{"list":"other","total":63,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"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":"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":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2308.09713","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","created":"2023-08-18","cited_by_count":737},{"id":"2306.13643","title":"LightGlue: Local Feature Matching at Light Speed","created":"2023-06-23","cited_by_count":590},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"1905.03561","title":"D2-Net: A Trainable CNN for Joint Detection and Description of Local Features","created":"2019-05-09","cited_by_count":326},{"id":"2006.13566","title":"DISK: Learning local features with policy gradient","created":"2020-06-24","cited_by_count":312},{"id":"1603.09114","title":"LIFT: Learned Invariant Feature Transform","created":"2016-03-30","cited_by_count":306},{"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":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287},{"id":"1704.05939","title":"HPatches: A benchmark and evaluation of handcrafted and learned local descriptors","created":"2017-04-19","cited_by_count":264},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263},{"id":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250},{"id":"2204.04153","title":"Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories","created":"2022-04-08","cited_by_count":217},{"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":"2404.04319","title":"SpatialTracker: Tracking Any 2D Pixels in 3D Space","created":"2024-04-05","cited_by_count":181},{"id":"2202.00667","title":"DKM: Dense Kernelized Feature Matching for Geometry Estimation","created":"2022-02-01","cited_by_count":177},{"id":"1810.10510","title":"Neighbourhood Consensus Networks","created":"2018-10-24","cited_by_count":174},{"id":"2208.14201","title":"ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer","created":"2022-08-30","cited_by_count":171},{"id":"2210.10716","title":"CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion","created":"2022-10-19","cited_by_count":160},{"id":"1908.10543","title":"SPair-71k: A Large-scale Benchmark for Semantic Correspondence","created":"2019-08-28","cited_by_count":146},{"id":"1912.05524","title":"GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences","created":"2019-12-11","cited_by_count":139},{"id":"1703.05593","title":"Convolutional neural network architecture for geometric matching","created":"2017-03-16","cited_by_count":138},{"id":"1904.05019","title":"SOSNet: Second Order Similarity Regularization for Local Descriptor Learning","created":"2019-04-10","cited_by_count":131},{"id":"2012.01909","title":"Patch2Pix: Epipolar-Guided Pixel-Level Correspondences","created":"2020-12-03","cited_by_count":129},{"id":"2108.12617","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","created":"2021-08-28","cited_by_count":123},{"id":"2305.15581","title":"Unsupervised Semantic Correspondence Using Stable Diffusion","created":"2023-05-24","cited_by_count":120},{"id":"2404.19174","title":"XFeat: Accelerated Features for Lightweight Image Matching","created":"2024-04-30","cited_by_count":113},{"id":"2311.17034","title":"Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence","created":"2023-11-28","cited_by_count":86},{"id":"1606.03558","title":"Universal Correspondence Network","created":"2016-06-11","cited_by_count":82},{"id":"2407.15420","title":"Local All-Pair Correspondence for Point Tracking","created":"2024-07-22","cited_by_count":80},{"id":"1904.04084","title":"ContextDesc: Local Descriptor Augmentation with Cross-Modality Context","created":"2019-04-08","cited_by_count":79},{"id":"2308.08479","title":"DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching","created":"2023-08-16","cited_by_count":63},{"id":"1712.06861","title":"End-to-end weakly-supervised semantic alignment","created":"2017-12-19","cited_by_count":60},{"id":"1904.01810","title":"SFNet: Learning Object-aware Semantic Correspondence","created":"2019-04-03","cited_by_count":60},{"id":"1511.05065","title":"Proposal Flow","created":"2015-11-16","cited_by_count":57},{"id":"2405.12979","title":"OmniGlue: Generalizable Feature Matching with Foundation Model Guidance","created":"2024-05-21","cited_by_count":56},{"id":"2202.06817","title":"CATs++: Boosting Cost Aggregation with Convolutions and Transformers","created":"2022-02-14","cited_by_count":53},{"id":"1703.07144","title":"Proposal Flow: Semantic Correspondences from Object Proposals","created":"2017-03-21","cited_by_count":47},{"id":"1702.00926","title":"FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence","created":"2017-02-03","cited_by_count":42},{"id":"2203.12870","title":"RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization","created":"2022-03-24","cited_by_count":38},{"id":"2310.17569","title":"SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matching","created":"2023-10-26","cited_by_count":38},{"id":"2208.06974","title":"Learning Semantic Correspondence with Sparse Annotations","created":"2022-08-15","cited_by_count":31},{"id":"2302.03956","title":"Neural Congealing: Aligning Images to a Joint Semantic Atlas","created":"2023-02-08","cited_by_count":31},{"id":"2304.14845","title":"SFD2: Semantic-guided Feature Detection and Description","created":"2023-04-28","cited_by_count":28},{"id":"2004.01673","title":"S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching","created":"2020-04-03","cited_by_count":23},{"id":"1904.02969","title":"Semantic Attribute Matching Networks","created":"2019-04-05","cited_by_count":20},{"id":"2409.02104","title":"DynOMo: Online Point Tracking by Dynamic Online Monocular Gaussian Reconstruction","created":"2024-09-03","cited_by_count":20}],"next_cursor":null}