{"list":"other","total":79,"rows":[{"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":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"1909.12828","title":"Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop","created":"2019-09-27","cited_by_count":627},{"id":"1903.05625","title":"Tracking without bells and whistles","created":"2019-03-13","cited_by_count":382},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287},{"id":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281},{"id":"2103.16507","title":"PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop","created":"2021-03-30","cited_by_count":250},{"id":"2208.00571","title":"CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation","created":"2022-08-01","cited_by_count":238},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"id":"2207.06400","title":"PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images","created":"2022-07-13","cited_by_count":153},{"id":"1702.07486","title":"Deep representation learning for human motion prediction and classification","created":"2017-02-24","cited_by_count":98},{"id":"1611.09010","title":"3D Human Pose Estimation from a Single Image via Distance Matrix Regression","created":"2016-11-28","cited_by_count":73},{"id":"2308.00783","title":"Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking","created":"2023-08-01","cited_by_count":67},{"id":"2303.10404","title":"MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking","created":"2023-03-18","cited_by_count":64},{"id":"2404.03736","title":"SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer","created":"2024-04-04","cited_by_count":61},{"id":"2403.02075","title":"DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction","created":"2024-03-04","cited_by_count":59},{"id":"2102.02267","title":"DEFT: Detection Embeddings for Tracking","created":"2021-02-03","cited_by_count":56},{"id":"2507.02939","title":"Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting","created":"2025-06-27","cited_by_count":55},{"id":"2105.04322","title":"RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation","created":"2021-05-10","cited_by_count":52},{"id":"2002.12625","title":"4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras","created":"2020-02-28","cited_by_count":49},{"id":"2303.14747","title":"Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation","created":"2023-03-26","cited_by_count":47},{"id":"2406.10580","title":"IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization","created":"2024-06-15","cited_by_count":42},{"id":"2412.13753","title":"Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localization","created":"2024-12-18","cited_by_count":35},{"id":"2203.14208","title":"Towards Discriminative Representation: Multi-view Trajectory Contrastive Learning for Online Multi-object Tracking","created":"2022-03-27","cited_by_count":33},{"id":"2405.15124","title":"Scaling Law for Time Series Forecasting","created":"2024-05-24","cited_by_count":33},{"id":"2401.00847","title":"Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera","created":"2024-01-01","cited_by_count":31},{"id":"2505.12079","title":"SepPrune: Structured Pruning for Efficient Deep Speech Separation","created":"2025-05-17","cited_by_count":31},{"id":"2205.14882","title":"Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving","created":"2022-05-30","cited_by_count":30},{"id":"2411.16805","title":"Human Motion Instruction Tuning","created":"2024-11-25","cited_by_count":29},{"id":"2412.04802","title":"Unsupervised Hyperspectral Image Super-Resolution via Self-Supervised Modality Decoupling","created":"2024-12-06","cited_by_count":26},{"id":"2307.03833","title":"Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation","created":"2023-07-07","cited_by_count":24},{"id":"2012.11806","title":"Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos","created":"2020-12-22","cited_by_count":23},{"id":"2505.11003","title":"ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization","created":"2025-05-16","cited_by_count":22},{"id":"2410.05180","title":"Mitigating the Risk of Health Inequity Exacerbated by Large Language Models","created":"2024-10-07","cited_by_count":21},{"id":"2501.07256","title":"EdgeTAM: On-Device Track Anything Model","created":"2025-01-13","cited_by_count":21},{"id":"2410.02892","title":"The Role of Deductive and Inductive Reasoning in Large Language Models","created":"2024-10-03","cited_by_count":20},{"id":"2305.12497","title":"PanoContext-Former: Panoramic Total Scene Understanding with a Transformer","created":"2023-05-21","cited_by_count":19},{"id":"2404.11987","title":"MultiPhys: Multi-Person Physics-aware 3D Motion Estimation","created":"2024-04-18","cited_by_count":18},{"id":"2408.09178","title":"MambaTrack: A Simple Baseline for Multiple Object Tracking with State Space Model","created":"2024-08-17","cited_by_count":18},{"id":"2603.10090","title":"A Survey of Weight Space Learning: Understanding, Representation, and Generation","created":"2026-03-10","cited_by_count":18},{"id":"2212.09098","title":"Mask-FPAN: Semi-Supervised Face Parsing in the Wild With De-Occlusion and UV GAN","created":"2022-12-18","cited_by_count":16},{"id":"2502.18180","title":"ChatMotion: A Multimodal Multi-Agent for Human Motion Analysis","created":"2025-02-25","cited_by_count":14},{"id":"2503.17690","title":"CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model","created":"2025-03-22","cited_by_count":14},{"id":"2504.12186","title":"CoMotion: Concurrent Multi-person 3D Motion","created":"2025-04-16","cited_by_count":13},{"id":"2406.01595","title":"MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild","created":"2024-06-03","cited_by_count":12},{"id":"2105.01937","title":"FLEX: Extrinsic Parameters-free Multi-view 3D Human Motion Reconstruction","created":"2021-05-05","cited_by_count":11},{"id":"2309.08644","title":"Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild","created":"2023-09-15","cited_by_count":11},{"id":"2402.12138","title":"Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers","created":"2024-02-19","cited_by_count":11},{"id":"2412.00091","title":"Graph Canvas for Controllable 3D Scene Generation","created":"2024-11-27","cited_by_count":11},{"id":"2502.18116","title":"Bayesian Optimization for Controlled Image Editing via LLMs","created":"2025-02-25","cited_by_count":11},{"id":"2505.20154","title":"UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models","created":"2025-05-26","cited_by_count":11},{"id":"2507.12062","title":"MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learning","created":"2025-07-16","cited_by_count":10},{"id":"2509.24156","title":"Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models","created":"2025-09-29","cited_by_count":10},{"id":"2311.12043","title":"Efficient Domain Adaptation via Generative Prior for 3D Infant Pose Estimation","created":"2023-11-17","cited_by_count":8},{"id":"2502.05147","title":"LP-DETR: Layer-wise Progressive Relations for Object Detection","created":"2025-02-07","cited_by_count":8},{"id":"2505.23290","title":"Wav2Sem: Plug-and-Play Audio Semantic Decoupling for 3D Speech-Driven Facial Animation","created":"2025-05-29","cited_by_count":8},{"id":"2507.10358","title":"Fine-Grained Zero-Shot Object Detection","created":"2025-07-14","cited_by_count":8},{"id":"2601.00536","title":"Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends","created":"2026-01-02","cited_by_count":8},{"id":"2507.17747","title":"Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarks","created":"2025-07-23","cited_by_count":7},{"id":"2410.03161","title":"Adaptive Masking Enhances Visual Grounding","created":"2024-10-04","cited_by_count":6},{"id":"2403.06086","title":"Towards Generalizable and Interpretable Motion Prediction: A Deep Variational Bayes Approach","created":"2024-03-10","cited_by_count":5},{"id":"2603.14952","title":"Pansharpening for Thin-Cloud Contaminated Remote Sensing Images: A Unified Framework and Benchmark Dataset","created":"2026-03-16","cited_by_count":5},{"id":"2409.18372","title":"You Only Speak Once to See","created":"2024-09-27","cited_by_count":4},{"id":"2502.01117","title":"Learning to Learn Weight Generation via Local Consistency Diffusion","created":"2025-02-03","cited_by_count":4},{"id":"2503.18282","title":"TrackID3x3: A Dataset and Algorithm for Multi-Player Tracking with Identification and Pose Estimation in 3x3 Basketball Full-court Videos","created":"2025-03-24","cited_by_count":4},{"id":"2508.01533","title":"ReasonAct: Progressive Training for Fine-Grained Video Reasoning in Small Models","created":"2025-08-03","cited_by_count":4},{"id":"2507.12001","title":"AU-Blendshape for Fine-grained Stylized 3D Facial Expression Manipulation","created":"2025-07-16","cited_by_count":3},{"id":"2603.18257","title":"Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learning","created":"2026-03-18","cited_by_count":2},{"id":"2504.08175","title":"Multi-person Physics-based Pose Estimation for Combat Sports","created":"2025-04-11","cited_by_count":1},{"id":"2506.14988","title":"Fair Algorithms with Probing for Multi-Agent Multi-Armed Bandits","created":"2025-06-17","cited_by_count":1},{"id":"2510.19078","title":"UniHPR: Unified Human Pose Representation via Singular Value Contrastive Learning","created":"2025-10-21","cited_by_count":1},{"id":"2511.13001","title":"Medal S: Spatio-Textual Prompt Model for Medical Segmentation","created":"2025-11-17","cited_by_count":1}],"next_cursor":null}