{"list":"other","total":70,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"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":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"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":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"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":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"2403.17297","title":"InternLM2 Technical Report","created":"2024-03-26","cited_by_count":397},{"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":"2409.04429","title":"VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation","created":"2024-09-06","cited_by_count":295},{"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":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206},{"id":"2402.14817","title":"Cameras as Rays: Pose Estimation via Ray Diffusion","created":"2024-02-22","cited_by_count":131},{"id":"2210.10770","title":"LaMAR: Benchmarking Localization and Mapping for Augmented Reality","created":"2022-10-19","cited_by_count":100},{"id":"1803.08999","title":"LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image","created":"2018-03-23","cited_by_count":95},{"id":"2412.07679","title":"RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models","created":"2024-12-10","cited_by_count":89},{"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":"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":"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":"1804.04784","title":"FishEyeRecNet: A Multi-Context Collaborative Deep Network for Fisheye Image Rectification","created":"2018-04-13","cited_by_count":32},{"id":"2311.17389","title":"360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queries","created":"2023-11-29","cited_by_count":30},{"id":"2203.01824","title":"LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network","created":"2022-03-03","cited_by_count":29},{"id":"2303.12408","title":"Balanced Spherical Grid for Egocentric View Synthesis","created":"2023-03-22","cited_by_count":29},{"id":"1909.03459","title":"Blind Geometric Distortion Correction on Images Through Deep Learning","created":"2019-09-08","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":"2505.15145","title":"CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation","created":"2025-05-21","cited_by_count":23},{"id":"2406.13378","title":"PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation","created":"2024-06-19","cited_by_count":22},{"id":"2506.21356","title":"ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models","created":"2025-06-26","cited_by_count":22},{"id":"2303.10559","title":"Deep Learning for Camera Calibration and Beyond: A Survey","created":"2023-03-19","cited_by_count":20},{"id":"2503.12701","title":"AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration","created":"2025-03-16","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":"2304.12372","title":"Beyond the Pixel: a Photometrically Calibrated HDR Dataset for Luminance and Color Prediction","created":"2023-04-24","cited_by_count":14},{"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":"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},{"id":"2001.07960","title":"A Fixation-based 360{\\deg} Benchmark Dataset for Salient Object Detection","created":"2020-01-22","cited_by_count":8},{"id":"2404.10716","title":"MOWA: Multiple-in-One Image Warping Model","created":"2024-04-16","cited_by_count":8},{"id":"2411.17240","title":"Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration","created":"2024-11-26","cited_by_count":8},{"id":"2509.26555","title":"Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation","created":"2025-09-30","cited_by_count":6},{"id":"2409.15553","title":"SOFI: Multi-Scale Deformable Transformer for Camera Calibration with Enhanced Line Queries","created":"2024-09-23","cited_by_count":3},{"id":"2503.21581","title":"AlignDiff: Learning Physically-Grounded Camera Alignment via Diffusion","created":"2025-03-27","cited_by_count":2}],"next_cursor":null}