{"list":"other","total":108,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"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":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"2602.15922","title":"World Action Models are Zero-shot Policies","created":"2026-02-17","cited_by_count":465},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2405.10314","title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","created":"2024-05-16","cited_by_count":432},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"2409.02048","title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","created":"2024-09-03","cited_by_count":403},{"id":"2505.09568","title":"BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset","created":"2025-05-14","cited_by_count":376},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341},{"id":"2106.02634","title":"Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering","created":"2021-06-04","cited_by_count":332},{"id":"2409.04429","title":"VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation","created":"2024-09-06","cited_by_count":295},{"id":"1804.00650","title":"DeepMVS: Learning Multi-view Stereopsis","created":"2018-04-02","cited_by_count":277},{"id":"2511.22699","title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","created":"2025-11-27","cited_by_count":277},{"id":"2412.03572","title":"Navigation World Models","created":"2024-12-04","cited_by_count":272},{"id":"2506.15564","title":"Show-o2: Improved Native Unified Multimodal Models","created":"2025-06-18","cited_by_count":250},{"id":"2504.06256","title":"Transfer between Modalities with MetaQueries","created":"2025-04-08","cited_by_count":236},{"id":"1812.00324","title":"CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark","created":"2018-12-02","cited_by_count":214},{"id":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206},{"id":"2412.03069","title":"TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation","created":"2024-12-04","cited_by_count":202},{"id":"2503.14489","title":"Stable Virtual Camera: Generative View Synthesis with Diffusion Models","created":"2025-03-18","cited_by_count":182},{"id":"2604.15804","title":"Qwen3.5-Omni Technical Report","created":"2026-04-17","cited_by_count":174},{"id":"2402.03162","title":"Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion","created":"2024-02-05","cited_by_count":167},{"id":"2406.02509","title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","created":"2024-06-04","cited_by_count":166},{"id":"2606.02800","title":"Cosmos 3: Omnimodal World Models for Physical AI","created":"2026-06-01","cited_by_count":165},{"id":"2407.12781","title":"VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control","created":"2024-07-17","cited_by_count":156},{"id":"2402.14817","title":"Cameras as Rays: Pose Estimation via Ray Diffusion","created":"2024-02-22","cited_by_count":131},{"id":"2108.12617","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","created":"2021-08-28","cited_by_count":123},{"id":"2210.10770","title":"LaMAR: Benchmarking Localization and Mapping for Augmented Reality","created":"2022-10-19","cited_by_count":100},{"id":"2507.07982","title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","created":"2025-07-10","cited_by_count":96},{"id":"2412.07679","title":"RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models","created":"2024-12-10","cited_by_count":89},{"id":"1809.00716","title":"InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset","created":"2018-09-03","cited_by_count":87},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85},{"id":"2508.10893","title":"STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer","created":"2025-08-14","cited_by_count":82},{"id":"2505.14357","title":"Vid2World: Crafting Video Diffusion Models to Interactive World Models","created":"2025-05-20","cited_by_count":76},{"id":"2212.03239","title":"Perspective Fields for Single Image Camera Calibration","created":"2022-12-06","cited_by_count":75},{"id":"2503.21979","title":"Harmonizing Visual Representations for Unified Multimodal Understanding and Generation","created":"2025-03-27","cited_by_count":74},{"id":"2504.15376","title":"Towards Understanding Camera Motions in Any Video","created":"2025-04-21","cited_by_count":64},{"id":"1904.00853","title":"Precise Detection in Densely Packed Scenes","created":"2019-04-01","cited_by_count":63},{"id":"2206.05683","title":"APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking","created":"2022-06-12","cited_by_count":56},{"id":"2504.01934","title":"ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement","created":"2025-04-02","cited_by_count":54},{"id":"2409.06704","title":"GeoCalib: Learning Single-image Calibration with Geometric Optimization","created":"2024-09-10","cited_by_count":52},{"id":"2503.13436","title":"Unified Autoregressive Visual Generation and Understanding with Continuous Tokens","created":"2025-03-17","cited_by_count":51},{"id":"2505.05422","title":"TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation","created":"2025-05-08","cited_by_count":51},{"id":"2505.23661","title":"OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation","created":"2025-05-29","cited_by_count":46},{"id":"1712.01259","title":"A Perceptual Measure for Deep Single Image Camera Calibration","created":"2017-12-02","cited_by_count":45},{"id":"2604.20329","title":"Image Generators are Generalist Vision Learners","created":"2026-04-22","cited_by_count":43},{"id":"2309.08816","title":"EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding","created":"2023-09-15","cited_by_count":40},{"id":"1909.12118","title":"WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild","created":"2019-09-25","cited_by_count":39},{"id":"2509.21657","title":"FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction","created":"2025-09-25","cited_by_count":38},{"id":"2605.10730","title":"Qwen-Image-2.0 Technical Report","created":"2026-05-11","cited_by_count":36},{"id":"2306.10988","title":"Tame a Wild Camera: In-the-Wild Monocular Camera Calibration","created":"2023-06-19","cited_by_count":34},{"id":"2109.02259","title":"CTRL-C: Camera calibration TRansformer with Line-Classification","created":"2021-09-06","cited_by_count":33},{"id":"2512.08931","title":"Astra: General Interactive World Model with Autoregressive Denoising","created":"2025-12-09","cited_by_count":33},{"id":"1804.04784","title":"FishEyeRecNet: A Multi-Context Collaborative Deep Network for Fisheye Image Rectification","created":"2018-04-13","cited_by_count":32},{"id":"2411.16157","title":"MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model","created":"2024-11-25","cited_by_count":32},{"id":"2411.18363","title":"ChatRex: Taming Multimodal LLM for Joint Perception and Understanding","created":"2024-11-27","cited_by_count":30},{"id":"1909.03459","title":"Blind Geometric Distortion Correction on Images Through Deep Learning","created":"2019-09-08","cited_by_count":28},{"id":"2601.05138","title":"VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control","created":"2026-01-08","cited_by_count":28},{"id":"1608.05684","title":"Detecting Vanishing Points using Global Image Context in a Non-Manhattan World","created":"2016-08-19","cited_by_count":27},{"id":"2412.02168","title":"Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis","created":"2024-12-03","cited_by_count":26},{"id":"2503.08507","title":"Referring to Any Person","created":"2025-03-11","cited_by_count":21},{"id":"2303.10559","title":"Deep Learning for Camera Calibration and Beyond: A Survey","created":"2023-03-19","cited_by_count":20},{"id":"2601.21406","title":"Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation","created":"2026-01-29","cited_by_count":20},{"id":"2510.08673","title":"Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation","created":"2025-10-09","cited_by_count":19},{"id":"2503.12701","title":"AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration","created":"2025-03-16","cited_by_count":18},{"id":"2603.02049","title":"WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories","created":"2026-03-02","cited_by_count":18},{"id":"2503.21193","title":"UGen: Unified Autoregressive Multimodal Model with Progressive Vocabulary Learning","created":"2025-03-27","cited_by_count":16},{"id":"2007.10689","title":"A Deep Ordinal Distortion Estimation Approach for Distortion Rectification","created":"2020-07-21","cited_by_count":13},{"id":"2007.11855","title":"Neural Geometric Parser for Single Image Camera Calibration","created":"2020-07-23","cited_by_count":13},{"id":"2011.08988","title":"Minimal Solvers for Single-View Lens-Distorted Camera Auto-Calibration","created":"2020-11-17","cited_by_count":13},{"id":"2501.12910","title":"PreciseCam: Precise Camera Control for Text-to-Image Generation","created":"2025-01-22","cited_by_count":13},{"id":"2601.17237","title":"C-RADIOv4 (Tech Report)","created":"2026-01-24","cited_by_count":12},{"id":"2605.04128","title":"JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation","created":"2026-05-05","cited_by_count":12},{"id":"2308.10694","title":"Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction","created":"2023-08-21","cited_by_count":9},{"id":"2405.15619","title":"DiffCalib: Reformulating Monocular Camera Calibration as Diffusion-Based Dense Incident Map Generation","created":"2024-05-24","cited_by_count":9}],"next_cursor":"100"}