{"list":"other","total":90,"rows":[{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"1908.04616","title":"Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data","created":"2019-08-13","cited_by_count":532},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"1905.12681","title":"What Makes Training Multi-Modal Classification Networks Hard?","created":"2019-05-29","cited_by_count":344},{"id":"2301.07525","title":"OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation","created":"2023-01-18","cited_by_count":326},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"2203.15332","title":"Balanced Multimodal Learning via On-the-fly Gradient Modulation","created":"2022-03-29","cited_by_count":264},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"1702.05448","title":"Learning to Detect Human-Object Interactions","created":"2017-02-17","cited_by_count":240},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"2005.00343","title":"The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines","created":"2020-04-29","cited_by_count":225},{"id":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"2101.02692","title":"Where2Act: From Pixels to Actions for Articulated 3D Objects","created":"2021-01-07","cited_by_count":182},{"id":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180},{"id":"2012.11581","title":"Populating 3D Scenes by Learning Human-Scene Interaction","created":"2020-12-21","cited_by_count":164},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155},{"id":"2312.16170","title":"EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI","created":"2023-12-26","cited_by_count":147},{"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":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137},{"id":"1812.04558","title":"Grounded Human-Object Interaction Hotspots from Video","created":"2018-12-11","cited_by_count":129},{"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":"2001.04583","title":"EGO-TOPO: Environment Affordances from Egocentric Video","created":"2020-01-14","cited_by_count":111},{"id":"2305.12411","title":"Synthesizing Diverse Human Motions in 3D Indoor Scenes","created":"2023-05-21","cited_by_count":109},{"id":"2304.00464","title":"UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning","created":"2023-04-02","cited_by_count":107},{"id":"2103.16397","title":"3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding","created":"2021-03-30","cited_by_count":100},{"id":"2204.02445","title":"CHORE: Contact, Human and Object REconstruction from a single RGB image","created":"2022-04-05","cited_by_count":95},{"id":"2206.08312","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","created":"2022-06-16","cited_by_count":95},{"id":"2212.04636","title":"Ego-Body Pose Estimation via Ego-Head Pose Estimation","created":"2022-12-09","cited_by_count":94},{"id":"2009.01439","title":"Learning Dexterous Grasping with Object-Centric Visual Affordances","created":"2020-09-03","cited_by_count":85},{"id":"2202.08432","title":"AKB-48: A Real-World Articulated Object Knowledge Base","created":"2022-02-17","cited_by_count":82},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","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":"1903.05690","title":"Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments","created":"2019-03-13","cited_by_count":72},{"id":"2303.10437","title":"Grounding 3D Object Affordance from 2D Interactions in Images","created":"2023-03-18","cited_by_count":62},{"id":"1811.10698","title":"LSTA: Long Short-Term Attention for Egocentric Action Recognition","created":"2018-11-26","cited_by_count":57},{"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":"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":"2106.15087","title":"O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning","created":"2021-06-29","cited_by_count":46},{"id":"2202.06875","title":"Visual Acoustic Matching","created":"2022-02-14","cited_by_count":45},{"id":"2303.03373","title":"Detecting Human-Object Contact in Images","created":"2023-03-06","cited_by_count":41},{"id":"2101.04924","title":"Learning to Anticipate Egocentric Actions by Imagination","created":"2021-01-13","cited_by_count":40},{"id":"2108.03658","title":"One-Shot Object Affordance Detection in the Wild","created":"2021-08-08","cited_by_count":40},{"id":"2309.08816","title":"EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding","created":"2023-09-15","cited_by_count":40},{"id":"2010.09676","title":"Detecting Hands and Recognizing Physical Contact in the Wild","created":"2020-10-19","cited_by_count":38},{"id":"2211.14154","title":"Interaction Region Visual Transformer for Egocentric Action Anticipation","created":"2022-11-25","cited_by_count":37},{"id":"2202.13519","title":"PartAfford: Part-level Affordance Discovery from 3D Objects","created":"2022-02-28","cited_by_count":36},{"id":"2312.11782","title":"Learning Object State Changes in Videos: An Open-World Perspective","created":"2023-12-19","cited_by_count":36},{"id":"2207.12080","title":"Intention-Conditioned Long-Term Human Egocentric Action Forecasting","created":"2022-07-25","cited_by_count":35},{"id":"2304.06024","title":"Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views","created":"2023-04-12","cited_by_count":33},{"id":"2301.02217","title":"EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding","created":"2023-01-05","cited_by_count":32},{"id":"2311.16495","title":"Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement","created":"2023-11-28","cited_by_count":31},{"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":"2404.04819","title":"Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer","created":"2024-04-07","cited_by_count":29},{"id":"2206.09106","title":"Embodied Scene-aware Human Pose Estimation","created":"2022-06-18","cited_by_count":28},{"id":"2401.08739","title":"EgoGen: An Egocentric Synthetic Data Generator","created":"2024-01-16","cited_by_count":27},{"id":"2011.05558","title":"Intentonomy: a Dataset and Study towards Human Intent Understanding","created":"2020-11-11","cited_by_count":22},{"id":"2207.11365","title":"EgoEnv: Human-centric environment representations from egocentric video","created":"2022-07-22","cited_by_count":22},{"id":"2208.13196","title":"Grounded Affordance from Exocentric View","created":"2022-08-28","cited_by_count":22},{"id":"2202.12076","title":"Phrase-Based Affordance Detection via Cyclic Bilateral Interaction","created":"2022-02-24","cited_by_count":19},{"id":"2212.06301","title":"Egocentric Video Task Translation","created":"2022-12-13","cited_by_count":19},{"id":"2207.01971","title":"DualAfford: Learning Collaborative Visual Affordance for Dual-gripper Manipulation","created":"2022-07-05","cited_by_count":18},{"id":"2309.02120","title":"Multi-label affordance mapping from egocentric vision","created":"2023-09-05","cited_by_count":18},{"id":"2309.08138","title":"Find What You Want: Learning Demand-conditioned Object Attribute Space for Demand-driven Navigation","created":"2023-09-15","cited_by_count":18},{"id":"2110.07692","title":"Shaping embodied agent behavior with activity-context priors from egocentric video","created":"2021-10-14","cited_by_count":17},{"id":"2404.04933","title":"UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection","created":"2024-04-07","cited_by_count":16},{"id":"2302.03292","title":"Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos","created":"2023-02-07","cited_by_count":15},{"id":"2307.15064","title":"Self-Supervised Visual Acoustic Matching","created":"2023-07-27","cited_by_count":14},{"id":"2401.14785","title":"SimpleEgo: Predicting Probabilistic Body Pose from Egocentric Cameras","created":"2024-01-26","cited_by_count":12},{"id":"2307.02041","title":"Multimodal Imbalance-Aware Gradient Modulation for Weakly-supervised Audio-Visual Video Parsing","created":"2023-07-05","cited_by_count":11},{"id":"2404.05206","title":"SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos","created":"2024-04-08","cited_by_count":11},{"id":"2011.07252","title":"Ego2Hands: A Dataset for Egocentric Two-hand Segmentation and Detection","created":"2020-11-14","cited_by_count":9},{"id":"2403.03037","title":"A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives","created":"2024-03-05","cited_by_count":9},{"id":"2306.09172","title":"Action Sensitivity Learning for the Ego4D Episodic Memory Challenge 2023","created":"2023-06-15","cited_by_count":7},{"id":"2405.05552","title":"Bidirectional Progressive Transformer for Interaction Intention Anticipation","created":"2024-05-09","cited_by_count":6}],"next_cursor":null}