{"list":"other","total":76,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"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":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"2303.11381","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","created":"2023-03-20","cited_by_count":517},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"2212.02500","title":"PhysDiff: Physics-Guided Human Motion Diffusion Model","created":"2022-12-05","cited_by_count":368},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"2309.16585","title":"Text-to-3D using Gaussian Splatting","created":"2023-09-28","cited_by_count":299},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"2304.12995","title":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head","created":"2023-04-25","cited_by_count":265},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"2305.18752","title":"GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction","created":"2023-05-30","cited_by_count":248},{"id":"2301.06015","title":"Diffusion-based Generation, Optimization, and Planning in 3D Scenes","created":"2023-01-15","cited_by_count":239},{"id":"2310.06773","title":"Uni3D: Exploring Unified 3D Representation at Scale","created":"2023-10-10","cited_by_count":237},{"id":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212},{"id":"2403.01823","title":"RT-H: Action Hierarchies Using Language","created":"2024-03-04","cited_by_count":210},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"id":"2312.06739","title":"SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models","created":"2023-12-11","cited_by_count":177},{"id":"2012.11581","title":"Populating 3D Scenes by Learning Human-Scene Interaction","created":"2020-12-21","cited_by_count":164},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"id":"2007.15649","title":"Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild","created":"2020-07-30","cited_by_count":152},{"id":"2112.11454","title":"GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping","created":"2021-12-21","cited_by_count":144},{"id":"2311.16097","title":"CG-HOI: Contact-Guided 3D Human-Object Interaction Generation","created":"2023-11-27","cited_by_count":138},{"id":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137},{"id":"2012.05522","title":"Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes","created":"2020-12-10","cited_by_count":135},{"id":"2205.00541","title":"COUCH: Towards Controllable Human-Chair Interactions","created":"2022-05-01","cited_by_count":135},{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130},{"id":"2203.13954","title":"GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection","created":"2022-03-26","cited_by_count":120},{"id":"2311.15707","title":"SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation","created":"2023-11-27","cited_by_count":117},{"id":"2312.02949","title":"LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models","created":"2023-12-05","cited_by_count":113},{"id":"2305.14167","title":"DetGPT: Detect What You Need via Reasoning","created":"2023-05-23","cited_by_count":112},{"id":"2312.03913","title":"Controllable Human-Object Interaction Synthesis","created":"2023-12-06","cited_by_count":109},{"id":"2108.10399","title":"Learning Motion Priors for 4D Human Body Capture in 3D Scenes","created":"2021-08-23","cited_by_count":98},{"id":"2305.05662","title":"InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language","created":"2023-05-09","cited_by_count":96},{"id":"2204.02445","title":"CHORE: Contact, Human and Object REconstruction from a single RGB image","created":"2022-04-05","cited_by_count":95},{"id":"2309.07918","title":"Unified Human-Scene Interaction via Prompted Chain-of-Contacts","created":"2023-09-14","cited_by_count":94},{"id":"2312.06553","title":"HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models","created":"2023-12-11","cited_by_count":93},{"id":"2212.10621","title":"Full-Body Articulated Human-Object Interaction","created":"2022-12-20","cited_by_count":78},{"id":"2312.04393","title":"PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction","created":"2023-12-07","cited_by_count":76},{"id":"2311.18836","title":"ChatPose: Chatting about 3D Human Pose","created":"2023-11-30","cited_by_count":72},{"id":"1909.01507","title":"Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense","created":"2019-09-04","cited_by_count":71},{"id":"2109.09913","title":"Physics-based Human Motion Estimation and Synthesis from Videos","created":"2021-09-21","cited_by_count":66},{"id":"2311.06612","title":"PerceptionGPT: Effectively Fusing Visual Perception into LLM","created":"2023-11-11","cited_by_count":59},{"id":"2012.01591","title":"Holistic 3D Human and Scene Mesh Estimation from Single View Images","created":"2020-12-02","cited_by_count":54},{"id":"2309.08480","title":"PoseFix: Correcting 3D Human Poses with Natural Language","created":"2023-09-15","cited_by_count":40},{"id":"2108.08420","title":"D3D-HOI: Dynamic 3D Human-Object Interactions from Videos","created":"2021-08-19","cited_by_count":39},{"id":"2209.02485","title":"Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors","created":"2022-09-06","cited_by_count":30},{"id":"2312.00690","title":"Open-vocabulary object 6D pose estimation","created":"2023-12-01","cited_by_count":29},{"id":"2406.07221","title":"Open-World Human-Object Interaction Detection via Multi-modal Prompts","created":"2024-06-11","cited_by_count":28},{"id":"2110.06901","title":"A Survey on Deep Learning for Skeleton-Based Human Animation","created":"2021-10-13","cited_by_count":27},{"id":"2008.10162","title":"Hierarchical Style-based Networks for Motion Synthesis","created":"2020-08-24","cited_by_count":23},{"id":"2202.00259","title":"Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics","created":"2022-02-01","cited_by_count":22},{"id":"2305.12252","title":"Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Model","created":"2023-05-20","cited_by_count":22},{"id":"2312.09237","title":"Pixel Aligned Language Models","created":"2023-12-14","cited_by_count":17},{"id":"2308.10174","title":"Neural Interactive Keypoint Detection","created":"2023-08-20","cited_by_count":12},{"id":"2304.04140","title":"Semantic Human Parsing via Scalable Semantic Transfer over Multiple Label Domains","created":"2023-04-09","cited_by_count":11},{"id":"2403.11237","title":"FORCE: Physics-aware Human-object Interaction","created":"2024-03-17","cited_by_count":7}],"next_cursor":null}