{"list":"other","total":55,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2011.12948","title":"Nerfies: Deformable Neural Radiance Fields","created":"2020-11-25","cited_by_count":1198},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2308.09713","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","created":"2023-08-18","cited_by_count":737},{"id":"2301.09632","title":"HexPlane: A Fast Representation for Dynamic Scenes","created":"2023-01-23","cited_by_count":587},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442},{"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":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250},{"id":"2301.11280","title":"Text-To-4D Dynamic Scene Generation","created":"2023-01-26","cited_by_count":205},{"id":"2312.17142","title":"DreamGaussian4D: Generative 4D Gaussian Splatting","created":"2023-12-28","cited_by_count":194},{"id":"2208.04726","title":"Deep Patch Visual Odometry","created":"2022-08-08","cited_by_count":190},{"id":"2012.05901","title":"Robust Consistent Video Depth Estimation","created":"2020-12-10","cited_by_count":188},{"id":"1905.02082","title":"ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals","created":"2019-05-06","cited_by_count":181},{"id":"2405.17421","title":"MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds","created":"2024-05-27","cited_by_count":179},{"id":"2406.01900","title":"Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation","created":"2024-06-04","cited_by_count":174},{"id":"2406.10324","title":"L4GM: Large 4D Gaussian Reconstruction Model","created":"2024-06-14","cited_by_count":144},{"id":"2405.20674","title":"4Diffusion: Multi-view Video Diffusion Model for 4D Generation","created":"2024-05-31","cited_by_count":104},{"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":"2506.05207","title":"Follow-Your-Motion: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning","created":"2025-06-05","cited_by_count":81},{"id":"2007.13988","title":"Monocular Real-Time Volumetric Performance Capture","created":"2020-07-28","cited_by_count":74},{"id":"2405.02280","title":"DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos","created":"2024-05-03","cited_by_count":63},{"id":"2506.04590","title":"Follow-Your-Creation: Empowering 4D Creation through Video Inpainting","created":"2025-06-05","cited_by_count":62},{"id":"2506.17267","title":"CF-VLM:CounterFactual Vision-Language Fine-tuning","created":"2025-06-10","cited_by_count":59},{"id":"2505.23399","title":"GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning","created":"2025-05-29","cited_by_count":58},{"id":"2509.16630","title":"Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation","created":"2025-09-20","cited_by_count":43},{"id":"2502.07350","title":"KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems","created":"2025-02-11","cited_by_count":37},{"id":"2510.17845","title":"MAT-Agent: Adaptive Multi-Agent Training Optimization","created":"2025-10-10","cited_by_count":35},{"id":"2509.02785","title":"DrDiff: Dynamic Routing Diffusion with Hierarchical Attention for Breaking the Efficiency-Quality Trade-off","created":"2025-09-02","cited_by_count":34},{"id":"2512.08228","title":"MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models","created":"2025-12-09","cited_by_count":34},{"id":"2509.04876","title":"OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration","created":"2025-09-05","cited_by_count":30},{"id":"1808.07471","title":"Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks","created":"2018-08-22","cited_by_count":27},{"id":"2007.09943","title":"TENet: Triple Excitation Network for Video Salient Object Detection","created":"2020-07-20","cited_by_count":26},{"id":"2310.08530","title":"X-Pose: Detecting Any Keypoints","created":"2023-10-12","cited_by_count":21},{"id":"2510.10035","title":"Failure-Driven Workflow Refinement","created":"2025-10-11","cited_by_count":20},{"id":"2512.08240","title":"Hybrid Token Compression for Vision-Language Models","created":"2025-12-09","cited_by_count":20},{"id":"2404.14410","title":"Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses","created":"2024-04-22","cited_by_count":17},{"id":"2510.11978","title":"Learning Dynamics of VLM Finetuning","created":"2025-10-13","cited_by_count":17},{"id":"2510.22391","title":"Top-Down Semantic Refinement for Image Captioning","created":"2025-10-25","cited_by_count":16},{"id":"2512.18623","title":"LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction","created":"2025-12-21","cited_by_count":15},{"id":"2309.05418","title":"FlowIBR: Leveraging Pre-Training for Efficient Neural Image-Based Rendering of Dynamic Scenes","created":"2023-09-11","cited_by_count":14},{"id":"2510.22710","title":"RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability","created":"2025-10-26","cited_by_count":14},{"id":"2511.13193","title":"Cost-Effective Communication: An Auction-based Method for Language Agent Interaction","created":"2025-11-17","cited_by_count":14},{"id":"2503.16422","title":"1000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering","created":"2025-03-20","cited_by_count":13},{"id":"1712.02250","title":"Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation","created":"2017-12-06","cited_by_count":12},{"id":"2511.13211","title":"3DAlign-DAER: Dynamic Attention Policy and Efficient Retrieval Strategy for Fine-grained 3D-Text Alignment at Scale","created":"2025-11-17","cited_by_count":12},{"id":"2005.00069","title":"Occlusion resistant learning of intuitive physics from videos","created":"2020-04-30","cited_by_count":8},{"id":"2405.17187","title":"Memorize What Matters: Emergent Scene Decomposition from Multitraverse","created":"2024-05-27","cited_by_count":8},{"id":"2512.18477","title":"STORM: Search-Guided Generative World Models for Robotic Manipulation","created":"2025-12-20","cited_by_count":7},{"id":"2303.00050","title":"Dynamic Multi-View Scene Reconstruction Using Neural Implicit Surface","created":"2023-02-28","cited_by_count":6},{"id":"2411.06602","title":"Adaptive and Temporally Consistent Gaussian Surfels for Multi-view Dynamic Reconstruction","created":"2024-11-10","cited_by_count":5}],"next_cursor":null}