{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2005.04259","title":"VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation","created":"2020-05-08","cited_by_count":530},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"2007.13732","title":"Learning Lane Graph Representations for Motion Forecasting","created":"2020-07-27","cited_by_count":382},{"id":"1903.01945","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2019-03-05","cited_by_count":373},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"2012.13392","title":"Deep Learning-Based Human Pose Estimation: A Survey","created":"2020-12-24","cited_by_count":207},{"id":"2012.11581","title":"Populating 3D Scenes by Learning Human-Scene Interaction","created":"2020-12-21","cited_by_count":164},{"id":"1901.08043","title":"Bottom-up Object Detection by Grouping Extreme and Center Points","created":"2019-01-23","cited_by_count":156},{"id":"1912.09930","title":"Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks","created":"2019-12-20","cited_by_count":114},{"id":"1909.08453","title":"Pose-aware Multi-level Feature Network for Human Object Interaction Detection","created":"2019-09-18","cited_by_count":88},{"id":"2007.03056","title":"VPN: Learning Video-Pose Embedding for Activities of Daily Living","created":"2020-07-06","cited_by_count":57},{"id":"2309.15273","title":"DECO: Dense Estimation of 3D Human-Scene Contact In The Wild","created":"2023-09-26","cited_by_count":54},{"id":"2312.08963","title":"LEMON: Learning 3D Human-Object Interaction Relation from 2D Images","created":"2023-12-14","cited_by_count":49},{"id":"2206.06291","title":"Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection","created":"2022-06-13","cited_by_count":47},{"id":"1712.02310","title":"From Lifestyle Vlogs to Everyday Interactions","created":"2017-12-06","cited_by_count":42},{"id":"2304.08114","title":"ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection","created":"2023-04-17","cited_by_count":41},{"id":"2304.04997","title":"Relational Context Learning for Human-Object Interaction Detection","created":"2023-04-11","cited_by_count":36},{"id":"2207.14192","title":"Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection","created":"2022-07-28","cited_by_count":34},{"id":"1802.07898","title":"Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points","created":"2018-02-22","cited_by_count":33},{"id":"2301.04019","title":"FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection","created":"2023-01-08","cited_by_count":30},{"id":"1908.08391","title":"Learning Object-Action Relations from Bimanual Human Demonstration Using Graph Networks","created":"2019-08-22","cited_by_count":29},{"id":"2308.10305","title":"Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video","created":"2023-08-20","cited_by_count":25},{"id":"2311.09817","title":"Neural-Logic Human-Object Interaction Detection","created":"2023-11-16","cited_by_count":25},{"id":"2010.10095","title":"BiST: Bi-directional Spatio-Temporal Reasoning for Video-Grounded Dialogues","created":"2020-10-20","cited_by_count":22},{"id":"2112.03030","title":"Pose2Room: Understanding 3D Scenes from Human Activities","created":"2021-12-01","cited_by_count":22},{"id":"2405.04771","title":"Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches","created":"2024-05-08","cited_by_count":22},{"id":"1712.08002","title":"Human Action Recognition: Pose-based Attention draws focus to Hands","created":"2017-12-20","cited_by_count":21},{"id":"1604.03692","title":"Learning Social Affordance for Human-Robot Interaction","created":"2016-04-13","cited_by_count":20},{"id":"2007.02355","title":"HoughNet: Integrating near and long-range evidence for bottom-up object detection","created":"2020-07-05","cited_by_count":20},{"id":"2305.17861","title":"Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization","created":"2023-05-29","cited_by_count":20},{"id":"2207.09425","title":"Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos","created":"2022-07-19","cited_by_count":17},{"id":"2103.02758","title":"Learning Asynchronous and Sparse Human-Object Interaction in Videos","created":"2021-03-03","cited_by_count":16},{"id":"2205.01271","title":"Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation","created":"2022-05-03","cited_by_count":16},{"id":"2407.10159","title":"RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentation","created":"2024-07-14","cited_by_count":15},{"id":"2206.01908","title":"Video-based Human-Object Interaction Detection from Tubelet Tokens","created":"2022-06-04","cited_by_count":13},{"id":"2502.02504","title":"Unified Spatial-Temporal Edge-Enhanced Graph Networks for Pedestrian Trajectory Prediction","created":"2025-02-04","cited_by_count":13},{"id":"2108.08633","title":"Spatio-Temporal Interaction Graph Parsing Networks for Human-Object Interaction Recognition","created":"2021-08-19","cited_by_count":12},{"id":"2206.15275","title":"Multiclass-SGCN: Sparse Graph-based Trajectory Prediction with Agent Class Embedding","created":"2022-06-30","cited_by_count":9},{"id":"2502.14676","title":"BP-SGCN: Behavioral Pseudo-Label Informed Sparse Graph Convolution Network for Pedestrian and Heterogeneous Trajectory Prediction","created":"2025-02-20","cited_by_count":9},{"id":"2110.03562","title":"Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions","created":"2021-10-07","cited_by_count":8},{"id":"2308.08370","title":"Agglomerative Transformer for Human-Object Interaction Detection","created":"2023-08-16","cited_by_count":8},{"id":"2302.14581","title":"HopFIR: Hop-wise GraphFormer with Intragroup Joint Refinement for 3D Human Pose Estimation","created":"2023-02-28","cited_by_count":7},{"id":"2410.07912","title":"Understanding Spatio-Temporal Relations in Human-Object Interaction using Pyramid Graph Convolutional Network","created":"2024-10-10","cited_by_count":7},{"id":"1703.00503","title":"Learning Social Affordance Grammar from Videos: Transferring Human Interactions to Human-Robot Interactions","created":"2017-03-01","cited_by_count":5},{"id":"2308.16160","title":"Occ$^2$Net: Robust Image Matching Based on 3D Occupancy Estimation for Occluded Regions","created":"2023-08-14","cited_by_count":5},{"id":"2407.00917","title":"From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos","created":"2024-07-01","cited_by_count":4},{"id":"2112.11834","title":"Bottom-up approaches for multi-person pose estimation and it's applications: A brief review","created":"2021-12-22","cited_by_count":2},{"id":"2406.18691","title":"Geometric Features Enhanced Human-Object Interaction Detection","created":"2024-06-26","cited_by_count":2}],"next_cursor":null}