{"list":"other","total":171,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"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":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"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":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2310.11513","title":"GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment","created":"2023-10-17","cited_by_count":972},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"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":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1911.10127","title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","created":"2019-11-22","cited_by_count":490},{"id":"1911.11132","title":"Scaling Out-of-Distribution Detection for Real-World Settings","created":"2019-11-25","cited_by_count":465},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457},{"id":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2410.23218","title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","created":"2024-10-30","cited_by_count":378},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"id":"1605.06457","title":"Virtual Worlds as Proxy for Multi-Object Tracking Analysis","created":"2016-05-20","cited_by_count":341},{"id":"2312.02145","title":"Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation","created":"2023-12-04","cited_by_count":327},{"id":"2301.07525","title":"OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation","created":"2023-01-18","cited_by_count":326},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302},{"id":"1805.00123","title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","created":"2018-04-30","cited_by_count":284},{"id":"1804.00650","title":"DeepMVS: Learning Multi-view Stereopsis","created":"2018-04-02","cited_by_count":277},{"id":"2001.06303","title":"Detection and Tracking Meet Drones Challenge","created":"2020-01-16","cited_by_count":263},{"id":"2507.02546","title":"MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details","created":"2025-07-03","cited_by_count":261},{"id":"2103.10213","title":"ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction","created":"2021-03-18","cited_by_count":256},{"id":"2306.00968","title":"GRES: Generalized Referring Expression Segmentation","created":"2023-06-01","cited_by_count":254},{"id":"1908.00463","title":"DIODE: A Dense Indoor and Outdoor DEpth Dataset","created":"2019-08-01","cited_by_count":240},{"id":"2411.17465","title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent","created":"2024-11-26","cited_by_count":232},{"id":"2312.02228","title":"PixelLM: Pixel Reasoning with Large Multimodal Model","created":"2023-12-04","cited_by_count":222},{"id":"1812.00324","title":"CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark","created":"2018-12-02","cited_by_count":214},{"id":"2102.12219","title":"Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges","created":"2021-02-24","cited_by_count":204},{"id":"2105.05486","title":"TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text","created":"2021-05-12","cited_by_count":171},{"id":"2109.03805","title":"Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking","created":"2021-09-08","cited_by_count":166},{"id":"2409.18124","title":"Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction","created":"2024-09-26","cited_by_count":166},{"id":"1811.10200","title":"IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments","created":"2018-11-26","cited_by_count":163},{"id":"1907.12347","title":"FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation","created":"2019-07-29","cited_by_count":160},{"id":"1707.05972","title":"Drone-based Object Counting by Spatially Regularized Regional Proposal Network","created":"2017-07-19","cited_by_count":156},{"id":"2206.07669","title":"A Unified Sequence Interface for Vision Tasks","created":"2022-06-15","cited_by_count":152},{"id":"2206.01062","title":"DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis","created":"2022-06-02","cited_by_count":148},{"id":"2301.01795","title":"PACO: Parts and Attributes of Common Objects","created":"2023-01-04","cited_by_count":146},{"id":"2103.05569","title":"FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery","created":"2021-03-09","cited_by_count":143},{"id":"1907.00945","title":"ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019","created":"2019-07-01","cited_by_count":139},{"id":"1805.01328","title":"Evaluation of CNN-based Single-Image Depth Estimation Methods","created":"2018-05-03","cited_by_count":138},{"id":"2406.08394","title":"VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks","created":"2024-06-12","cited_by_count":137},{"id":"1808.00157","title":"Instance-level Human Parsing via Part Grouping Network","created":"2018-08-01","cited_by_count":134},{"id":"1901.07973","title":"DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images","created":"2019-01-23","cited_by_count":134},{"id":"1912.09641","title":"ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard","created":"2019-12-20","cited_by_count":128},{"id":"2112.01522","title":"Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks","created":"2021-12-02","cited_by_count":125},{"id":"2403.00712","title":"Rethinking Inductive Biases for Surface Normal Estimation","created":"2024-03-01","cited_by_count":124},{"id":"2108.12617","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","created":"2021-08-28","cited_by_count":123},{"id":"2111.12085","title":"UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling","created":"2021-11-23","cited_by_count":122},{"id":"2408.08872","title":"xGen-MM (BLIP-3): A Family of Open Large Multimodal Models","created":"2024-08-16","cited_by_count":116},{"id":"2401.12592","title":"RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos","created":"2024-01-23","cited_by_count":115},{"id":"2207.11247","title":"Panoptic Scene Graph Generation","created":"2022-07-22","cited_by_count":114},{"id":"1909.07072","title":"A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension","created":"2019-09-16","cited_by_count":111},{"id":"1703.05446","title":"Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing","created":"2017-03-16","cited_by_count":109},{"id":"1803.10683","title":"Pose2Seg: Detection Free Human Instance Segmentation","created":"2018-03-28","cited_by_count":107},{"id":"2112.00933","title":"PartImageNet: A Large, High-Quality Dataset of Parts","created":"2021-12-02","cited_by_count":107}],"next_cursor":"100"}