{"list":"other","total":62,"rows":[{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"2202.03026","title":"Context Autoencoder for Self-Supervised Representation Learning","created":"2022-02-07","cited_by_count":297},{"id":"2306.12156","title":"Fast Segment Anything","created":"2023-06-21","cited_by_count":290},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"2101.02692","title":"Where2Act: From Pixels to Actions for Articulated 3D Objects","created":"2021-01-07","cited_by_count":182},{"id":"2312.16217","title":"ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation","created":"2023-12-24","cited_by_count":162},{"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":"2212.09506","title":"CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation","created":"2022-12-16","cited_by_count":118},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111},{"id":"2303.12538","title":"Affordance Diffusion: Synthesizing Hand-Object Interactions","created":"2023-03-21","cited_by_count":110},{"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":"2106.14440","title":"VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects","created":"2021-06-28","cited_by_count":80},{"id":"2403.18036","title":"Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance","created":"2024-03-26","cited_by_count":80},{"id":"2203.02668","title":"Cross Language Image Matching for Weakly Supervised Semantic Segmentation","created":"2022-03-05","cited_by_count":72},{"id":"2401.07487","title":"Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation","created":"2024-01-15","cited_by_count":71},{"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":"2401.06341","title":"AffordanceLLM: Grounding Affordance from Vision Language Models","created":"2024-01-12","cited_by_count":55},{"id":"2306.03899","title":"Towards Label-free Scene Understanding by Vision Foundation Models","created":"2023-06-06","cited_by_count":54},{"id":"2305.05803","title":"Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentation","created":"2023-05-09","cited_by_count":53},{"id":"2305.11173","title":"Going Denser with Open-Vocabulary Part Segmentation","created":"2023-05-18","cited_by_count":51},{"id":"2312.08963","title":"LEMON: Learning 3D Human-Object Interaction Relation from 2D Images","created":"2023-12-14","cited_by_count":49},{"id":"2308.01477","title":"HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructions","created":"2023-08-02","cited_by_count":48},{"id":"2311.17776","title":"One-Shot Open Affordance Learning with Foundation Models","created":"2023-11-29","cited_by_count":45},{"id":"2303.02401","title":"Open-Vocabulary Affordance Detection in 3D Point Clouds","created":"2023-03-04","cited_by_count":41},{"id":"2303.14644","title":"Affordance Grounding from Demonstration Video to Target Image","created":"2023-03-26","cited_by_count":34},{"id":"2305.09664","title":"Understanding 3D Object Interaction from a Single Image","created":"2023-05-16","cited_by_count":33},{"id":"2312.03585","title":"Foundation Model Assisted Weakly Supervised Semantic Segmentation","created":"2023-12-06","cited_by_count":33},{"id":"2106.14747","title":"One-Shot Affordance Detection","created":"2021-06-28","cited_by_count":32},{"id":"2401.12978","title":"Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models","created":"2024-01-23","cited_by_count":32},{"id":"2209.07147","title":"One-Shot Transfer of Affordance Regions? AffCorrs!","created":"2022-09-15","cited_by_count":31},{"id":"2305.01275","title":"Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentation","created":"2023-05-02","cited_by_count":27},{"id":"2403.11289","title":"ManipVQA: Injecting Robotic Affordance and Physically Grounded Information into Multi-Modal Large Language Models","created":"2024-03-17","cited_by_count":25},{"id":"2111.12608","title":"Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing","created":"2021-11-24","cited_by_count":22},{"id":"2208.13196","title":"Grounded Affordance from Exocentric View","created":"2022-08-28","cited_by_count":22},{"id":"2305.01586","title":"An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems","created":"2023-05-02","cited_by_count":19},{"id":"2310.13026","title":"Weakly-Supervised Semantic Segmentation with Image-Level Labels: from Traditional Models to Foundation Models","created":"2023-10-19","cited_by_count":19},{"id":"2302.03292","title":"Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos","created":"2023-02-07","cited_by_count":15},{"id":"2404.11000","title":"OVAL-Prompt: Open-Vocabulary Affordance Localization for Robot Manipulation through LLM Affordance-Grounding","created":"2024-04-17","cited_by_count":15},{"id":"2406.11189","title":"Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation","created":"2024-06-17","cited_by_count":15},{"id":"2407.16696","title":"PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects","created":"2024-07-23","cited_by_count":15},{"id":"2405.12461","title":"WorldAfford: Affordance Grounding based on Natural Language Instructions","created":"2024-05-21","cited_by_count":14},{"id":"2303.00871","title":"Bayesian Deep Learning for Affordance Segmentation in images","created":"2023-03-02","cited_by_count":13},{"id":"2404.12015","title":"What does CLIP know about peeling a banana?","created":"2024-04-18","cited_by_count":9},{"id":"2107.02095","title":"Are standard Object Segmentation models sufficient for Learning Affordance Segmentation?","created":"2021-07-05","cited_by_count":6},{"id":"2404.05603","title":"Self-Explainable Affordance Learning with Embodied Caption","created":"2024-04-08","cited_by_count":4},{"id":"2407.15771","title":"Local Occupancy-Enhanced Object Grasping with Multiple Triplanar Projection","created":"2024-07-22","cited_by_count":2}],"next_cursor":null}