{"list":"other","total":97,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"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":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2004.07728","title":"Image Quality Assessment: Unifying Structure and Texture Similarity","created":"2020-04-16","cited_by_count":811},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"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":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366},{"id":"2310.11440","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","created":"2023-10-17","cited_by_count":340},{"id":"2303.08320","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","created":"2023-03-15","cited_by_count":331},{"id":"2311.16498","title":"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model","created":"2023-11-27","cited_by_count":330},{"id":"2306.08571","title":"GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image","created":"2023-06-14","cited_by_count":321},{"id":"1808.07371","title":"Everybody Dance Now","created":"2018-08-22","cited_by_count":315},{"id":"2304.01186","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","created":"2023-04-03","cited_by_count":314},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296},{"id":"1905.00953","title":"Omni-Scale Feature Learning for Person Re-Identification","created":"2019-05-02","cited_by_count":295},{"id":"2403.14781","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","created":"2024-03-21","cited_by_count":272},{"id":"2312.09067","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","created":"2023-12-14","cited_by_count":268},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"2401.15977","title":"Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling","created":"2024-01-29","cited_by_count":211},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206},{"id":"2307.00716","title":"JourneyDB: A Benchmark for Generative Image Understanding","created":"2023-07-03","cited_by_count":205},{"id":"2411.04746","title":"Taming Rectified Flow for Inversion and Editing","created":"2024-11-07","cited_by_count":204},{"id":"2406.19680","title":"MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance","created":"2024-06-28","cited_by_count":198},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185},{"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":"2304.06025","title":"DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion","created":"2023-04-12","cited_by_count":167},{"id":"2408.06070","title":"ControlNeXt: Powerful and Efficient Control for Image and Video Generation","created":"2024-08-12","cited_by_count":159},{"id":"2409.16283","title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","created":"2024-09-24","cited_by_count":153},{"id":"2307.00040","title":"DisCo: Disentangled Control for Realistic Human Dance Generation","created":"2023-06-30","cited_by_count":142},{"id":"2311.01813","title":"FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation","created":"2023-11-03","cited_by_count":122},{"id":"2405.17414","title":"Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control","created":"2024-05-27","cited_by_count":117},{"id":"2406.01188","title":"UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation","created":"2024-06-03","cited_by_count":102},{"id":"2411.11922","title":"SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory","created":"2024-11-18","cited_by_count":94},{"id":"2112.02815","title":"Make It Move: Controllable Image-to-Video Generation with Text Descriptions","created":"2021-12-06","cited_by_count":88},{"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":"2411.17697","title":"StableAnimator: High-Quality Identity-Preserving Human Image Animation","created":"2024-11-26","cited_by_count":88},{"id":"2303.15380","title":"Hi4D: 4D Instance Segmentation of Close Human Interaction","created":"2023-03-27","cited_by_count":87},{"id":"2405.18991","title":"EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation","created":"2024-05-29","cited_by_count":77},{"id":"1910.06827","title":"Learning Generalisable Omni-Scale Representations for Person Re-Identification","created":"2019-10-15","cited_by_count":74},{"id":"1807.11152","title":"Pose Guided Human Video Generation","created":"2018-07-30","cited_by_count":67},{"id":"2407.01094","title":"Evaluation of Text-to-Video Generation Models: A Dynamics Perspective","created":"2024-07-01","cited_by_count":67},{"id":"2407.17438","title":"HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation","created":"2024-07-24","cited_by_count":64},{"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":"2503.16421","title":"MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance","created":"2025-03-20","cited_by_count":61},{"id":"2406.08850","title":"COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing","created":"2024-06-13","cited_by_count":59},{"id":"2407.16124","title":"Fr\\'echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos","created":"2024-07-23","cited_by_count":58},{"id":"2012.03796","title":"Pose-Guided Human Animation from a Single Image in the Wild","created":"2020-12-07","cited_by_count":53},{"id":"1711.08682","title":"Deep Video Generation, Prediction and Completion of Human Action Sequences","created":"2017-11-23","cited_by_count":52},{"id":"2311.05461","title":"Control3D: Towards Controllable Text-to-3D Generation","created":"2023-11-09","cited_by_count":46},{"id":"2405.03770","title":"Foundation Models for Video Understanding: A Survey","created":"2024-05-06","cited_by_count":46},{"id":"2405.18525","title":"REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment","created":"2024-05-28","cited_by_count":45},{"id":"2409.01055","title":"Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation","created":"2024-09-02","cited_by_count":42},{"id":"2504.11289","title":"UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer","created":"2025-04-15","cited_by_count":42},{"id":"1910.10093","title":"Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch","created":"2019-10-22","cited_by_count":41},{"id":"2504.01724","title":"DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance","created":"2025-04-02","cited_by_count":36},{"id":"2412.09349","title":"DisPose: Disentangling Pose Guidance for Controllable Human Image Animation","created":"2024-12-12","cited_by_count":35},{"id":"2501.10687","title":"EMO2: End-Effector Guided Audio-Driven Avatar Video Generation","created":"2025-01-18","cited_by_count":33},{"id":"2410.20294","title":"Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions","created":"2024-10-27","cited_by_count":31},{"id":"2203.07931","title":"DialogueNeRF: Towards Realistic Avatar Face-to-Face Conversation Video Generation","created":"2022-03-15","cited_by_count":30},{"id":"2403.12959","title":"WHAC: World-grounded Humans and Cameras","created":"2024-03-19","cited_by_count":30},{"id":"2405.18156","title":"VividPose: Advancing Stable Video Diffusion for Realistic Human Image Animation","created":"2024-05-28","cited_by_count":27},{"id":"2312.05107","title":"DreaMoving: A Human Video Generation Framework based on Diffusion Models","created":"2023-12-08","cited_by_count":25},{"id":"2411.17423","title":"DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters","created":"2024-11-26","cited_by_count":24},{"id":"2501.14677","title":"MatAnyone: Stable Video Matting with Consistent Memory Propagation","created":"2025-01-24","cited_by_count":24},{"id":"2503.11423","title":"TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation","created":"2025-03-14","cited_by_count":24},{"id":"2403.20287","title":"Benchmarking Counterfactual Image Generation","created":"2024-03-29","cited_by_count":22},{"id":"2311.13574","title":"XAGen: 3D Expressive Human Avatars Generation","created":"2023-11-22","cited_by_count":17},{"id":"2405.15758","title":"InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation","created":"2024-05-24","cited_by_count":16},{"id":"2409.18980","title":"IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Web","created":"2024-09-14","cited_by_count":16},{"id":"2308.01854","title":"Reconstructing Three-Dimensional Models of Interacting Humans","created":"2023-08-03","cited_by_count":14},{"id":"2403.19467","title":"Beyond Talking -- Generating Holistic 3D Human Dyadic Motion for Communication","created":"2024-03-28","cited_by_count":14},{"id":"2504.04126","title":"Multi-identity Human Image Animation with Structural Video Diffusion","created":"2025-04-05","cited_by_count":13},{"id":"2404.04363","title":"Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs","created":"2024-04-05","cited_by_count":12},{"id":"2409.04440","title":"Synergy and Synchrony in Couple Dances","created":"2024-09-06","cited_by_count":9},{"id":"2412.16495","title":"Follow-Your-MultiPose: Tuning-Free Multi-Character Text-to-Video Generation via Pose Guidance","created":"2024-12-21","cited_by_count":7},{"id":"2412.14484","title":"Llama Learns to Direct: DirectorLLM for Human-Centric Video Generation","created":"2024-12-19","cited_by_count":6},{"id":"2503.10626","title":"NIL: No-data Imitation Learning by Leveraging Pre-trained Video Diffusion Models","created":"2025-03-13","cited_by_count":5},{"id":"2308.14353","title":"ZhuJiu: A Multi-dimensional, Multi-faceted Chinese Benchmark for Large Language Models","created":"2023-08-28","cited_by_count":4},{"id":"2503.04666","title":"What Are You Doing? A Closer Look at Controllable Human Video Generation","created":"2025-03-06","cited_by_count":3},{"id":"2503.16579","title":"World Knowledge from AI Image Generation for Robot Control","created":"2025-03-20","cited_by_count":1}],"next_cursor":null}