{"list":"other","total":81,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2206.00927","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","created":"2022-06-02","cited_by_count":1979},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906},{"id":"2304.08465","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","created":"2023-04-17","cited_by_count":727},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2302.03027","title":"Zero-shot Image-to-Image Translation","created":"2023-02-06","cited_by_count":505},{"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":"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":"1607.03827","title":"The KIT Motion-Language Dataset","created":"2016-07-13","cited_by_count":338},{"id":"2103.15679","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","created":"2021-03-29","cited_by_count":320},{"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":"2102.04942","title":"Robust Motion In-betweening","created":"2021-02-09","cited_by_count":229},{"id":"2212.04495","title":"MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis","created":"2022-12-08","cited_by_count":218},{"id":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212},{"id":"2305.00976","title":"TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis","created":"2023-05-02","cited_by_count":198},{"id":"2307.02421","title":"DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models","created":"2023-07-05","cited_by_count":195},{"id":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"id":"1906.02569","title":"Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild","created":"2019-06-06","cited_by_count":178},{"id":"2209.04066","title":"TEACH: Temporal Action Composition for 3D Humans","created":"2022-09-09","cited_by_count":176},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"id":"2303.14613","title":"GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents","created":"2023-03-26","cited_by_count":158},{"id":"2112.07642","title":"EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices","created":"2021-12-14","cited_by_count":139},{"id":"2311.16097","title":"CG-HOI: Contact-Guided 3D Human-Object Interaction Generation","created":"2023-11-27","cited_by_count":138},{"id":"2312.03596","title":"MMM: Generative Masked Motion Model","created":"2023-12-06","cited_by_count":131},{"id":"2004.11207","title":"Self-Attention Attribution: Interpreting Information Interactions Inside Transformer","created":"2020-04-23","cited_by_count":125},{"id":"2005.05732","title":"Skeleton-Aware Networks for Deep Motion Retargeting","created":"2020-05-12","cited_by_count":124},{"id":"2309.00796","title":"AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism","created":"2023-09-02","cited_by_count":117},{"id":"2409.14393","title":"MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting","created":"2024-09-22","cited_by_count":116},{"id":"2305.12411","title":"Synthesizing Diverse Human Motions in 3D Indoor Scenes","created":"2023-05-21","cited_by_count":109},{"id":"1710.05298","title":"Text2Action: Generative Adversarial Synthesis from Language to Action","created":"2017-10-15","cited_by_count":106},{"id":"2101.11101","title":"Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agents","created":"2021-01-26","cited_by_count":106},{"id":"2310.12978","title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","created":"2023-10-19","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":"2401.08559","title":"Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation","created":"2024-01-16","cited_by_count":91},{"id":"2306.05414","title":"Improving Tuning-Free Real Image Editing with Proximal Guidance","created":"2023-06-08","cited_by_count":87},{"id":"2402.15509","title":"Seamless Human Motion Composition with Blended Positional Encodings","created":"2024-02-23","cited_by_count":80},{"id":"2212.10621","title":"Full-Body Articulated Human-Object Interaction","created":"2022-12-20","cited_by_count":78},{"id":"2304.02419","title":"TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration","created":"2023-04-05","cited_by_count":76},{"id":"2211.16016","title":"UDE: A Unified Driving Engine for Human Motion Generation","created":"2022-11-29","cited_by_count":67},{"id":"2403.13900","title":"CoMo: Controllable Motion Generation through Language Guided Pose Code Editing","created":"2024-03-20","cited_by_count":67},{"id":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65},{"id":"2202.05274","title":"Motion Puzzle: Arbitrary Motion Style Transfer by Body Part","created":"2022-02-10","cited_by_count":64},{"id":"2304.10417","title":"SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation","created":"2023-04-20","cited_by_count":64},{"id":"2408.00712","title":"MotionFix: Text-Driven 3D Human Motion Editing","created":"2024-08-01","cited_by_count":64},{"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":"2310.10198","title":"MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations","created":"2023-10-16","cited_by_count":60},{"id":"2206.08010","title":"MoDi: Unconditional Motion Synthesis from Diverse Data","created":"2022-06-16","cited_by_count":59},{"id":"1804.10652","title":"Human Motion Modeling using DVGANs","created":"2018-04-27","cited_by_count":45},{"id":"2312.04547","title":"Digital Life Project: Autonomous 3D Characters with Social Intelligence","created":"2023-12-07","cited_by_count":43},{"id":"2405.15763","title":"FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis","created":"2024-05-24","cited_by_count":42},{"id":"2405.09814","title":"Semantic Gesticulator: Semantics-Aware Co-Speech Gesture Synthesis","created":"2024-05-16","cited_by_count":40},{"id":"2305.18729","title":"Real-World Image Variation by Aligning Diffusion Inversion Chain","created":"2023-05-30","cited_by_count":37},{"id":"2310.14729","title":"MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusion","created":"2023-10-23","cited_by_count":37},{"id":"2407.12783","title":"SMooDi: Stylized Motion Diffusion Model","created":"2024-07-17","cited_by_count":37},{"id":"2007.13886","title":"Perpetual Motion: Generating Unbounded Human Motion","created":"2020-07-27","cited_by_count":36},{"id":"2403.13307","title":"LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment","created":"2024-03-20","cited_by_count":33},{"id":"2401.13505","title":"Generative Human Motion Stylization in Latent Space","created":"2024-01-24","cited_by_count":30},{"id":"2205.02540","title":"Real-time Controllable Motion Transition for Characters","created":"2022-05-05","cited_by_count":29},{"id":"2306.05421","title":"Stochastic Multi-Person 3D Motion Forecasting","created":"2023-06-08","cited_by_count":28},{"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":"2203.05922","title":"Visualizing and Understanding Patch Interactions in Vision Transformer","created":"2022-03-11","cited_by_count":26},{"id":"2312.14828","title":"Plan, Posture and Go: Towards Open-World Text-to-Motion Generation","created":"2023-12-22","cited_by_count":26},{"id":"2404.15383","title":"WANDR: Intention-guided Human Motion Generation","created":"2024-04-23","cited_by_count":26},{"id":"2306.00378","title":"Example-based Motion Synthesis via Generative Motion Matching","created":"2023-06-01","cited_by_count":16},{"id":"2304.14070","title":"Compositional 3D Human-Object Neural Animation","created":"2023-04-27","cited_by_count":9},{"id":"2407.06188","title":"CrowdMoGen: Zero-Shot Text-Driven Collective Motion Generation","created":"2024-07-08","cited_by_count":4},{"id":"2303.16856","title":"Robust Dancer: Long-term 3D Dance Synthesis Using Unpaired Data","created":"2023-03-29","cited_by_count":3}],"next_cursor":null}