{"list":"other","total":52,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"1807.03888","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","created":"2018-07-10","cited_by_count":1485},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"1610.02415","title":"Automatic chemical design using a data-driven continuous representation of molecules","created":"2016-10-07","cited_by_count":765},{"id":"1807.02811","title":"A Tutorial on Bayesian Optimization","created":"2018-07-08","cited_by_count":744},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"1505.00880","title":"Multi-view Convolutional Neural Networks for 3D Shape Recognition","created":"2015-05-05","cited_by_count":565},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"1912.03263","title":"Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One","created":"2019-12-06","cited_by_count":405},{"id":"2104.12229","title":"Vector Neurons: A General Framework for SO(3)-Equivariant Networks","created":"2021-04-25","cited_by_count":305},{"id":"1802.03690","title":"On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups","created":"2018-02-11","cited_by_count":300},{"id":"2206.09012","title":"Diffusion models as plug-and-play priors","created":"2022-06-17","cited_by_count":231},{"id":"1811.02017","title":"A General Theory of Equivariant CNNs on Homogeneous Spaces","created":"2018-11-05","cited_by_count":228},{"id":"2008.05659","title":"What Should Not Be Contrastive in Contrastive Learning","created":"2020-08-13","cited_by_count":226},{"id":"2011.13244","title":"MVTN: Multi-View Transformation Network for 3D Shape Recognition","created":"2020-11-26","cited_by_count":140},{"id":"2006.09191","title":"Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining","created":"2020-06-16","cited_by_count":123},{"id":"2211.06489","title":"Equivariance with Learned Canonicalization Functions","created":"2022-11-11","cited_by_count":109},{"id":"2211.07740","title":"Denoising diffusion models for out-of-distribution detection","created":"2022-11-14","cited_by_count":104},{"id":"2008.08145","title":"Category Level Object Pose Estimation via Neural Analysis-by-Synthesis","created":"2020-08-18","cited_by_count":100},{"id":"2201.11872","title":"Local Latent Space Bayesian Optimization over Structured Inputs","created":"2022-01-28","cited_by_count":79},{"id":"2501.18841","title":"Trading Inference-Time Compute for Adversarial Robustness","created":"2025-01-31","cited_by_count":61},{"id":"2210.03895","title":"ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints","created":"2022-10-08","cited_by_count":48},{"id":"2310.01647","title":"Equivariant Adaptation of Large Pretrained Models","created":"2023-10-02","cited_by_count":41},{"id":"1611.07596","title":"Fast Fourier Color Constancy","created":"2016-11-23","cited_by_count":37},{"id":"2106.05121","title":"Grounding inductive biases in natural images:invariance stems from variations in data","created":"2021-06-09","cited_by_count":27},{"id":"2406.09613","title":"ImageNet3D: Towards General-Purpose Object-Level 3D Understanding","created":"2024-06-13","cited_by_count":25},{"id":"2306.09349","title":"UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Video","created":"2023-06-15","cited_by_count":22},{"id":"2307.10235","title":"Towards Viewpoint-Invariant Visual Recognition via Adversarial Training","created":"2023-07-16","cited_by_count":19},{"id":"2002.12896","title":"A Multi-Hypothesis Approach to Color Constancy","created":"2020-02-28","cited_by_count":18},{"id":"2401.01764","title":"Understanding the Detrimental Class-level Effects of Data Augmentation","created":"2023-12-07","cited_by_count":13},{"id":"2203.09739","title":"Do Deep Networks Transfer Invariances Across Classes?","created":"2022-03-18","cited_by_count":12},{"id":"2403.01946","title":"A Generative Model of Symmetry Transformations","created":"2024-03-04","cited_by_count":10},{"id":"2404.12139","title":"Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models","created":"2024-04-18","cited_by_count":9},{"id":"1611.05744","title":"Compensating for Large In-Plane Rotations in Natural Images","created":"2016-11-17","cited_by_count":2},{"id":"2309.16672","title":"Learning to Transform for Generalizable Instance-wise Invariance","created":"2023-09-28","cited_by_count":2},{"id":"2407.03842","title":"Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation","created":"2024-07-04","cited_by_count":1}],"next_cursor":null}