{"list":"other","total":70,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"1807.05511","title":"Object Detection with Deep Learning: A Review","created":"2018-07-15","cited_by_count":528},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"id":"2103.02603","title":"Towards Open World Object Detection","created":"2021-03-03","cited_by_count":297},{"id":"1812.01866","title":"Few-shot Object Detection via Feature Reweighting","created":"2018-12-05","cited_by_count":265},{"id":"1911.11462","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","created":"2019-11-26","cited_by_count":249},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"1908.01998","title":"Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector","created":"2019-08-06","cited_by_count":206},{"id":"2209.03494","title":"Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations","created":"2022-09-07","cited_by_count":196},{"id":"1812.04605","title":"DeepV2D: Video to Depth with Differentiable Structure from Motion","created":"2018-12-11","cited_by_count":185},{"id":"1701.08493","title":"A Survey of Structure from Motion","created":"2017-01-30","cited_by_count":158},{"id":"2106.01178","title":"ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection","created":"2021-06-02","cited_by_count":157},{"id":"2011.13244","title":"MVTN: Multi-View Transformation Network for 3D Shape Recognition","created":"2020-11-26","cited_by_count":140},{"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":"2103.17265","title":"Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors","created":"2021-03-31","cited_by_count":137},{"id":"1804.09626","title":"Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos","created":"2018-04-25","cited_by_count":128},{"id":"2001.09691","title":"Multi-Modal Domain Adaptation for Fine-Grained Action Recognition","created":"2020-01-27","cited_by_count":115},{"id":"2112.00431","title":"MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions","created":"2021-12-01","cited_by_count":108},{"id":"2011.14598","title":"Video Self-Stitching Graph Network for Temporal Action Localization","created":"2020-11-30","cited_by_count":104},{"id":"2003.04668","title":"Incremental Few-Shot Object Detection","created":"2020-03-10","cited_by_count":102},{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","cited_by_count":99},{"id":"2212.04636","title":"Ego-Body Pose Estimation via Ego-Head Pose Estimation","created":"2022-12-09","cited_by_count":94},{"id":"2207.09137","title":"ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild","created":"2022-07-19","cited_by_count":92},{"id":"1704.07804","title":"SfM-Net: Learning of Structure and Motion from Video","created":"2017-04-25","cited_by_count":89},{"id":"1907.10045","title":"xR-EgoPose: Egocentric 3D Human Pose from an HMD Camera","created":"2019-07-23","cited_by_count":79},{"id":"1803.05959","title":"Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera","created":"2018-03-15","cited_by_count":68},{"id":"1806.06157","title":"Object Level Visual Reasoning in Videos","created":"2018-06-16","cited_by_count":67},{"id":"2110.09936","title":"NeuralDiff: Segmenting 3D objects that move in egocentric videos","created":"2021-10-19","cited_by_count":57},{"id":"2208.01633","title":"UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture","created":"2022-08-02","cited_by_count":57},{"id":"2104.13454","title":"Estimating Egocentric 3D Human Pose in Global Space","created":"2021-04-27","cited_by_count":56},{"id":"2011.01519","title":"SelfPose: 3D Egocentric Pose Estimation from a Headset Mounted Camera","created":"2020-11-02","cited_by_count":49},{"id":"1603.07763","title":"Seeing Invisible Poses: Estimating 3D Body Pose from Egocentric Video","created":"2016-03-24","cited_by_count":45},{"id":"2210.04932","title":"NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields","created":"2022-10-10","cited_by_count":44},{"id":"2111.01024","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","created":"2021-11-01","cited_by_count":41},{"id":"2103.13164","title":"M3DSSD: Monocular 3D Single Stage Object Detector","created":"2021-03-24","cited_by_count":39},{"id":"2203.09215","title":"HSC4D: Human-centered 4D Scene Capture in Large-scale Indoor-outdoor Space Using Wearable IMUs and LiDAR","created":"2022-03-17","cited_by_count":38},{"id":"2205.01652","title":"Episodic Memory Question Answering","created":"2022-05-03","cited_by_count":32},{"id":"2201.00471","title":"Revisiting Open World Object Detection","created":"2022-01-03","cited_by_count":30},{"id":"2203.14250","title":"End-to-End Active Speaker Detection","created":"2022-03-27","cited_by_count":25},{"id":"2211.10528","title":"Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization","created":"2022-11-18","cited_by_count":24},{"id":"2105.04447","title":"SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation","created":"2021-05-10","cited_by_count":23},{"id":"2203.13903","title":"Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection","created":"2022-03-25","cited_by_count":23},{"id":"2111.15363","title":"Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding","created":"2021-11-30","cited_by_count":22},{"id":"2211.14053","title":"Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization","created":"2022-11-25","cited_by_count":19},{"id":"2204.02509","title":"Depth-Guided Sparse Structure-from-Motion for Movies and TV Shows","created":"2022-04-05","cited_by_count":15},{"id":"2208.01949","title":"Negative Frames Matter in Egocentric Visual Query 2D Localization","created":"2022-08-03","cited_by_count":14},{"id":"2010.13439","title":"On Embodied Visual Navigation in Real Environments Through Habitat","created":"2020-10-26","cited_by_count":9}],"next_cursor":null}