{"list":"other","total":79,"rows":[{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"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":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2310.19512","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","created":"2023-10-30","cited_by_count":535},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2310.12190","title":"DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors","created":"2023-10-18","cited_by_count":471},{"id":"2303.09535","title":"FateZero: Fusing Attentions for Zero-shot Text-based Video Editing","created":"2023-03-16","cited_by_count":466},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"id":"2307.10373","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","created":"2023-07-19","cited_by_count":442},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2311.04145","title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","created":"2023-11-07","cited_by_count":350},{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337},{"id":"2305.13077","title":"ControlVideo: Training-free Controllable Text-to-Video Generation","created":"2023-05-22","cited_by_count":327},{"id":"2303.12688","title":"Pix2Video: Video Editing using Image Diffusion","created":"2023-03-22","cited_by_count":320},{"id":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315},{"id":"2303.04761","title":"Video-P2P: Video Editing with Cross-attention Control","created":"2023-03-08","cited_by_count":314},{"id":"2305.10855","title":"TextDiffuser: Diffusion Models as Text Painters","created":"2023-05-18","cited_by_count":229},{"id":"2310.08465","title":"MotionDirector: Motion Customization of Text-to-Video Diffusion Models","created":"2023-10-12","cited_by_count":173},{"id":"2311.03054","title":"AnyText: Multilingual Visual Text Generation And Editing","created":"2023-11-06","cited_by_count":170},{"id":"2503.09642","title":"Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k","created":"2025-03-12","cited_by_count":163},{"id":"2501.09038","title":"Do generative video models understand physical principles?","created":"2025-01-14","cited_by_count":161},{"id":"2403.14468","title":"AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks","created":"2024-03-21","cited_by_count":154},{"id":"2507.05595","title":"PaddleOCR 3.0 Technical Report","created":"2025-07-08","cited_by_count":143},{"id":"2311.16465","title":"TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering","created":"2023-11-28","cited_by_count":140},{"id":"2410.11831","title":"CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos","created":"2024-10-15","cited_by_count":128},{"id":"2312.04524","title":"RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models","created":"2023-12-07","cited_by_count":114},{"id":"2503.05639","title":"VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control","created":"2025-03-07","cited_by_count":84},{"id":"1908.03047","title":"Editing Text in the Wild","created":"2019-08-08","cited_by_count":82},{"id":"2309.16496","title":"CCEdit: Creative and Controllable Video Editing via Diffusion Models","created":"2023-09-28","cited_by_count":82},{"id":"2403.19546","title":"Croissant: A Metadata Format for ML-Ready Datasets","created":"2024-03-28","cited_by_count":81},{"id":"2312.17681","title":"FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis","created":"2023-12-29","cited_by_count":79},{"id":"2312.04884","title":"UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models","created":"2023-12-08","cited_by_count":59},{"id":"2411.15245","title":"AnyText2: Visual Text Generation and Editing With Customizable Attributes","created":"2024-11-22","cited_by_count":53},{"id":"2512.07826","title":"OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing","created":"2025-12-08","cited_by_count":53},{"id":"2003.08152","title":"SwapText: Image Based Texts Transfer in Scenes","created":"2020-03-18","cited_by_count":50},{"id":"2505.03329","title":"FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editing","created":"2025-05-06","cited_by_count":46},{"id":"2304.05568","title":"Improving Diffusion Models for Scene Text Editing with Dual Encoders","created":"2023-04-12","cited_by_count":45},{"id":"2305.10825","title":"DiffUTE: Universal Text Editing Diffusion Model","created":"2023-05-18","cited_by_count":45},{"id":"2410.10133","title":"TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control","created":"2024-10-14","cited_by_count":45},{"id":"2407.07111","title":"Diffusion Model-Based Video Editing: A Survey","created":"2024-06-26","cited_by_count":44},{"id":"2405.12211","title":"Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using Spatio-Temporal Slices","created":"2024-05-20","cited_by_count":40},{"id":"2508.18633","title":"ROSE: Remove Objects with Side Effects in Videos","created":"2025-08-26","cited_by_count":38},{"id":"2212.01982","title":"Exploring Stroke-Level Modifications for Scene Text Editing","created":"2022-12-05","cited_by_count":37},{"id":"2303.17870","title":"GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation","created":"2023-03-31","cited_by_count":34},{"id":"2510.11647","title":"IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment","created":"2025-10-13","cited_by_count":28},{"id":"2412.04508","title":"Video Quality Assessment: A Comprehensive Survey","created":"2024-12-04","cited_by_count":15},{"id":"2109.02762","title":"STRIVE: Scene Text Replacement In Videos","created":"2021-09-06","cited_by_count":13},{"id":"2505.17778","title":"TextFlux: An OCR-Free DiT Model for High-Fidelity Multilingual Scene Text Synthesis","created":"2025-05-23","cited_by_count":13},{"id":"2503.08387","title":"Recognition-Synergistic Scene Text Editing","created":"2025-03-11","cited_by_count":12},{"id":"2409.09668","title":"EditBoard: Towards a Comprehensive Evaluation Benchmark for Text-Based Video Editing Models","created":"2024-09-15","cited_by_count":11},{"id":"2505.04915","title":"GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing","created":"2025-05-08","cited_by_count":11},{"id":"2505.19535","title":"TDVE-Assessor: Benchmarking and Evaluating the Quality of Text-Driven Video Editing with LMMs","created":"2025-05-26","cited_by_count":11},{"id":"2512.00752","title":"Charts Are Not Images: On the Challenges of Scientific Chart Editing","created":"2025-11-30","cited_by_count":11},{"id":"2602.08277","title":"PISCO: Precise Video Instance Insertion with Sparse Control","created":"2026-02-09","cited_by_count":10},{"id":"2602.10113","title":"ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generation","created":"2026-02-10","cited_by_count":8},{"id":"2603.14375","title":"The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics","created":"2026-03-15","cited_by_count":8},{"id":"2408.10623","title":"TextMastero: Mastering High-Quality Scene Text Editing in Diverse Languages and Styles","created":"2024-08-20","cited_by_count":5},{"id":"2603.16864","title":"SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation","created":"2026-03-17","cited_by_count":5},{"id":"2604.16272","title":"VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects","created":"2026-04-17","cited_by_count":4},{"id":"2511.05573","title":"Video Text Preservation with Synthetic Text-Rich Videos","created":"2025-11-04","cited_by_count":3},{"id":"2604.05898","title":"Physics-Aware Video Instance Removal Benchmark","created":"2026-04-07","cited_by_count":3}],"next_cursor":null}