{"list":"other","total":97,"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"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":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"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":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"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":"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":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"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":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2304.08465","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","created":"2023-04-17","cited_by_count":727},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2310.19512","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","created":"2023-10-30","cited_by_count":535},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"id":"2302.13848","title":"ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation","created":"2023-02-27","cited_by_count":416},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"id":"2309.15103","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","created":"2023-09-26","cited_by_count":349},{"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":"2309.15818","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","created":"2023-09-27","cited_by_count":302},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"2411.19108","title":"Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model","created":"2024-11-28","cited_by_count":269},{"id":"2405.01434","title":"StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation","created":"2024-05-02","cited_by_count":247},{"id":"2304.00186","title":"Subject-driven Text-to-Image Generation via Apprenticeship Learning","created":"2023-04-01","cited_by_count":212},{"id":"2302.01329","title":"Dreamix: Video Diffusion Models are General Video Editors","created":"2023-02-02","cited_by_count":191},{"id":"2312.04433","title":"DreamVideo: Composing Your Dream Videos with Customized Subject and Motion","created":"2023-12-07","cited_by_count":188},{"id":"2406.01900","title":"Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation","created":"2024-06-04","cited_by_count":174},{"id":"2310.08465","title":"MotionDirector: Motion Customization of Text-to-Video Diffusion Models","created":"2023-10-12","cited_by_count":173},{"id":"2411.17440","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","created":"2024-11-26","cited_by_count":158},{"id":"2304.08477","title":"Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation","created":"2023-04-17","cited_by_count":137},{"id":"2311.17009","title":"Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer","created":"2023-11-28","cited_by_count":124},{"id":"2404.15275","title":"ID-Animator: Zero-Shot Identity-Preserving Human Video Generation","created":"2024-04-23","cited_by_count":124},{"id":"2204.08129","title":"Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding","created":"2022-04-18","cited_by_count":103},{"id":"2406.01188","title":"UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation","created":"2024-06-03","cited_by_count":102},{"id":"2406.17758","title":"MotionBooth: Motion-Aware Customized Text-to-Video Generation","created":"2024-06-25","cited_by_count":93},{"id":"2312.09109","title":"VideoLCM: Video Latent Consistency Model","created":"2023-12-14","cited_by_count":92},{"id":"2410.10306","title":"Animate-X: Universal Character Image Animation with Enhanced Motion Representation","created":"2024-10-14","cited_by_count":88},{"id":"2312.00845","title":"VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models","created":"2023-12-01","cited_by_count":86},{"id":"2312.12490","title":"InstructVideo: Instructing Video Diffusion Models with Human Feedback","created":"2023-12-19","cited_by_count":86},{"id":"2303.13495","title":"ReVersion: Diffusion-Based Relation Inversion from Images","created":"2023-03-23","cited_by_count":82},{"id":"2404.01647","title":"EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis","created":"2024-04-02","cited_by_count":80},{"id":"2401.09962","title":"CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects","created":"2024-01-18","cited_by_count":77},{"id":"2412.18597","title":"DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation","created":"2024-12-24","cited_by_count":74},{"id":"2501.04698","title":"ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning","created":"2025-01-08","cited_by_count":68},{"id":"2501.06187","title":"Multi-subject Open-set Personalization in Video Generation","created":"2025-01-10","cited_by_count":66},{"id":"2408.13239","title":"CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities","created":"2024-08-23","cited_by_count":60},{"id":"2501.08453","title":"Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models","created":"2025-01-14","cited_by_count":60},{"id":"2402.09368","title":"Magic-Me: Identity-Specific Video Customized Diffusion","created":"2024-02-14","cited_by_count":59},{"id":"2311.18830","title":"MotionEditor: Editing Video Motion via Content-Aware Diffusion","created":"2023-11-30","cited_by_count":57},{"id":"2209.01814","title":"RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection","created":"2022-09-05","cited_by_count":55},{"id":"2402.14780","title":"Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models","created":"2024-02-22","cited_by_count":55},{"id":"2312.15770","title":"A Recipe for Scaling up Text-to-Video Generation with Text-free Videos","created":"2023-12-25","cited_by_count":51},{"id":"2312.04483","title":"Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation","created":"2023-12-07","cited_by_count":50},{"id":"2407.08674","title":"Still-Moving: Customized Video Generation without Customized Video Data","created":"2024-07-11","cited_by_count":50},{"id":"2502.04299","title":"MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation","created":"2025-02-06","cited_by_count":50},{"id":"2312.05390","title":"NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Models","created":"2023-12-08","cited_by_count":47},{"id":"2410.13830","title":"DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control","created":"2024-10-17","cited_by_count":43},{"id":"2403.06375","title":"FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization","created":"2024-03-11","cited_by_count":39},{"id":"2403.20193","title":"Motion Inversion for Video Customization","created":"2024-03-29","cited_by_count":30},{"id":"2405.20325","title":"MotionFollower: Editing Video Motion via Lightweight Score-Guided Diffusion","created":"2024-05-30","cited_by_count":29},{"id":"2411.17048","title":"PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation","created":"2024-11-26","cited_by_count":29},{"id":"2403.12002","title":"DreamMotion: Space-Time Self-Similar Score Distillation for Zero-Shot Video Editing","created":"2024-03-18","cited_by_count":28},{"id":"2312.12155","title":"Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval","created":"2023-12-19","cited_by_count":27},{"id":"2403.01901","title":"FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio","created":"2024-03-04","cited_by_count":20},{"id":"2405.12796","title":"DisenStudio: Customized Multi-subject Text-to-Video Generation with Disentangled Spatial Control","created":"2024-05-21","cited_by_count":20},{"id":"2502.13995","title":"FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation","created":"2025-02-19","cited_by_count":18},{"id":"2412.03085","title":"Mimir: Improving Video Diffusion Models for Precise Text Understanding","created":"2024-12-04","cited_by_count":16},{"id":"2412.19645","title":"VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Models","created":"2024-12-27","cited_by_count":16},{"id":"2412.10533","title":"SUGAR: Subject-Driven Video Customization in a Zero-Shot Manner","created":"2024-12-13","cited_by_count":12},{"id":"2502.06527","title":"CustomVideoX: 3D Reference Attention Driven Dynamic Adaptation for Zero-Shot Customized Video Diffusion Transformers","created":"2025-02-10","cited_by_count":11},{"id":"2104.00356","title":"Exploiting Relationship for Complex-scene Image Generation","created":"2021-04-01","cited_by_count":9},{"id":"2410.23280","title":"DreamRelation: Bridging Customization and Relation Generation","created":"2024-10-30","cited_by_count":9},{"id":"2503.03708","title":"Rethinking Video Tokenization: A Conditioned Diffusion-based Approach","created":"2025-03-05","cited_by_count":9},{"id":"2408.09397","title":"Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony","created":"2024-08-18","cited_by_count":6},{"id":"2412.15491","title":"GCA-3D: Towards Generalized and Consistent Domain Adaptation of 3D Generators","created":"2024-12-20","cited_by_count":4}],"next_cursor":null}