{"list":"other","total":95,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"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":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"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":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"id":"2212.02500","title":"PhysDiff: Physics-Guided Human Motion Diffusion Model","created":"2022-12-05","cited_by_count":368},{"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":"2303.01418","title":"Human Motion Diffusion as a Generative Prior","created":"2023-03-02","cited_by_count":357},{"id":"2402.15648","title":"MambaIR: A Simple Baseline for Image Restoration with State-Space Model","created":"2024-02-23","cited_by_count":352},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"id":"2003.14111","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","created":"2020-03-31","cited_by_count":343},{"id":"1607.03827","title":"The KIT Motion-Language Dataset","created":"2016-07-13","cited_by_count":338},{"id":"2107.12213","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","created":"2021-07-26","cited_by_count":322},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"2402.02491","title":"VM-UNet: Vision Mamba UNet for Medical Image Segmentation","created":"2024-02-04","cited_by_count":287},{"id":"2401.13560","title":"SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation","created":"2024-01-24","cited_by_count":266},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"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":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227},{"id":"2305.12577","title":"Guided Motion Diffusion for Controllable Human Motion Synthesis","created":"2023-05-21","cited_by_count":223},{"id":"2212.04495","title":"MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis","created":"2022-12-08","cited_by_count":218},{"id":"2209.00349","title":"FLAME: Free-form Language-based Motion Synthesis & Editing","created":"2022-09-01","cited_by_count":217},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"id":"2305.00976","title":"TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis","created":"2023-05-02","cited_by_count":198},{"id":"2307.16715","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","created":"2023-07-31","cited_by_count":190},{"id":"2004.07514","title":"Local-Global Video-Text Interactions for Temporal Grounding","created":"2020-04-16","cited_by_count":188},{"id":"2402.03302","title":"Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining","created":"2024-02-05","cited_by_count":179},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178},{"id":"2209.04066","title":"TEACH: Temporal Action Composition for 3D Humans","created":"2022-09-09","cited_by_count":176},{"id":"2402.10739","title":"PointMamba: A Simple State Space Model for Point Cloud Analysis","created":"2024-02-16","cited_by_count":167},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"id":"2306.10900","title":"MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators","created":"2023-06-19","cited_by_count":145},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136},{"id":"2206.12037","title":"How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projections","created":"2022-06-24","cited_by_count":122},{"id":"2001.06891","title":"Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences","created":"2020-01-19","cited_by_count":118},{"id":"2204.13686","title":"HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling","created":"2022-04-28","cited_by_count":117},{"id":"2309.00796","title":"AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism","created":"2023-09-02","cited_by_count":117},{"id":"1703.01515","title":"CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos","created":"2017-03-04","cited_by_count":112},{"id":"2312.15004","title":"FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing","created":"2023-12-22","cited_by_count":106},{"id":"1912.06971","title":"Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks","created":"2019-12-15","cited_by_count":103},{"id":"2203.16434","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","created":"2022-03-30","cited_by_count":98},{"id":"2403.14520","title":"Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference","created":"2024-03-21","cited_by_count":97},{"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":"2403.13600","title":"VL-Mamba: Exploring State Space Models for Multimodal Learning","created":"2024-03-20","cited_by_count":93},{"id":"1807.10418","title":"W-TALC: Weakly-supervised Temporal Activity Localization and Classification","created":"2018-07-27","cited_by_count":87},{"id":"2308.06947","title":"Knowing Where to Focus: Event-aware Transformer for Video Grounding","created":"2023-08-14","cited_by_count":79},{"id":"2309.06284","title":"Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model","created":"2023-09-12","cited_by_count":79},{"id":"2402.12192","title":"Pan-Mamba: Effective pan-sharpening with State Space Model","created":"2024-02-19","cited_by_count":73},{"id":"2211.16016","title":"UDE: A Unified Driving Engine for Human Motion Generation","created":"2022-11-29","cited_by_count":67},{"id":"2308.14480","title":"Priority-Centric Human Motion Generation in Discrete Latent Space","created":"2023-08-28","cited_by_count":67},{"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":"2305.09662","title":"Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation","created":"2023-05-16","cited_by_count":56},{"id":"2401.14168","title":"Vivim: a Video Vision Mamba for Medical Video Segmentation","created":"2024-01-25","cited_by_count":52},{"id":"2210.15929","title":"Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training","created":"2022-10-28","cited_by_count":45},{"id":"2311.01015","title":"Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs","created":"2023-11-02","cited_by_count":45},{"id":"2209.13306","title":"Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding","created":"2022-09-27","cited_by_count":42},{"id":"2309.08480","title":"PoseFix: Correcting 3D Human Poses with Natural Language","created":"2023-09-15","cited_by_count":40},{"id":"2312.11538","title":"Iterative Motion Editing with Natural Language","created":"2023-12-15","cited_by_count":40},{"id":"2108.11244","title":"Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction","created":"2021-08-25","cited_by_count":37},{"id":"2305.09381","title":"AMD: Autoregressive Motion Diffusion","created":"2023-05-16","cited_by_count":30},{"id":"2305.08953","title":"Motion Question Answering via Modular Motion Programs","created":"2023-05-15","cited_by_count":27},{"id":"2212.02837","title":"Pretrained Diffusion Models for Unified Human Motion Synthesis","created":"2022-12-06","cited_by_count":26},{"id":"2212.04638","title":"FLAG3D: A 3D Fitness Activity Dataset with Language Instruction","created":"2022-12-09","cited_by_count":23},{"id":"2003.07564","title":"Feedback Graph Convolutional Network for Skeleton-based Action Recognition","created":"2020-03-17","cited_by_count":22},{"id":"1906.06514","title":"PVRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction","created":"2019-06-15","cited_by_count":20},{"id":"2402.07245","title":"Semi-Mamba-UNet: Pixel-Level Contrastive and Pixel-Level Cross-Supervised Visual Mamba-based UNet for Semi-Supervised Medical Image Segmentation","created":"2024-02-11","cited_by_count":20},{"id":"2111.11051","title":"Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition","created":"2021-11-22","cited_by_count":19},{"id":"2308.01850","title":"Synthesizing Long-Term Human Motions with Diffusion Models via Coherent Sampling","created":"2023-08-03","cited_by_count":19},{"id":"2308.09611","title":"Language-guided Human Motion Synthesis with Atomic Actions","created":"2023-08-18","cited_by_count":17},{"id":"2007.06426","title":"Multitask Non-Autoregressive Model for Human Motion Prediction","created":"2020-07-13","cited_by_count":16},{"id":"2308.14500","title":"LAC: Latent Action Composition for Skeleton-based Action Segmentation","created":"2023-08-28","cited_by_count":15},{"id":"2312.10960","title":"Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model","created":"2023-12-18","cited_by_count":13},{"id":"2305.15842","title":"Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language","created":"2023-05-25","cited_by_count":11},{"id":"2311.17408","title":"Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Prediction","created":"2023-11-29","cited_by_count":11},{"id":"2401.11115","title":"MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation","created":"2024-01-20","cited_by_count":10},{"id":"2312.12227","title":"HuTuMotion: Human-Tuned Navigation of Latent Motion Diffusion Models with Minimal Feedback","created":"2023-12-19","cited_by_count":6}],"next_cursor":null}