{"list":"other","total":98,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"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":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"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":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"2403.14781","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","created":"2024-03-21","cited_by_count":272},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228},{"id":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212},{"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":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"id":"2412.02700","title":"Motion Prompting: Controlling Video Generation with Motion Trajectories","created":"2024-12-03","cited_by_count":178},{"id":"2407.21705","title":"Tora: Trajectory-oriented Diffusion Transformer for Video Generation","created":"2024-07-31","cited_by_count":164},{"id":"2408.06070","title":"ControlNeXt: Powerful and Efficient Control for Image and Video Generation","created":"2024-08-12","cited_by_count":159},{"id":"2205.00541","title":"COUCH: Towards Controllable Human-Chair Interactions","created":"2022-05-01","cited_by_count":135},{"id":"2212.07555","title":"IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions","created":"2022-12-14","cited_by_count":124},{"id":"2406.10126","title":"Training-free Camera Control for Video Generation","created":"2024-06-14","cited_by_count":122},{"id":"2203.13954","title":"GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection","created":"2022-03-26","cited_by_count":120},{"id":"2501.08331","title":"Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise","created":"2025-01-14","cited_by_count":117},{"id":"2003.05541","title":"VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions","created":"2020-03-11","cited_by_count":115},{"id":"2303.12538","title":"Affordance Diffusion: Synthesizing Hand-Object Interactions","created":"2023-03-21","cited_by_count":110},{"id":"2312.03913","title":"Controllable Human-Object Interaction Synthesis","created":"2023-12-06","cited_by_count":109},{"id":"2503.14492","title":"Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control","created":"2025-03-18","cited_by_count":106},{"id":"2204.02445","title":"CHORE: Contact, Human and Object REconstruction from a single RGB image","created":"2022-04-05","cited_by_count":95},{"id":"2401.00896","title":"TrailBlazer: Trajectory Control for Diffusion-Based Video Generation","created":"2023-12-31","cited_by_count":91},{"id":"2207.12824","title":"Compositional Human-Scene Interaction Synthesis with Semantic Control","created":"2022-07-26","cited_by_count":83},{"id":"2404.10685","title":"Generating Human Interaction Motions in Scenes with Text Control","created":"2024-04-16","cited_by_count":80},{"id":"2212.10621","title":"Full-Body Articulated Human-Object Interaction","created":"2022-12-20","cited_by_count":78},{"id":"2307.07511","title":"NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis","created":"2023-07-14","cited_by_count":78},{"id":"2311.18448","title":"HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video","created":"2023-11-30","cited_by_count":78},{"id":"2502.08639","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation","created":"2025-02-12","cited_by_count":74},{"id":"2412.07759","title":"3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation","created":"2024-12-10","cited_by_count":71},{"id":"2502.04896","title":"Goku: Flow Based Video Generative Foundation Models","created":"2025-02-07","cited_by_count":67},{"id":"2406.17840","title":"Human-Object Interaction from Human-Level Instructions","created":"2024-06-25","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":"2411.19324","title":"Trajectory Attention for Fine-grained Video Motion Control","created":"2024-11-28","cited_by_count":63},{"id":"2303.15786","title":"HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models","created":"2023-03-28","cited_by_count":61},{"id":"2405.14864","title":"Video Diffusion Models are Training-free Motion Interpreter and Controller","created":"2024-05-23","cited_by_count":61},{"id":"2502.06145","title":"Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance","created":"2025-02-10","cited_by_count":61},{"id":"2406.16863","title":"FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models","created":"2024-06-24","cited_by_count":56},{"id":"2502.04299","title":"MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation","created":"2025-02-06","cited_by_count":50},{"id":"2406.19353","title":"CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement","created":"2024-06-27","cited_by_count":44},{"id":"2404.12383","title":"G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis","created":"2024-04-18","cited_by_count":43},{"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":"2505.22944","title":"ATI: Any Trajectory Instruction for Controllable Video Generation","created":"2025-05-28","cited_by_count":43},{"id":"2501.01427","title":"VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control","created":"2025-01-02","cited_by_count":42},{"id":"2303.03373","title":"Detecting Human-Object Contact in Images","created":"2023-03-06","cited_by_count":41},{"id":"2311.17737","title":"GenZI: Zero-Shot 3D Human-Scene Interaction Generation","created":"2023-11-29","cited_by_count":40},{"id":"2412.05263","title":"Mind the Time: Temporally-Controlled Multi-Event Video Generation","created":"2024-12-06","cited_by_count":40},{"id":"2010.09676","title":"Detecting Hands and Recognizing Physical Contact in the Wild","created":"2020-10-19","cited_by_count":38},{"id":"2309.03696","title":"Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory","created":"2023-09-07","cited_by_count":38},{"id":"2502.08244","title":"FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis","created":"2025-02-12","cited_by_count":37},{"id":"2412.05066","title":"BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects","created":"2024-12-06","cited_by_count":30},{"id":"1907.12006","title":"ROAM: Recurrently Optimizing Tracking Model","created":"2019-07-28","cited_by_count":28},{"id":"2503.23715","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","created":"2025-03-31","cited_by_count":26},{"id":"2412.18600","title":"ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation","created":"2024-12-24","cited_by_count":25},{"id":"2303.14005","title":"Category Query Learning for Human-Object Interaction Classification","created":"2023-03-24","cited_by_count":21},{"id":"2404.01758","title":"GEARS: Local Geometry-aware Hand-object Interaction Synthesis","created":"2024-04-02","cited_by_count":20},{"id":"2501.03059","title":"Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation","created":"2025-01-06","cited_by_count":20},{"id":"2211.15663","title":"Hand-Object Interaction Image Generation","created":"2022-11-28","cited_by_count":19},{"id":"2508.05506","title":"MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips","created":"2025-08-07","cited_by_count":17},{"id":"2412.17730","title":"Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimicking","created":"2024-12-23","cited_by_count":16},{"id":"2012.09402","title":"LIGHTEN: Learning Interactions with Graph and Hierarchical TEmporal Networks for HOI in videos","created":"2020-12-17","cited_by_count":14},{"id":"2412.20104","title":"SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis","created":"2024-12-28","cited_by_count":14},{"id":"2506.08797","title":"HunyuanVideo-HOMA: Generic Human-Object Interaction in Multimodal Driven Human Animation","created":"2025-06-10","cited_by_count":14},{"id":"2505.24315","title":"InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing","created":"2025-05-30","cited_by_count":13},{"id":"2507.05963","title":"Tora2: Motion and Appearance Customized Diffusion Transformer for Multi-Entity Video Generation","created":"2025-07-08","cited_by_count":12},{"id":"2510.03135","title":"Mask2IV: Interaction-Centric Video Generation via Mask Trajectories","created":"2025-10-03","cited_by_count":10},{"id":"2407.20566","title":"Monocular Human-Object Reconstruction in the Wild","created":"2024-07-30","cited_by_count":9},{"id":"2503.06012","title":"End-to-End HOI Reconstruction Transformer with Graph-based Encoding","created":"2025-03-08","cited_by_count":8},{"id":"2508.18213","title":"Follow My Hold: Hand-Object Interaction Reconstruction through Geometric Guidance","created":"2025-08-25","cited_by_count":8},{"id":"2111.12747","title":"Layered Controllable Video Generation","created":"2021-11-24","cited_by_count":7},{"id":"2503.18950","title":"Target-Aware Video Diffusion Models","created":"2025-03-24","cited_by_count":7},{"id":"2505.15800","title":"Interspatial Attention for Efficient 4D Human Video Generation","created":"2025-05-21","cited_by_count":7},{"id":"2506.19840","title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","created":"2025-06-24","cited_by_count":6},{"id":"2510.02287","title":"MultiModal Action Conditioned Video Generation","created":"2025-10-02","cited_by_count":3},{"id":"2502.13968","title":"Betsu-Betsu: Multi-View Separable 3D Reconstruction of Two Interacting Objects","created":"2025-02-19","cited_by_count":2},{"id":"2510.08561","title":"MultiCOIN: Multi-Modal COntrollable Video INbetweening","created":"2025-10-09","cited_by_count":2}],"next_cursor":null}