{"list":"other","total":67,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"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":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2207.01696","title":"TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts","created":"2022-07-04","cited_by_count":359},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"1907.01108","title":"Language2Pose: Natural Language Grounded Pose Forecasting","created":"2019-07-02","cited_by_count":257},{"id":"2310.08580","title":"OmniControl: Control Any Joint at Any Time for Human Motion Generation","created":"2023-10-12","cited_by_count":238},{"id":"2306.07207","title":"Valley: Video Assistant with Large Language model Enhanced abilitY","created":"2023-06-12","cited_by_count":234},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227},{"id":"2212.04495","title":"MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis","created":"2022-12-08","cited_by_count":218},{"id":"2311.05437","title":"LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents","created":"2023-11-09","cited_by_count":193},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178},{"id":"2404.19759","title":"MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model","created":"2024-04-30","cited_by_count":168},{"id":"2305.13292","title":"VideoLLM: Modeling Video Sequence with Large Language Models","created":"2023-05-22","cited_by_count":116},{"id":"2312.02949","title":"LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models","created":"2023-12-05","cited_by_count":113},{"id":"2311.16103","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","created":"2023-11-27","cited_by_count":107},{"id":"1710.05298","title":"Text2Action: Generative Adversarial Synthesis from Language to Action","created":"2017-10-15","cited_by_count":106},{"id":"2310.12978","title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","created":"2023-10-19","cited_by_count":104},{"id":"2309.07918","title":"Unified Human-Scene Interaction via Prompted Chain-of-Contacts","created":"2023-09-14","cited_by_count":94},{"id":"2205.13001","title":"Towards Diverse and Natural Scene-aware 3D Human Motion Synthesis","created":"2022-05-25","cited_by_count":91},{"id":"2312.02256","title":"EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation","created":"2023-12-04","cited_by_count":89},{"id":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83},{"id":"2305.12529","title":"DreamWaltz: Make a Scene with Complex 3D Animatable Avatars","created":"2023-05-21","cited_by_count":82},{"id":"2211.16016","title":"UDE: A Unified Driving Engine for Human Motion Generation","created":"2022-11-29","cited_by_count":67},{"id":"2304.14407","title":"ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System","created":"2023-04-27","cited_by_count":65},{"id":"2311.16468","title":"AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond","created":"2023-11-28","cited_by_count":63},{"id":"1705.06400","title":"Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks","created":"2017-05-18","cited_by_count":61},{"id":"2308.09036","title":"Synthesizing Physically Plausible Human Motions in 3D Scenes","created":"2023-08-17","cited_by_count":49},{"id":"2312.00589","title":"Merlin:Empowering Multimodal LLMs with Foresight Minds","created":"2023-11-30","cited_by_count":46},{"id":"2212.05897","title":"MultiAct: Long-Term 3D Human Motion Generation from Multiple Action Labels","created":"2022-12-12","cited_by_count":45},{"id":"2304.04227","title":"Video ChatCaptioner: Towards Enriched Spatiotemporal Descriptions","created":"2023-04-09","cited_by_count":42},{"id":"2311.16511","title":"GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation","created":"2023-11-25","cited_by_count":36},{"id":"2310.16534","title":"An Early Evaluation of GPT-4V(ision)","created":"2023-10-25","cited_by_count":31},{"id":"2305.08953","title":"Motion Question Answering via Modular Motion Programs","created":"2023-05-15","cited_by_count":27},{"id":"2310.10873","title":"IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models","created":"2023-10-16","cited_by_count":27},{"id":"2312.08983","title":"Interactive Humanoid: Online Full-Body Motion Reaction Synthesis with Social Affordance Canonicalization and Forecasting","created":"2023-12-14","cited_by_count":27},{"id":"2203.13815","title":"Versatile Multi-Modal Pre-Training for Human-Centric Perception","created":"2022-03-25","cited_by_count":26},{"id":"2310.10644","title":"TOSS:High-quality Text-guided Novel View Synthesis from a Single Image","created":"2023-10-16","cited_by_count":26},{"id":"2303.08345","title":"Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos","created":"2023-03-15","cited_by_count":23},{"id":"2305.12252","title":"Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Model","created":"2023-05-20","cited_by_count":22},{"id":"2401.06129","title":"Distilling Vision-Language Models on Millions of Videos","created":"2024-01-11","cited_by_count":20},{"id":"2210.05232","title":"DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation","created":"2022-10-11","cited_by_count":9}],"next_cursor":null}