{"list":"other","total":73,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"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":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"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":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"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":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"2309.13101","title":"Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction","created":"2023-09-22","cited_by_count":759},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"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":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365},{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327},{"id":"2312.02145","title":"Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation","created":"2023-12-04","cited_by_count":327},{"id":"2103.01913","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","created":"2021-03-02","cited_by_count":287},{"id":"1804.00650","title":"DeepMVS: Learning Multi-view Stereopsis","created":"2018-04-02","cited_by_count":277},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276},{"id":"2211.05783","title":"Unifying Flow, Stereo and Depth Estimation","created":"2022-11-10","cited_by_count":275},{"id":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250},{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"2409.02095","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","created":"2024-09-03","cited_by_count":204},{"id":"2112.12761","title":"BANMo: Building Animatable 3D Neural Models from Many Casual Videos","created":"2021-12-23","cited_by_count":197},{"id":"2301.02239","title":"Robust Dynamic Radiance Fields","created":"2023-01-05","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":"2501.03847","title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control","created":"2025-01-07","cited_by_count":185},{"id":"2502.20110","title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","created":"2025-02-27","cited_by_count":173},{"id":"2303.01943","title":"Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo","created":"2023-03-03","cited_by_count":172},{"id":"2501.04001","title":"Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos","created":"2025-01-07","cited_by_count":159},{"id":"2305.02296","title":"DynamicStereo: Consistent Dynamic Depth from Stereo Videos","created":"2023-05-03","cited_by_count":148},{"id":"2407.06358","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","created":"2024-07-08","cited_by_count":146},{"id":"1806.05620","title":"DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes","created":"2018-06-14","cited_by_count":134},{"id":"2104.04691","title":"Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation","created":"2021-04-10","cited_by_count":133},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133},{"id":"2504.20995","title":"TesserAct: Learning 4D Embodied World Models","created":"2025-04-29","cited_by_count":94},{"id":"2207.09137","title":"ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild","created":"2022-07-19","cited_by_count":92},{"id":"1809.08379","title":"DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments","created":"2018-09-22","cited_by_count":91},{"id":"2412.09621","title":"Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos","created":"2024-12-12","cited_by_count":89},{"id":"2504.16072","title":"Describe Anything: Detailed Localized Image and Video Captioning","created":"2025-04-22","cited_by_count":84},{"id":"2209.12118","title":"BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video","created":"2022-09-25","cited_by_count":66},{"id":"2504.15376","title":"Towards Understanding Camera Motions in Any Video","created":"2025-04-21","cited_by_count":64},{"id":"2506.22355","title":"Embodied AI Agents: Modeling the World","created":"2025-06-27","cited_by_count":61},{"id":"2401.01887","title":"LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry","created":"2024-01-03","cited_by_count":56},{"id":"1904.08913","title":"Deep Rigid Instance Scene Flow","created":"2019-04-18","cited_by_count":54},{"id":"2406.12459","title":"HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors","created":"2024-06-18","cited_by_count":54},{"id":"2212.06200","title":"Breaking the \"Object\" in Video Object Segmentation","created":"2022-12-12","cited_by_count":49},{"id":"2503.10437","title":"4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models","created":"2025-03-13","cited_by_count":35},{"id":"2211.03889","title":"Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable Categories","created":"2022-11-07","cited_by_count":29},{"id":"2503.21761","title":"Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video","created":"2025-03-27","cited_by_count":29},{"id":"2504.17788","title":"Dynamic Camera Poses and Where to Find Them","created":"2025-04-24","cited_by_count":27},{"id":"2412.13647","title":"G-VEval: A Versatile Metric for Evaluating Image and Video Captions Using GPT-4o","created":"2024-12-18","cited_by_count":23},{"id":"2109.09903","title":"AirDOS: Dynamic SLAM benefits from Articulated Objects","created":"2021-09-21","cited_by_count":21},{"id":"2407.03204","title":"Expressive Gaussian Human Avatars from Monocular RGB Video","created":"2024-07-03","cited_by_count":21},{"id":"2505.12253","title":"LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understanding","created":"2025-05-18","cited_by_count":17},{"id":"2504.08212","title":"RealCam-Vid: High-resolution Video Dataset with Dynamic Scenes and Metric-scale Camera Movements","created":"2025-04-11","cited_by_count":14},{"id":"2312.04031","title":"The Importance of Coordinate Frames in Dynamic SLAM","created":"2023-12-07","cited_by_count":2}],"next_cursor":null}