count":62},{"id":"2108.01621","title":"Domain Generalization via Gradient Surgery","created":"2021-08-03","cited_by_count":60},{"id":"2303.02001","title":"Zero-shot Object Counting","created":"2023-03-03","cited_by_count":57},{"id":"2207.10988","title":"Few-shot Object Counting and Detection","created":"2022-07-22","cited_by_count":55},{"id":"2404.16622","title":"DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting","created":"2024-04-25","cited_by_count":49},{"id":"2404.09216","title":"DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection","created":"2024-04-14","cited_by_count":48},{"id":"2304.04231","title":"CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model","created":"2023-04-09","cited_by_count":47},{"id":"2306.03221","title":"Structural Re-weighting Improves Graph Domain Adaptation","created":"2023-06-05","cited_by_count":45},{"id":"2312.16580","title":"VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting","created":"2023-12-27","cited_by_count":45},{"id":"2302.14338","title":"Turning a CLIP Model into a Scene Text Detector","created":"2023-02-28","cited_by_count":44},{"id":"2309.01151","title":"EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignment","created":"2023-09-03","cited_by_count":44},{"id":"2205.10203","title":"Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision","created":"2022-05-20","cited_by_count":41},{"id":"2306.01851","title":"Open-world Text-specified Object Counting","created":"2023-06-02","cited_by_count":41},{"id":"2303.11324","title":"Open-vocabulary Panoptic Segmentation with Embedding Modulation","created":"2023-03-20","cited_by_count":39},{"id":"2311.12386","title":"Point, Segment and Count: A Generalized Framework for Object Counting","created":"2023-11-21","cited_by_count":39},{"id":"2402.03241","title":"FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition","created":"2024-02-05","cited_by_count":36},{"id":"2205.14212","title":"Exemplar Free Class Agnostic Counting","created":"2022-05-27","cited_by_count":32},{"id":"2105.02440","title":"Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark","created":"2021-05-06","cited_by_count":31},{"id":"2403.15132","title":"Transfer CLIP for Generalizable Image Denoising","created":"2024-03-22","cited_by_count":29},{"id":"1912.03677","title":"Domain-adaptive Crowd Counting via High-quality Image Translation and Density Reconstruction","created":"2019-12-08","cited_by_count":26},{"id":"2407.04948","title":"Zero-shot Object Counting with Good Exemplars","created":"2024-07-06","cited_by_count":21},{"id":"2212.02573","title":"Domain-General Crowd Counting in Unseen Scenarios","created":"2022-12-05","cited_by_count":20},{"id":"2304.00741","title":"DeGPR: Deep Guided Posterior Regularization for Multi-Class Cell Detection and Counting","created":"2023-04-03","cited_by_count":18},{"id":"2403.09124","title":"Single Domain Generalization for Crowd Counting","created":"2024-03-14","cited_by_count":17},{"id":"2008.05383","title":"Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer","created":"2020-08-12","cited_by_count":13},{"id":"2112.05993","title":"Object Counting: You Only Need to Look at One","created":"2021-12-11","cited_by_count":13},{"id":"2308.05311","title":"DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting","created":"2023-08-10","cited_by_count":12}],"next_cursor":null}