{"list":"other","total":52,"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"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":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"2311.16498","title":"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model","created":"2023-11-27","cited_by_count":330},{"id":"2211.10658","title":"EDGE: Editable Dance Generation From Music","created":"2022-11-19","cited_by_count":287},{"id":"2203.13055","title":"Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory","created":"2022-03-24","cited_by_count":212},{"id":"2008.04838","title":"TransNet V2: An effective deep network architecture for fast shot transition detection","created":"2020-08-11","cited_by_count":171},{"id":"2303.11089","title":"EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation","created":"2023-03-20","cited_by_count":142},{"id":"2410.07718","title":"Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation","created":"2024-10-10","cited_by_count":97},{"id":"2212.03741","title":"FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation","created":"2022-12-07","cited_by_count":88},{"id":"2410.10306","title":"Animate-X: Universal Character Image Animation with Enhanced Motion Representation","created":"2024-10-14","cited_by_count":88},{"id":"2311.17590","title":"SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis","created":"2023-11-29","cited_by_count":86},{"id":"2509.14055","title":"Wan-Animate: Unified Character Animation and Replacement with Holistic Replication","created":"2025-09-17","cited_by_count":80},{"id":"2306.10799","title":"SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces","created":"2023-06-19","cited_by_count":68},{"id":"2403.10518","title":"Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives","created":"2024-03-15","cited_by_count":61},{"id":"2503.10076","title":"VMBench: A Benchmark for Perception-Aligned Video Motion Generation","created":"2025-03-13","cited_by_count":49},{"id":"2403.18811","title":"Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment","created":"2024-03-27","cited_by_count":47},{"id":"2403.09471","title":"MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models","created":"2024-03-14","cited_by_count":46},{"id":"2508.12880","title":"Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models","created":"2025-08-18","cited_by_count":36},{"id":"2412.16563","title":"SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis","created":"2024-12-21","cited_by_count":32},{"id":"2211.11248","title":"Video Background Music Generation: Dataset, Method and Evaluation","created":"2022-11-21","cited_by_count":29},{"id":"2507.03905","title":"EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation","created":"2025-07-05","cited_by_count":29},{"id":"2505.21448","title":"OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers","created":"2025-05-27","cited_by_count":27},{"id":"2510.12586","title":"There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-training","created":"2025-10-14","cited_by_count":24},{"id":"2504.10358","title":"FingER: Content Aware Fine-grained Evaluation with Reasoning for AI-Generated Videos","created":"2025-04-14","cited_by_count":22},{"id":"2507.11245","title":"NarrLV: Towards a Comprehensive Narrative-Centric Evaluation for Long Video Generation","created":"2025-07-15","cited_by_count":22},{"id":"2410.20389","title":"Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patterns","created":"2024-10-27","cited_by_count":21},{"id":"2505.17543","title":"MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation","created":"2025-05-23","cited_by_count":18},{"id":"2501.15420","title":"Visual Generation Without Guidance","created":"2025-01-26","cited_by_count":17},{"id":"2504.09209","title":"EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation","created":"2025-04-12","cited_by_count":17},{"id":"2502.17414","title":"X-Dancer: Expressive Music to Human Dance Video Generation","created":"2025-02-24","cited_by_count":15},{"id":"2405.09266","title":"Dance Any Beat: Blending Beats with Visuals in Dance Video Generation","created":"2024-05-15","cited_by_count":14},{"id":"2310.10300","title":"BeatDance: A Beat-Based Model-Agnostic Contrastive Learning Framework for Music-Dance Retrieval","created":"2023-10-16","cited_by_count":12},{"id":"2511.10076","title":"Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints","created":"2025-11-13","cited_by_count":12},{"id":"2511.21029","title":"FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation","created":"2025-11-26","cited_by_count":11},{"id":"2401.01382","title":"Exploring Multi-Modal Control in Music-Driven Dance Generation","created":"2024-01-01","cited_by_count":10},{"id":"2506.14742","title":"SyncTalk++: High-Fidelity and Efficient Synchronized Talking Heads Synthesis Using Gaussian Splatting","created":"2025-06-17","cited_by_count":9},{"id":"2507.00790","title":"LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior Sampling","created":"2025-07-01","cited_by_count":9},{"id":"2412.19123","title":"CoheDancers: Enhancing Interactive Group Dance Generation through Music-Driven Coherence Decomposition","created":"2024-12-26","cited_by_count":8},{"id":"2407.19976","title":"MambaGesture: Enhancing Co-Speech Gesture Generation with Mamba and Disentangled Multi-Modality Fusion","created":"2024-07-29","cited_by_count":6},{"id":"2507.19836","title":"ChoreoMuse: Robust Music-to-Dance Video Generation with Style Transfer and Beat-Adherent Motion","created":"2025-07-26","cited_by_count":4}],"next_cursor":null}