{"list":"other","total":54,"rows":[{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"1511.07247","title":"NetVLAD: CNN architecture for weakly supervised place recognition","created":"2015-11-23","cited_by_count":941},{"id":"2007.11898","title":"ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM","created":"2020-07-23","cited_by_count":878},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"2112.12130","title":"NICE-SLAM: Neural Implicit Scalable Encoding for SLAM","created":"2021-12-22","cited_by_count":589},{"id":"1812.03506","title":"From Coarse to Fine: Robust Hierarchical Localization at Large Scale","created":"2018-12-09","cited_by_count":559},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2104.00681","title":"NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video","created":"2021-04-01","cited_by_count":241},{"id":"2103.01486","title":"Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition","created":"2021-03-02","cited_by_count":238},{"id":"2002.12324","title":"Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC","created":"2020-02-27","cited_by_count":176},{"id":"1912.05909","title":"MAGSAC++, a fast, reliable and accurate robust estimator","created":"2019-12-11","cited_by_count":161},{"id":"2112.07642","title":"EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices","created":"2021-12-14","cited_by_count":139},{"id":"1610.07940","title":"End-to-end Learning of Deep Visual Representations for Image Retrieval","created":"2016-10-25","cited_by_count":122},{"id":"2210.05494","title":"Map-free Visual Relocalization: Metric Pose Relative to a Single Image","created":"2022-10-11","cited_by_count":114},{"id":"2210.10770","title":"LaMAR: Benchmarking Localization and Mapping for Augmented Reality","created":"2022-10-19","cited_by_count":100},{"id":"2204.00559","title":"DFNet: Enhance Absolute Pose Regression with Direct Feature Matching","created":"2022-04-01","cited_by_count":82},{"id":"2204.09443","title":"GIMO: Gaze-Informed Human Motion Prediction in Context","created":"2022-04-20","cited_by_count":81},{"id":"2303.17912","title":"CIRCLE: Capture In Rich Contextual Environments","created":"2023-03-31","cited_by_count":79},{"id":"1908.02484","title":"Expert Sample Consensus Applied to Camera Re-Localization","created":"2019-08-07","cited_by_count":70},{"id":"2007.13867","title":"Robust Image Retrieval-based Visual Localization using Kapture","created":"2020-07-27","cited_by_count":66},{"id":"2207.10762","title":"MeshLoc: Mesh-Based Visual Localization","created":"2022-07-21","cited_by_count":62},{"id":"2305.16487","title":"EgoHumans: An Egocentric 3D Multi-Human Benchmark","created":"2023-05-25","cited_by_count":60},{"id":"1909.09803","title":"Visual Odometry Revisited: What Should Be Learnt?","created":"2019-09-21","cited_by_count":57},{"id":"2211.15658","title":"Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries","created":"2022-11-28","cited_by_count":49},{"id":"2305.01599","title":"EgoLocate: Real-time Motion Capture, Localization, and Mapping with Sparse Body-mounted Sensors","created":"2023-05-02","cited_by_count":48},{"id":"2104.03362","title":"SOLD2: Self-supervised Occlusion-aware Line Description and Detection","created":"2021-04-07","cited_by_count":47},{"id":"2008.02004","title":"Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes","created":"2020-08-05","cited_by_count":31},{"id":"1809.01019","title":"Leveraging Deep Visual Descriptors for Hierarchical Efficient Localization","created":"2018-09-04","cited_by_count":29},{"id":"2205.15761","title":"Investigating the Role of Image Retrieval for Visual Localization -- An exhaustive benchmark","created":"2022-05-31","cited_by_count":27},{"id":"2103.11161","title":"MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans","created":"2021-03-20","cited_by_count":26},{"id":"2110.10355","title":"Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Cameras","created":"2021-10-20","cited_by_count":26},{"id":"2206.08365","title":"Virtual Correspondence: Humans as a Cue for Extreme-View Geometry","created":"2022-06-16","cited_by_count":25},{"id":"2304.07500","title":"The 7th AI City Challenge","created":"2023-04-15","cited_by_count":20},{"id":"1607.06986","title":"Ego2Top: Matching Viewers in Egocentric and Top-view Videos","created":"2016-07-24","cited_by_count":17},{"id":"2204.01268","title":"Improving Monocular Visual Odometry Using Learned Depth","created":"2022-04-04","cited_by_count":17},{"id":"2001.05161","title":"Pose-Assisted Multi-Camera Collaboration for Active Object Tracking","created":"2020-01-15","cited_by_count":16},{"id":"2008.05785","title":"Predicting Visual Overlap of Images Through Interpretable Non-Metric Box Embeddings","created":"2020-08-13","cited_by_count":16},{"id":"2106.14729","title":"Real-Time Multi-View 3D Human Pose Estimation using Semantic Feedback to Smart Edge Sensors","created":"2021-06-28","cited_by_count":16},{"id":"2104.08568","title":"Wide-Baseline Multi-Camera Calibration using Person Re-Identification","created":"2021-04-17","cited_by_count":15},{"id":"2303.03767","title":"Proactive Multi-Camera Collaboration For 3D Human Pose Estimation","created":"2023-03-07","cited_by_count":13},{"id":"1712.03084","title":"An Integrated Platform for Live 3D Human Reconstruction and Motion Capturing","created":"2017-12-08","cited_by_count":12},{"id":"2105.01937","title":"FLEX: Extrinsic Parameters-free Multi-view 3D Human Motion Reconstruction","created":"2021-05-05","cited_by_count":11},{"id":"2209.13906","title":"SmartMocap: Joint Estimation of Human and Camera Motion using Uncalibrated RGB Cameras","created":"2022-09-28","cited_by_count":8},{"id":"1608.08334","title":"Egocentric Meets Top-view","created":"2016-08-30","cited_by_count":7},{"id":"1607.06408","title":"Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking","created":"2016-07-21","cited_by_count":6},{"id":"2209.07393","title":"Online Marker-free Extrinsic Camera Calibration using Person Keypoint Detections","created":"2022-09-15","cited_by_count":6},{"id":"2303.03797","title":"External Camera-based Mobile Robot Pose Estimation for Collaborative Perception with Smart Edge Sensors","created":"2023-03-07","cited_by_count":4},{"id":"2304.12624","title":"Shape-Net: Room Layout Estimation from Panoramic Images Robust to Occlusion using Knowledge Distillation with 3D Shapes as Additional Inputs","created":"2023-04-25","cited_by_count":2}],"next_cursor":null}