{"list":"other","total":56,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"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":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611},{"id":"2012.09740","title":"Understanding the Behaviour of Contrastive Loss","created":"2020-12-15","cited_by_count":398},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330},{"id":"2305.15347","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","created":"2023-05-24","cited_by_count":301},{"id":"2307.06135","title":"SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning","created":"2023-07-12","cited_by_count":294},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"1604.03605","title":"What do different evaluation metrics tell us about saliency models?","created":"2016-04-12","cited_by_count":185},{"id":"1812.04558","title":"Grounded Human-Object Interaction Hotspots from Video","created":"2018-12-11","cited_by_count":129},{"id":"2103.14862","title":"TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization","created":"2021-03-27","cited_by_count":123},{"id":"2210.01911","title":"Grounding Language with Visual Affordances over Unstructured Data","created":"2022-10-04","cited_by_count":101},{"id":"2309.07970","title":"Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping","created":"2023-09-14","cited_by_count":91},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82},{"id":"2104.02867","title":"Affordance Transfer Learning for Human-Object Interaction Detection","created":"2021-04-07","cited_by_count":79},{"id":"1803.09125","title":"Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition","created":"2018-03-24","cited_by_count":78},{"id":"2003.12058","title":"Grounded Situation Recognition","created":"2020-03-26","cited_by_count":78},{"id":"1701.01081","title":"SalGAN: Visual Saliency Prediction with Generative Adversarial Networks","created":"2017-01-04","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":"2303.15786","title":"HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models","created":"2023-03-28","cited_by_count":61},{"id":"2303.17811","title":"Zero-shot Referring Image Segmentation with Global-Local Context Features","created":"2023-03-31","cited_by_count":61},{"id":"2209.12941","title":"End-to-End Affordance Learning for Robotic Manipulation","created":"2022-09-26","cited_by_count":57},{"id":"1610.01563","title":"DeepGaze II: Reading fixations from deep features trained on object recognition","created":"2016-10-05","cited_by_count":55},{"id":"1609.01064","title":"A Deep Multi-Level Network for Saliency Prediction","created":"2016-09-05","cited_by_count":54},{"id":"2103.04523","title":"Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization","created":"2021-03-08","cited_by_count":46},{"id":"2303.08268","title":"Chat with the Environment: Interactive Multimodal Perception Using Large Language Models","created":"2023-03-14","cited_by_count":43},{"id":"2303.02401","title":"Open-Vocabulary Affordance Detection in 3D Point Clouds","created":"2023-03-04","cited_by_count":41},{"id":"2309.01093","title":"CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection","created":"2023-09-03","cited_by_count":36},{"id":"2205.13803","title":"Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions","created":"2022-05-27","cited_by_count":34},{"id":"2303.14644","title":"Affordance Grounding from Demonstration Video to Target Image","created":"2023-03-26","cited_by_count":34},{"id":"2209.07147","title":"One-Shot Transfer of Affordance Regions? AffCorrs!","created":"2022-09-15","cited_by_count":31},{"id":"2004.07400","title":"Affordances in Robotic Tasks -- A Survey","created":"2020-04-15","cited_by_count":28},{"id":"2108.05675","title":"Learning Visual Affordance Grounding from Demonstration Videos","created":"2021-08-12","cited_by_count":25},{"id":"1906.09836","title":"Learning Grasp Affordance Reasoning through Semantic Relations","created":"2019-06-24","cited_by_count":23},{"id":"2403.11391","title":"Investigating the Benefits of Projection Head for Representation Learning","created":"2024-03-18","cited_by_count":20},{"id":"2309.09556","title":"Affordance-Driven Next-Best-View Planning for Robotic Grasping","created":"2023-09-18","cited_by_count":16},{"id":"2309.05069","title":"Exploiting CLIP for Zero-shot HOI Detection Requires Knowledge Distillation at Multiple Levels","created":"2023-09-10","cited_by_count":5}],"next_cursor":null}