{"list":"other","total":105,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"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":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2312.16256","title":"DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision","created":"2023-12-26","cited_by_count":537},{"id":"2409.02048","title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","created":"2024-09-03","cited_by_count":403},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296},{"id":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276},{"id":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255},{"id":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250},{"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":"1801.01973","title":"A Note on the Inception Score","created":"2018-01-06","cited_by_count":226},{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226},{"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":"2307.00716","title":"JourneyDB: A Benchmark for Generative Image Understanding","created":"2023-07-03","cited_by_count":205},{"id":"2406.08801","title":"Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation","created":"2024-06-13","cited_by_count":202},{"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":"2407.08136","title":"EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions","created":"2024-07-11","cited_by_count":196},{"id":"2305.03027","title":"NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads","created":"2023-05-04","cited_by_count":194},{"id":"2403.17694","title":"AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation","created":"2024-03-26","cited_by_count":194},{"id":"2205.03409","title":"VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution","created":"2022-05-06","cited_by_count":176},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174},{"id":"1804.03619","title":"Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation","created":"2018-04-10","cited_by_count":162},{"id":"2403.07420","title":"DragAnything: Motion Control for Anything using Entity Representation","created":"2024-03-12","cited_by_count":159},{"id":"2311.10982","title":"Make Pixels Dance: High-Dynamic Video Generation","created":"2023-11-18","cited_by_count":140},{"id":"2402.02309","title":"Jailbreaking Attack against Multimodal Large Language Model","created":"2024-02-04","cited_by_count":135},{"id":"2402.04324","title":"ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation","created":"2024-02-06","cited_by_count":132},{"id":"2502.01061","title":"OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models","created":"2025-02-03","cited_by_count":129},{"id":"2412.00733","title":"Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer","created":"2024-12-01","cited_by_count":122},{"id":"2402.01566","title":"Boximator: Generating Rich and Controllable Motions for Video Synthesis","created":"2024-02-02","cited_by_count":107},{"id":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104},{"id":"2409.02634","title":"Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency","created":"2024-09-04","cited_by_count":102},{"id":"2405.16645","title":"Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models","created":"2024-05-26","cited_by_count":100},{"id":"2507.16869","title":"Controllable Video Generation: A Survey","created":"2025-07-22","cited_by_count":98},{"id":"2410.07718","title":"Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation","created":"2024-10-10","cited_by_count":97},{"id":"2410.10306","title":"Animate-X: Universal Character Image Animation with Enhanced Motion Representation","created":"2024-10-14","cited_by_count":88},{"id":"2406.02511","title":"V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation","created":"2024-06-04","cited_by_count":86},{"id":"2506.18866","title":"OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation","created":"2025-06-23","cited_by_count":83},{"id":"2006.13846","title":"Understanding SSIM","created":"2020-06-24","cited_by_count":77},{"id":"2504.04842","title":"FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis","created":"2025-04-07","cited_by_count":77},{"id":"2411.16331","title":"Sonic: Shifting Focus to Global Audio Perception in Portrait Animation","created":"2024-11-25","cited_by_count":72},{"id":"2505.20156","title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters","created":"2025-05-26","cited_by_count":69},{"id":"2411.04989","title":"SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation","created":"2024-11-07","cited_by_count":68},{"id":"2407.07860","title":"Controlling Space and Time with Diffusion Models","created":"2024-07-10","cited_by_count":66},{"id":"2407.17438","title":"HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation","created":"2024-07-24","cited_by_count":64},{"id":"2409.16160","title":"MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling","created":"2024-09-24","cited_by_count":64},{"id":"2408.13239","title":"CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities","created":"2024-08-23","cited_by_count":60},{"id":"2503.18860","title":"HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation","created":"2025-03-24","cited_by_count":59},{"id":"2502.10059","title":"RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control","created":"2025-02-14","cited_by_count":57},{"id":"2508.15761","title":"Waver: Wave Your Way to Lifelike Video Generation","created":"2025-08-21","cited_by_count":52},{"id":"2401.04468","title":"MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation","created":"2024-01-09","cited_by_count":48},{"id":"2502.01572","title":"MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation","created":"2025-02-03","cited_by_count":45},{"id":"2508.08248","title":"StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation","created":"2025-08-11","cited_by_count":44},{"id":"1605.07116","title":"A Formal Evaluation of PSNR as Quality Measurement Parameter for Image Segmentation Algorithms","created":"2016-05-23","cited_by_count":42},{"id":"2405.11794","title":"ViViD: Video Virtual Try-on using Diffusion Models","created":"2024-05-20","cited_by_count":42},{"id":"2410.11795","title":"Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices","created":"2024-10-15","cited_by_count":41},{"id":"2412.15214","title":"LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis","created":"2024-12-19","cited_by_count":39},{"id":"2409.06202","title":"RealisDance: Equip controllable character animation with realistic hands","created":"2024-09-10","cited_by_count":37},{"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":"2501.10687","title":"EMO2: End-Effector Guided Audio-Driven Avatar Video Generation","created":"2025-01-18","cited_by_count":33},{"id":"2502.10841","title":"SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers","created":"2025-02-15","cited_by_count":33},{"id":"2312.13964","title":"PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models","created":"2023-12-21","cited_by_count":30},{"id":"2411.17048","title":"PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation","created":"2024-11-26","cited_by_count":29},{"id":"2506.03099","title":"TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models","created":"2025-06-03","cited_by_count":26},{"id":"2412.07730","title":"STIV: Scalable Text and Image Conditioned Video Generation","created":"2024-12-10","cited_by_count":25},{"id":"2308.16909","title":"StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generation","created":"2023-08-31","cited_by_count":19},{"id":"2503.14325","title":"LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models","created":"2025-03-18","cited_by_count":17},{"id":"2508.02807","title":"DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework","created":"2025-08-04","cited_by_count":17},{"id":"2503.05978","title":"MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice","created":"2025-03-07","cited_by_count":16},{"id":"2411.13552","title":"REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents","created":"2024-11-20","cited_by_count":14},{"id":"2503.19383","title":"MVPortrait: Text-Guided Motion and Emotion Control for Multi-view Vivid Portrait Animation","created":"2025-03-25","cited_by_count":14},{"id":"2403.01800","title":"AtomoVideo: High Fidelity Image-to-Video Generation","created":"2024-03-04","cited_by_count":12},{"id":"2503.00948","title":"Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think","created":"2025-03-02","cited_by_count":12},{"id":"2602.21818","title":"SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model","created":"2026-02-25","cited_by_count":12},{"id":"2505.16980","title":"Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction","created":"2025-05-22","cited_by_count":11},{"id":"2601.05729","title":"TAGRPO: Boosting GRPO on Image-to-Video Generation with Direct Trajectory Alignment","created":"2026-01-09","cited_by_count":10},{"id":"2503.09733","title":"I2V3D: Controllable image-to-video generation with 3D guidance","created":"2025-03-12","cited_by_count":9},{"id":"2512.06674","title":"RunawayEvil: Jailbreaking the Image-to-Video Generative Models","created":"2025-12-07","cited_by_count":8},{"id":"2602.10113","title":"ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generation","created":"2026-02-10","cited_by_count":8},{"id":"2505.19901","title":"Dynamic-I2V: Exploring Image-to-Video Generation Models via Multimodal LLM","created":"2025-05-26","cited_by_count":6},{"id":"2602.20664","title":"AnimeAgent: Is the Multi-Agent via Image-to-Video models a Good Disney Storytelling Artist?","created":"2026-02-24","cited_by_count":5},{"id":"2603.01000","title":"Let Your Image Move with Your Motion! -- Implicit Multi-Object Multi-Motion Transfer","created":"2026-03-01","cited_by_count":3}],"next_cursor":"100"}