{"list":"other","total":70,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"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":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"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":"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":"2304.01116","title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","created":"2023-04-03","cited_by_count":287},{"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":"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":"2305.00976","title":"TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis","created":"2023-05-02","cited_by_count":198},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178},{"id":"2203.15102","title":"Rethinking Semantic Segmentation: A Prototype View","created":"2022-03-28","cited_by_count":140},{"id":"2312.03596","title":"MMM: Generative Masked Motion Model","created":"2023-12-06","cited_by_count":131},{"id":"2309.00796","title":"AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism","created":"2023-09-02","cited_by_count":117},{"id":"2403.07487","title":"Motion Mamba: Efficient and Long Sequence Motion Generation","created":"2024-03-12","cited_by_count":112},{"id":"2103.09382","title":"SPICE: Semantic Pseudo-labeling for Image Clustering","created":"2021-03-17","cited_by_count":104},{"id":"2005.05751","title":"Unpaired Motion Style Transfer from Video to Animation","created":"2020-05-12","cited_by_count":94},{"id":"2311.17135","title":"TLControl: Trajectory and Language Control for Human Motion Synthesis","created":"2023-11-28","cited_by_count":94},{"id":"1912.03330","title":"ClusterFit: Improving Generalization of Visual Representations","created":"2019-12-06","cited_by_count":82},{"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":"2201.04439","title":"Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases","created":"2022-01-12","cited_by_count":72},{"id":"2211.16016","title":"UDE: A Unified Driving Engine for Human Motion Generation","created":"2022-11-29","cited_by_count":67},{"id":"2202.05274","title":"Motion Puzzle: Arbitrary Motion Style Transfer by Body Part","created":"2022-02-10","cited_by_count":64},{"id":"2209.07383","title":"Visual Recognition with Deep Nearest Centroids","created":"2022-09-15","cited_by_count":59},{"id":"2403.19435","title":"BAMM: Bidirectional Autoregressive Motion Model","created":"2024-03-28","cited_by_count":55},{"id":"2208.08165","title":"Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuning","created":"2022-08-17","cited_by_count":54},{"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":"2312.11538","title":"Iterative Motion Editing with Natural Language","created":"2023-12-15","cited_by_count":40},{"id":"2407.12783","title":"SMooDi: Stylized Motion Diffusion Model","created":"2024-07-17","cited_by_count":37},{"id":"2305.02187","title":"CLUSTSEG: Clustering for Universal Segmentation","created":"2023-05-03","cited_by_count":32},{"id":"2406.06508","title":"Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfer","created":"2024-06-10","cited_by_count":31},{"id":"2305.09381","title":"AMD: Autoregressive Motion Diffusion","created":"2023-05-16","cited_by_count":30},{"id":"2401.13505","title":"Generative Human Motion Stylization in Latent Space","created":"2024-01-24","cited_by_count":30},{"id":"2412.14706","title":"EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Space","created":"2024-12-19","cited_by_count":30},{"id":"2008.10162","title":"Hierarchical Style-based Networks for Motion Synthesis","created":"2020-08-24","cited_by_count":23},{"id":"2307.14605","title":"Clustering based Point Cloud Representation Learning for 3D Analysis","created":"2023-07-27","cited_by_count":23},{"id":"2401.02142","title":"GUESS:GradUally Enriching SyntheSis for Text-Driven Human Motion Generation","created":"2024-01-04","cited_by_count":22},{"id":"2303.04599","title":"Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space","created":"2023-03-08","cited_by_count":19},{"id":"2306.11970","title":"RSMT: Real-time Stylized Motion Transition for Characters","created":"2023-06-21","cited_by_count":19},{"id":"2403.06225","title":"MoST: Motion Style Transformer between Diverse Action Contents","created":"2024-03-10","cited_by_count":18},{"id":"2203.02574","title":"Style-ERD: Responsive and Coherent Online Motion Style Transfer","created":"2022-03-04","cited_by_count":17},{"id":"2503.19557","title":"Dance Like a Chicken: Low-Rank Stylization for Human Motion Diffusion","created":"2025-03-25","cited_by_count":16},{"id":"2311.01755","title":"Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detection","created":"2023-11-03","cited_by_count":15},{"id":"2502.06501","title":"Learning Clustering-based Prototypes for Compositional Zero-shot Learning","created":"2025-02-10","cited_by_count":14},{"id":"2503.07390","title":"PersonaBooth: Personalized Text-to-Motion Generation","created":"2025-03-10","cited_by_count":14},{"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":"2204.13314","title":"Region-level Contrastive and Consistency Learning for Semi-Supervised Semantic Segmentation","created":"2022-04-28","cited_by_count":12},{"id":"2403.16646","title":"Clustering Propagation for Universal Medical Image Segmentation","created":"2024-03-25","cited_by_count":12},{"id":"2403.17409","title":"Neural Clustering based Visual Representation Learning","created":"2024-03-26","cited_by_count":12},{"id":"2405.06646","title":"Diffusion-based Human Motion Style Transfer with Semantic Guidance","created":"2024-03-20","cited_by_count":7},{"id":"2503.21775","title":"StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion","created":"2025-03-27","cited_by_count":7},{"id":"2509.04058","title":"SMooGPT: Stylized Motion Generation using Large Language Models","created":"2025-09-04","cited_by_count":4},{"id":"2501.15043","title":"Prompt-Aware Controllable Shadow Removal","created":"2025-01-25","cited_by_count":2},{"id":"2503.11038","title":"ACMo: Attribute Controllable Motion Generation","created":"2025-03-14","cited_by_count":1}],"next_cursor":null}