{"list":"other","total":85,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"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":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"1704.04394","title":"DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents","created":"2017-04-14","cited_by_count":310},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"1804.00175","title":"DeepIM: Deep Iterative Matching for 6D Pose Estimation","created":"2018-03-31","cited_by_count":283},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"1908.07433","title":"Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation","created":"2019-08-20","cited_by_count":218},{"id":"2308.13561","title":"Project Aria: A New Tool for Egocentric Multi-Modal AI Research","created":"2023-08-24","cited_by_count":208},{"id":"1911.04231","title":"PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation","created":"2019-11-11","cited_by_count":204},{"id":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204},{"id":"2305.08275","title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","created":"2023-05-14","cited_by_count":202},{"id":"2003.08111","title":"Transformer Networks for Trajectory Forecasting","created":"2020-03-18","cited_by_count":181},{"id":"2404.04319","title":"SpatialTracker: Tracking Any 2D Pixels in 3D Space","created":"2024-04-05","cited_by_count":181},{"id":"2309.17024","title":"HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World","created":"2023-09-29","cited_by_count":166},{"id":"2205.12257","title":"OnePose: One-Shot Object Pose Estimation without CAD Models","created":"2022-05-24","cited_by_count":157},{"id":"1904.06830","title":"ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging","created":"2019-04-15","cited_by_count":147},{"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":"2403.19046","title":"LITA: Language Instructed Temporal-Localization Assistant","created":"2024-03-27","cited_by_count":125},{"id":"2301.07673","title":"OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models","created":"2023-01-18","cited_by_count":115},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111},{"id":"1905.09035","title":"What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention","created":"2019-05-22","cited_by_count":105},{"id":"2204.07153","title":"What's in your hands? 3D Reconstruction of Generic Objects in Hands","created":"2022-04-14","cited_by_count":90},{"id":"2404.00562","title":"Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction","created":"2024-03-31","cited_by_count":86},{"id":"2203.14628","title":"FS6D: Few-Shot 6D Pose Estimation of Novel Objects","created":"2022-03-28","cited_by_count":81},{"id":"1712.07576","title":"Learning to Act Properly: Predicting and Explaining Affordances from Images","created":"2017-12-20","cited_by_count":74},{"id":"2303.09665","title":"LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding","created":"2023-03-16","cited_by_count":64},{"id":"1502.05908","title":"Learning Descriptors for Object Recognition and 3D Pose Estimation","created":"2015-02-20","cited_by_count":60},{"id":"1904.05250","title":"Next-Active-Object prediction from Egocentric Videos","created":"2019-04-10","cited_by_count":55},{"id":"2312.03391","title":"Action Scene Graphs for Long-Form Understanding of Egocentric Videos","created":"2023-12-06","cited_by_count":51},{"id":"2306.08731","title":"EPIC Fields: Marrying 3D Geometry and Video Understanding","created":"2023-06-14","cited_by_count":49},{"id":"2405.01413","title":"MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors","created":"2024-05-02","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":"2406.09598","title":"Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Tracking","created":"2024-06-13","cited_by_count":48},{"id":"2411.02704","title":"RT-Affordance: Affordances are Versatile Intermediate Representations for Robot Manipulation","created":"2024-11-05","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":"2403.12011","title":"HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data","created":"2024-03-18","cited_by_count":37},{"id":"2307.08243","title":"Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting","created":"2023-07-17","cited_by_count":34},{"id":"2408.10123","title":"Learning Precise Affordances from Egocentric Videos for Robotic Manipulation","created":"2024-08-19","cited_by_count":34},{"id":"2203.13116","title":"Egocentric Prediction of Action Target in 3D","created":"2022-03-24","cited_by_count":31},{"id":"2404.05072","title":"Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind","created":"2024-04-07","cited_by_count":28},{"id":"1905.08855","title":"Looking to Relations for Future Trajectory Forecast","created":"2019-05-21","cited_by_count":23},{"id":"1904.03000","title":"What Object Should I Use? - Task Driven Object Detection","created":"2019-04-05","cited_by_count":22},{"id":"2403.17935","title":"OmniVid: A Generative Framework for Universal Video Understanding","created":"2024-03-26","cited_by_count":22},{"id":"2405.04370","title":"Diff-IP2D: Diffusion-Based Hand-Object Interaction Prediction on Egocentric Videos","created":"2024-05-07","cited_by_count":21},{"id":"2202.12076","title":"Phrase-Based Affordance Detection via Cyclic Bilateral Interaction","created":"2022-02-24","cited_by_count":19},{"id":"2409.02638","title":"MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videos","created":"2024-09-04","cited_by_count":18},{"id":"1603.04908","title":"First Person Action-Object Detection with EgoNet","created":"2016-03-15","cited_by_count":17},{"id":"2308.08303","title":"Leveraging Next-Active Objects for Context-Aware Anticipation in Egocentric Videos","created":"2023-08-16","cited_by_count":16},{"id":"2407.21510","title":"PEAR: Phrase-Based Hand-Object Interaction Anticipation","created":"2024-07-31","cited_by_count":10},{"id":"2405.12509","title":"Active Object Detection with Knowledge Aggregation and Distillation from Large Models","created":"2024-05-21","cited_by_count":8},{"id":"2307.01467","title":"Technical Report for Ego4D Long Term Action Anticipation Challenge 2023","created":"2023-07-04","cited_by_count":7},{"id":"2410.08530","title":"Ego3DT: Tracking Every 3D Object in Ego-centric Videos","created":"2024-10-11","cited_by_count":7}],"next_cursor":null}