{"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":"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":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"1912.01865","title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","created":"2019-12-04","cited_by_count":1098},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"id":"1710.11063","title":"Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks","created":"2017-10-30","cited_by_count":939},{"id":"1803.00567","title":"Computational Optimal Transport","created":"2018-03-01","cited_by_count":780},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2306.13643","title":"LightGlue: Local Feature Matching at Light Speed","created":"2023-06-23","cited_by_count":590},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2006.13566","title":"DISK: Learning local features with policy gradient","created":"2020-06-24","cited_by_count":312},{"id":"2305.15404","title":"RoMa: Robust Dense Feature Matching","created":"2023-05-24","cited_by_count":302},{"id":"2305.15347","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","created":"2023-05-24","cited_by_count":301},{"id":"1704.05939","title":"HPatches: A benchmark and evaluation of handcrafted and learned local descriptors","created":"2017-04-19","cited_by_count":264},{"id":"1503.01817","title":"YFCC100M: The New Data in Multimedia Research","created":"2015-03-05","cited_by_count":235},{"id":"2305.14334","title":"Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence","created":"2023-05-23","cited_by_count":214},{"id":"2306.05422","title":"Tracking Everything Everywhere All at Once","created":"2023-06-08","cited_by_count":193},{"id":"2103.14167","title":"COTR: Correspondence Transformer for Matching Across Images","created":"2021-03-25","cited_by_count":183},{"id":"2202.00667","title":"DKM: Dense Kernelized Feature Matching for Geometry Estimation","created":"2022-02-01","cited_by_count":177},{"id":"2208.14201","title":"ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer","created":"2022-08-30","cited_by_count":171},{"id":"2205.12257","title":"OnePose: One-Shot Object Pose Estimation without CAD Models","created":"2022-05-24","cited_by_count":157},{"id":"1703.05593","title":"Convolutional neural network architecture for geometric matching","created":"2017-03-16","cited_by_count":138},{"id":"2012.01909","title":"Patch2Pix: Epipolar-Guided Pixel-Level Correspondences","created":"2020-12-03","cited_by_count":129},{"id":"2305.15581","title":"Unsupervised Semantic Correspondence Using Stable Diffusion","created":"2023-05-24","cited_by_count":120},{"id":"2403.04765","title":"Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed","created":"2024-03-07","cited_by_count":120},{"id":"2004.10566","title":"Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions","created":"2020-04-22","cited_by_count":93},{"id":"2108.08771","title":"Learning to Match Features with Seeded Graph Matching Network","created":"2021-08-19","cited_by_count":92},{"id":"2311.17034","title":"Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence","created":"2023-11-28","cited_by_count":86},{"id":"2106.02520","title":"CATs: Cost Aggregation Transformers for Visual Correspondence","created":"2021-06-04","cited_by_count":77},{"id":"2304.02008","title":"GlueStick: Robust Image Matching by Sticking Points and Lines Together","created":"2023-04-04","cited_by_count":66},{"id":"2112.05143","title":"GAN-Supervised Dense Visual Alignment","created":"2021-12-09","cited_by_count":62},{"id":"2312.00786","title":"Dense Optical Tracking: Connecting the Dots","created":"2023-12-01","cited_by_count":61},{"id":"1712.06861","title":"End-to-end weakly-supervised semantic alignment","created":"2017-12-19","cited_by_count":60},{"id":"1908.06537","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","created":"2019-08-18","cited_by_count":56},{"id":"2304.06194","title":"SiLK -- Simple Learned Keypoints","created":"2023-04-12","cited_by_count":54},{"id":"2202.06817","title":"CATs++: Boosting Cost Aggregation with Convolutions and Transformers","created":"2022-02-14","cited_by_count":53},{"id":"1705.04043","title":"SCNet: Learning Semantic Correspondence","created":"2017-05-11","cited_by_count":48},{"id":"1703.07144","title":"Proposal Flow: Semantic Correspondences from Object Proposals","created":"2017-03-21","cited_by_count":47},{"id":"2310.17569","title":"SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matching","created":"2023-10-26","cited_by_count":38},{"id":"2304.14845","title":"SFD2: Semantic-guided Feature Detection and Description","created":"2023-04-28","cited_by_count":28},{"id":"2401.17592","title":"Local Feature Matching Using Deep Learning: A Survey","created":"2024-01-31","cited_by_count":26},{"id":"2004.12652","title":"Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos","created":"2020-04-27","cited_by_count":22},{"id":"2303.16624","title":"Adaptive Spot-Guided Transformer for Consistent Local Feature Matching","created":"2023-03-29","cited_by_count":22},{"id":"2205.01694","title":"End2End Multi-View Feature Matching with Differentiable Pose Optimization","created":"2022-05-03","cited_by_count":19},{"id":"2401.16741","title":"MESA: Matching Everything by Segmenting Anything","created":"2024-01-30","cited_by_count":16},{"id":"2312.00065","title":"Unsupervised Keypoints from Pretrained Diffusion Models","created":"2023-11-29","cited_by_count":15},{"id":"2207.05054","title":"Demystifying Unsupervised Semantic Correspondence Estimation","created":"2022-07-11","cited_by_count":10},{"id":"2211.15069","title":"FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural Network","created":"2022-11-28","cited_by_count":10},{"id":"2304.14837","title":"IMP: Iterative Matching and Pose Estimation with Adaptive Pooling","created":"2023-04-28","cited_by_count":10},{"id":"2305.00194","title":"Searching from Area to Point: A Hierarchical Framework for Semantic-Geometric Combined Feature Matching","created":"2023-04-29","cited_by_count":9},{"id":"2311.04336","title":"Efficient Semantic Matching with Hypercolumn Correlation","created":"2023-11-07","cited_by_count":6},{"id":"2401.03785","title":"Identifying Important Group of Pixels using Interactions","created":"2024-01-08","cited_by_count":6},{"id":"2305.04232","title":"CatFLW: Cat Facial Landmarks in the Wild Dataset","created":"2023-05-07","cited_by_count":5}],"next_cursor":null}