{"list":"other","total":72,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"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":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"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":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1906.01502","title":"How multilingual is Multilingual BERT?","created":"2019-06-04","cited_by_count":645},{"id":"1707.03237","title":"Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations","created":"2017-07-11","cited_by_count":620},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"2003.06957","title":"Frustratingly Simple Few-Shot Object Detection","created":"2020-03-16","cited_by_count":282},{"id":"1812.01866","title":"Few-shot Object Detection via Feature Reweighting","created":"2018-12-05","cited_by_count":265},{"id":"2203.11876","title":"Open-Vocabulary DETR with Conditional Matching","created":"2022-03-22","cited_by_count":220},{"id":"1908.01998","title":"Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector","created":"2019-08-06","cited_by_count":206},{"id":"2308.02487","title":"Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP","created":"2023-08-04","cited_by_count":201},{"id":"1912.11554","title":"Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro","created":"2019-12-24","cited_by_count":191},{"id":"1909.13032","title":"Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning","created":"2019-09-28","cited_by_count":182},{"id":"2103.05950","title":"FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding","created":"2021-03-10","cited_by_count":168},{"id":"2202.11539","title":"Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut","created":"2022-02-23","cited_by_count":167},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166},{"id":"2205.07839","title":"Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization","created":"2022-05-16","cited_by_count":150},{"id":"2007.12107","title":"Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild","created":"2020-07-23","cited_by_count":142},{"id":"2203.15102","title":"Rethinking Semantic Segmentation: A Prototype View","created":"2022-03-28","cited_by_count":140},{"id":"2303.13076","title":"CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching","created":"2023-03-23","cited_by_count":133},{"id":"2112.01513","title":"OW-DETR: Open-world Detection Transformer","created":"2021-12-02","cited_by_count":129},{"id":"2302.13996","title":"Aligning Bag of Regions for Open-Vocabulary Object Detection","created":"2023-02-27","cited_by_count":119},{"id":"1806.07823","title":"Unsupervised Learning of Object Landmarks through Conditional Image Generation","created":"2018-06-20","cited_by_count":114},{"id":"2210.11006","title":"SimpleClick: Interactive Image Segmentation with Simple Vision Transformers","created":"2022-10-20","cited_by_count":111},{"id":"1906.11883","title":"Unsupervised Learning of Object Keypoints for Perception and Control","created":"2019-06-19","cited_by_count":109},{"id":"2207.08954","title":"Exploiting Unlabeled Data with Vision and Language Models for Object Detection","created":"2022-07-18","cited_by_count":97},{"id":"2305.07011","title":"Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers","created":"2023-05-11","cited_by_count":91},{"id":"2204.13101","title":"Self-Supervised Learning of Object Parts for Semantic Segmentation","created":"2022-04-27","cited_by_count":90},{"id":"2105.09491","title":"Generalized Few-Shot Object Detection without Forgetting","created":"2021-05-20","cited_by_count":88},{"id":"1911.12529","title":"One-Shot Object Detection with Co-Attention and Co-Excitation","created":"2019-11-28","cited_by_count":67},{"id":"2212.07834","title":"Unsupervised Object Localization: Observing the Background to Discover Objects","created":"2022-12-15","cited_by_count":66},{"id":"2203.15021","title":"Few-Shot Object Detection with Fully Cross-Transformer","created":"2022-03-28","cited_by_count":64},{"id":"2209.07383","title":"Visual Recognition with Deep Nearest Centroids","created":"2022-09-15","cited_by_count":59},{"id":"2104.07719","title":"Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment","created":"2021-04-15","cited_by_count":57},{"id":"2112.09791","title":"Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networks","created":"2021-12-17","cited_by_count":55},{"id":"2306.05493","title":"Multi-Modal Classifiers for Open-Vocabulary Object Detection","created":"2023-06-08","cited_by_count":53},{"id":"1811.11507","title":"One-Shot Instance Segmentation","created":"2018-11-28","cited_by_count":43},{"id":"2112.05749","title":"Label, Verify, Correct: A Simple Few Shot Object Detection Method","created":"2021-12-10","cited_by_count":43},{"id":"2308.11796","title":"Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations","created":"2023-08-22","cited_by_count":35},{"id":"1603.01564","title":"High precision grasp pose detection in dense clutter","created":"2016-03-04","cited_by_count":34},{"id":"2112.11699","title":"Few-Shot Object Detection: A Comprehensive Survey","created":"2021-12-22","cited_by_count":29},{"id":"2211.08681","title":"Interclass Prototype Relation for Few-Shot Segmentation","created":"2022-11-16","cited_by_count":25},{"id":"2206.11134","title":"Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization","created":"2022-06-22","cited_by_count":23},{"id":"2303.09674","title":"DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection","created":"2023-03-16","cited_by_count":21},{"id":"2203.09093","title":"Semantic-aligned Fusion Transformer for One-shot Object Detection","created":"2022-03-17","cited_by_count":13},{"id":"2303.13040","title":"Open-Vocabulary Object Detection using Pseudo Caption Labels","created":"2023-03-23","cited_by_count":13},{"id":"2005.03819","title":"One-Shot Object Detection without Fine-Tuning","created":"2020-05-08","cited_by_count":11},{"id":"2303.04958","title":"NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging","created":"2023-03-09","cited_by_count":10},{"id":"2201.12437","title":"Mobile Robot Manipulation using Pure Object Detection","created":"2022-01-28","cited_by_count":8},{"id":"2207.03333","title":"FewSOL: A Dataset for Few-Shot Object Learning in Robotic Environments","created":"2022-07-06","cited_by_count":8},{"id":"2307.13640","title":"Optical Flow boosts Unsupervised Localization and Segmentation","created":"2023-07-25","cited_by_count":7},{"id":"2005.02641","title":"Incremental Few-Shot Object Detection for Robotics","created":"2020-05-06","cited_by_count":5},{"id":"2208.01084","title":"Robotic Interestingness via Human-Informed Few-Shot Object Detection","created":"2022-08-01","cited_by_count":3}],"next_cursor":null}