{"list":"other","total":52,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"1909.01377","title":"Deep Equilibrium Models","created":"2019-09-03","cited_by_count":615},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"1702.05448","title":"Learning to Detect Human-Object Interactions","created":"2017-02-17","cited_by_count":240},{"id":"1505.00256","title":"DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving","created":"2015-05-01","cited_by_count":231},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"2104.01538","title":"Hypercorrelation Squeeze for Few-Shot Segmentation","created":"2021-04-04","cited_by_count":193},{"id":"1604.03605","title":"What do different evaluation metrics tell us about saliency models?","created":"2016-04-12","cited_by_count":185},{"id":"2104.13682","title":"HOTR: End-to-End Human-Object Interaction Detection with Transformers","created":"2021-04-28","cited_by_count":183},{"id":"2312.16217","title":"ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation","created":"2023-12-24","cited_by_count":162},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"2211.05272","title":"GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts","created":"2022-11-10","cited_by_count":139},{"id":"1812.04558","title":"Grounded Human-Object Interaction Hotspots from Video","created":"2018-12-11","cited_by_count":129},{"id":"1709.07326","title":"AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection","created":"2017-09-21","cited_by_count":128},{"id":"2012.00924","title":"CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction","created":"2020-12-02","cited_by_count":128},{"id":"2103.16397","title":"3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding","created":"2021-03-30","cited_by_count":100},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82},{"id":"1712.07576","title":"Learning to Act Properly: Predicting and Explaining Affordances from Images","created":"2017-12-20","cited_by_count":74},{"id":"2008.09241","title":"Learning Affordance Landscapes for Interaction Exploration in 3D Environments","created":"2020-08-21","cited_by_count":65},{"id":"2303.09665","title":"LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding","created":"2023-03-16","cited_by_count":64},{"id":"2303.10437","title":"Grounding 3D Object Affordance from 2D Interactions in Images","created":"2023-03-18","cited_by_count":62},{"id":"2112.00246","title":"AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactions","created":"2021-12-01","cited_by_count":57},{"id":"1804.03080","title":"Binge Watching: Scaling Affordance Learning from Sitcoms","created":"2018-04-09","cited_by_count":41},{"id":"2303.03373","title":"Detecting Human-Object Contact in Images","created":"2023-03-06","cited_by_count":41},{"id":"2108.03658","title":"One-Shot Object Affordance Detection in the Wild","created":"2021-08-08","cited_by_count":40},{"id":"2309.01093","title":"CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection","created":"2023-09-03","cited_by_count":36},{"id":"2309.07473","title":"Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objects","created":"2023-09-14","cited_by_count":35},{"id":"2303.14644","title":"Affordance Grounding from Demonstration Video to Target Image","created":"2023-03-26","cited_by_count":34},{"id":"2106.14747","title":"One-Shot Affordance Detection","created":"2021-06-28","cited_by_count":32},{"id":"2205.05677","title":"HULC: 3D Human Motion Capture with Pose Manifold Sampling and Dense Contact Guidance","created":"2022-05-11","cited_by_count":29},{"id":"2210.03954","title":"Contact-aware Human Motion Forecasting","created":"2022-10-08","cited_by_count":27},{"id":"1708.00945","title":"Predicting Human Activities Using Stochastic Grammar","created":"2017-08-02","cited_by_count":22},{"id":"2208.13196","title":"Grounded Affordance from Exocentric View","created":"2022-08-28","cited_by_count":22},{"id":"1807.06775","title":"Visual Affordance and Function Understanding: A Survey","created":"2018-07-18","cited_by_count":20},{"id":"1707.02850","title":"Adaptive Binarization for Weakly Supervised Affordance Segmentation","created":"2017-07-10","cited_by_count":16},{"id":"2209.05802","title":"Learning Agent-Aware Affordances for Closed-Loop Interaction with Articulated Objects","created":"2022-09-13","cited_by_count":16},{"id":"2310.17290","title":"RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environments","created":"2023-10-26","cited_by_count":15},{"id":"2407.21510","title":"PEAR: Phrase-Based Hand-Object Interaction Anticipation","created":"2024-07-31","cited_by_count":10},{"id":"2405.05552","title":"Bidirectional Progressive Transformer for Interaction Intention Anticipation","created":"2024-05-09","cited_by_count":6},{"id":"2407.00614","title":"Learning Granularity-Aware Affordances from Human-Object Interaction for Tool-Based Functional Dexterous Grasping","created":"2024-06-30","cited_by_count":5},{"id":"2112.12886","title":"Rediscovering Affordance: A Reinforcement Learning Perspective","created":"2021-12-24","cited_by_count":4}],"next_cursor":null}