{"list":"other","total":66,"rows":[{"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":"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":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"1709.03410","title":"One-Shot Learning for Semantic Segmentation","created":"2017-09-11","cited_by_count":337},{"id":"2008.01449","title":"Prior Guided Feature Enrichment Network for Few-Shot Segmentation","created":"2020-08-04","cited_by_count":271},{"id":"2205.04334","title":"Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation","created":"2022-05-09","cited_by_count":243},{"id":"1611.05198","title":"One-Shot Video Object Segmentation","created":"2016-11-16","cited_by_count":235},{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"2106.05210","title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","created":"2021-06-09","cited_by_count":203},{"id":"1604.01850","title":"Joint Detection and Identification Feature Learning for Person Search","created":"2016-04-07","cited_by_count":190},{"id":"1910.02490","title":"Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping","created":"2019-10-06","cited_by_count":184},{"id":"2201.00487","title":"Language as Queries for Referring Video Object Segmentation","created":"2022-01-03","cited_by_count":182},{"id":"1409.7618","title":"Multiple Object Tracking: A Literature Review","created":"2014-09-26","cited_by_count":166},{"id":"1803.08006","title":"Video Object Segmentation with Language Referring Expressions","created":"2018-03-21","cited_by_count":162},{"id":"1604.02531","title":"Person Re-identification in the Wild","created":"2016-04-09","cited_by_count":157},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154},{"id":"2001.06810","title":"See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks","created":"2020-01-19","cited_by_count":138},{"id":"2111.14821","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","created":"2021-11-29","cited_by_count":135},{"id":"1506.08959","title":"A Large-Scale Car Dataset for Fine-Grained Categorization and Verification","created":"2015-06-30","cited_by_count":130},{"id":"2103.07941","title":"Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion","created":"2021-03-14","cited_by_count":129},{"id":"2112.01513","title":"OW-DETR: Open-world Detection Transformer","created":"2021-12-02","cited_by_count":129},{"id":"1903.09254","title":"CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification","created":"2019-03-21","cited_by_count":119},{"id":"2108.03032","title":"Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer","created":"2021-08-06","cited_by_count":116},{"id":"1808.08378","title":"Fusion++: Volumetric Object-Level SLAM","created":"2018-08-25","cited_by_count":98},{"id":"1905.00737","title":"The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation","created":"2019-05-02","cited_by_count":97},{"id":"2207.11549","title":"Self-Support Few-Shot Semantic Segmentation","created":"2022-07-23","cited_by_count":96},{"id":"1709.06750","title":"SegFlow: Joint Learning for Video Object Segmentation and Optical Flow","created":"2017-09-20","cited_by_count":92},{"id":"2303.14652","title":"Hierarchical Dense Correlation Distillation for Few-Shot Segmentation","created":"2023-03-26","cited_by_count":84},{"id":"1903.00268","title":"Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery","created":"2019-03-01","cited_by_count":80},{"id":"1603.08695","title":"Learning to Refine Object Segments","created":"2016-03-29","cited_by_count":67},{"id":"2302.01838","title":"vMAP: Vectorised Object Mapping for Neural Field SLAM","created":"2023-02-03","cited_by_count":67},{"id":"1812.07976","title":"MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM","created":"2018-12-19","cited_by_count":65},{"id":"2008.11516","title":"Making a Case for 3D Convolutions for Object Segmentation in Videos","created":"2020-08-26","cited_by_count":56},{"id":"2108.02958","title":"Learning Meta-class Memory for Few-Shot Semantic Segmentation","created":"2021-08-06","cited_by_count":56},{"id":"1706.06629","title":"Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects","created":"2017-06-20","cited_by_count":47},{"id":"1803.00557","title":"The 2018 DAVIS Challenge on Video Object Segmentation","created":"2018-03-01","cited_by_count":47},{"id":"2010.07820","title":"DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM","created":"2020-10-15","cited_by_count":47},{"id":"2003.13954","title":"FGN: Fully Guided Network for Few-Shot Instance Segmentation","created":"2020-03-31","cited_by_count":46},{"id":"2104.13643","title":"On the Unreasonable Effectiveness of Centroids in Image Retrieval","created":"2021-04-28","cited_by_count":45},{"id":"2005.11052","title":"VDO-SLAM: A Visual Dynamic Object-aware SLAM System","created":"2020-05-22","cited_by_count":40},{"id":"2207.07922","title":"Learning Quality-aware Dynamic Memory for Video Object Segmentation","created":"2022-07-16","cited_by_count":35},{"id":"2212.06826","title":"Look Before You Match: Instance Understanding Matters in Video Object Segmentation","created":"2022-12-13","cited_by_count":34},{"id":"1904.11781","title":"EM-Fusion: Dynamic Object-Level SLAM with Probabilistic Data Association","created":"2019-04-26","cited_by_count":28},{"id":"2008.06226","title":"BriNet: Towards Bridging the Intra-class and Inter-class Gaps in One-Shot Segmentation","created":"2020-08-14","cited_by_count":28},{"id":"1912.01300","title":"Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification","created":"2019-12-03","cited_by_count":22},{"id":"1901.01015","title":"Vehicle Re-Identification: an Efficient Baseline Using Triplet Embedding","created":"2019-01-04","cited_by_count":21},{"id":"2004.05538","title":"Self-Supervised Tuning for Few-Shot Segmentation","created":"2020-04-12","cited_by_count":17},{"id":"2105.05639","title":"FlipReID: Closing the Gap between Training and Inference in Person Re-Identification","created":"2021-05-12","cited_by_count":16},{"id":"1808.00760","title":"Incremental Object Database: Building 3D Models from Multiple Partial Observations","created":"2018-08-02","cited_by_count":15},{"id":"2008.09721","title":"ScribbleBox: Interactive Annotation Framework for Video Object Segmentation","created":"2020-08-22","cited_by_count":14},{"id":"2109.13910","title":"Online Object Model Reconstruction and Reuse for Lifelong Improvement of Robot Manipulation","created":"2021-09-28","cited_by_count":10},{"id":"2209.12744","title":"Baking in the Feature: Accelerating Volumetric Segmentation by Rendering Feature Maps","created":"2022-09-26","cited_by_count":7},{"id":"1708.00197","title":"Video Object Segmentation with Re-identification","created":"2017-08-01","cited_by_count":6},{"id":"2102.03898","title":"AttributeNet: Attribute Enhanced Vehicle Re-Identification","created":"2021-02-07","cited_by_count":6}],"next_cursor":null}