{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2212.02500","title":"PhysDiff: Physics-Guided Human Motion Diffusion Model","created":"2022-12-05","cited_by_count":368},{"id":"2103.11078","title":"AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis","created":"2021-03-20","cited_by_count":339},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"2103.01913","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","created":"2021-03-02","cited_by_count":287},{"id":"2304.01116","title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","created":"2023-04-03","cited_by_count":287},{"id":"1905.08233","title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","created":"2019-05-20","cited_by_count":284},{"id":"1909.04349","title":"FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images","created":"2019-09-10","cited_by_count":271},{"id":"1905.03079","title":"Capture, Learning, and Synthesis of 3D Speaking Styles","created":"2019-05-08","cited_by_count":259},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"1905.03820","title":"Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss","created":"2019-05-09","cited_by_count":252},{"id":"2008.09309","title":"InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image","created":"2020-08-21","cited_by_count":245},{"id":"2402.17485","title":"EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions","created":"2024-02-27","cited_by_count":235},{"id":"1704.07809","title":"Hand Keypoint Detection in Single Images using Multiview Bootstrapping","created":"2017-04-25","cited_by_count":231},{"id":"2203.13055","title":"Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory","created":"2022-03-24","cited_by_count":212},{"id":"2112.05329","title":"FaceFormer: Speech-Driven 3D Facial Animation with Transformers","created":"2021-12-10","cited_by_count":209},{"id":"2009.02119","title":"Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity","created":"2020-09-04","cited_by_count":202},{"id":"1906.04160","title":"Learning Individual Styles of Conversational Gesture","created":"2019-06-10","cited_by_count":191},{"id":"2104.07452","title":"Audio-Driven Emotional Video Portraits","created":"2021-04-15","cited_by_count":180},{"id":"2203.06605","title":"Depth-Aware Generative Adversarial Network for Talking Head Video Generation","created":"2022-03-13","cited_by_count":178},{"id":"1612.03153","title":"Panoptic Studio: A Massively Multiview System for Social Interaction Capture","created":"2016-12-09","cited_by_count":173},{"id":"2303.11089","title":"EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation","created":"2023-03-20","cited_by_count":142},{"id":"2203.13161","title":"Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation","created":"2022-03-24","cited_by_count":107},{"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":"2108.07938","title":"FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute Learning","created":"2021-08-18","cited_by_count":90},{"id":"2006.06119","title":"Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning","created":"2020-06-11","cited_by_count":81},{"id":"2111.03017","title":"MT3: Multi-Task Multitrack Music Transcription","created":"2021-11-04","cited_by_count":71},{"id":"2007.12553","title":"Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach","created":"2020-07-24","cited_by_count":65},{"id":"2010.01815","title":"High-resolution Piano Transcription with Pedals by Regressing Onset and Offset Times","created":"2020-10-05","cited_by_count":61},{"id":"1711.05376","title":"Sliced Wasserstein Distance for Learning Gaussian Mixture Models","created":"2017-11-15","cited_by_count":59},{"id":"2305.09662","title":"Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation","created":"2023-05-16","cited_by_count":56},{"id":"2101.10803","title":"ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning","created":"2021-01-26","cited_by_count":50},{"id":"2008.08213","title":"DeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modeling","created":"2020-08-19","cited_by_count":49},{"id":"2006.14348","title":"Audeo: Audio Generation for a Silent Performance Video","created":"2020-06-23","cited_by_count":47},{"id":"2310.10553","title":"TacticAI: an AI assistant for football tactics","created":"2023-10-16","cited_by_count":44},{"id":"2309.09294","title":"LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation","created":"2023-09-17","cited_by_count":40},{"id":"2204.00604","title":"Quantized GAN for Complex Music Generation from Dance Videos","created":"2022-04-01","cited_by_count":37},{"id":"2310.17768","title":"A Dataset of Relighted 3D Interacting Hands","created":"2023-10-26","cited_by_count":35},{"id":"2011.12999","title":"Learning to dance: A graph convolutional adversarial network to generate realistic dance motions from audio","created":"2020-11-25","cited_by_count":33},{"id":"2304.04150","title":"RoboPianist: Dexterous Piano Playing with Deep Reinforcement Learning","created":"2023-04-09","cited_by_count":30},{"id":"2204.13668","title":"Unaligned Supervision For Automatic Music Transcription in The Wild","created":"2022-04-28","cited_by_count":25},{"id":"1807.01126","title":"Weakly Supervised Deep Recurrent Neural Networks for Basic Dance Step Generation","created":"2018-07-03","cited_by_count":22},{"id":"2307.04305","title":"Automatic Piano Transcription with Hierarchical Frequency-Time Transformer","created":"2023-07-10","cited_by_count":22},{"id":"2210.05148","title":"DiffRoll: Diffusion-based Generative Music Transcription with Unsupervised Pretraining Capability","created":"2022-10-11","cited_by_count":13},{"id":"1905.11142","title":"Audio2Face: Generating Speech/Face Animation from Single Audio with Attention-Based Bidirectional LSTM Networks","created":"2019-05-27","cited_by_count":8},{"id":"2002.03761","title":"Music2Dance: DanceNet for Music-driven Dance Generation","created":"2020-02-02","cited_by_count":6},{"id":"2303.03745","title":"At Your Fingertips: Extracting Piano Fingering Instructions from Videos","created":"2023-03-07","cited_by_count":2}],"next_cursor":null}