{"total":85,"rows":[{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424,"area":null},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175,"area":null},{"id":"2204.13686","title":"HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling","created":"2022-04-28","cited_by_count":117,"area":null},{"id":"2111.01236","title":"Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation","created":"2021-11-01","cited_by_count":92,"area":null},{"id":"2209.08290","title":"Changer: Feature Interaction is What You Need for Change Detection","created":"2022-09-17","cited_by_count":79,"area":null},{"id":"2106.04263","title":"On the Connection between Local Attention and Dynamic Depth-wise Convolution","created":"2021-06-08","cited_by_count":62,"area":null},{"id":"2203.08713","title":"DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation","created":"2022-03-16","cited_by_count":29,"area":null},{"id":"2209.08194","title":"PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation","created":"2022-09-16","cited_by_count":27,"area":null},{"id":"2301.03036","title":"HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection","created":"2023-01-08","cited_by_count":27,"area":null},{"id":"2404.01614","title":"LR-FPN: Enhancing Remote Sensing Object Detection with Location Refined Feature Pyramid Network","created":"2024-04-02","cited_by_count":27,"area":null},{"id":"2308.15300","title":"MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detection","created":"2023-08-29","cited_by_count":25,"area":null},{"id":"2111.12696","title":"A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose","created":"2021-11-24","cited_by_count":21,"area":null},{"id":"2204.07370","title":"2D Human Pose Estimation: A Survey","created":"2022-04-15","cited_by_count":21,"area":null},{"id":"2308.13872","title":"Vision-Based Human Pose Estimation via Deep Learning: A Survey","created":"2023-08-26","cited_by_count":20,"area":null},{"id":"2205.01271","title":"Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation","created":"2022-05-03","cited_by_count":16,"area":null},{"id":"2109.03622","title":"Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation","created":"2021-09-08","cited_by_count":14,"area":null},{"id":"2402.15351","title":"AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks","created":"2024-02-23","cited_by_count":14,"area":null},{"id":"2403.11999","title":"HIRI-ViT: Scaling Vision Transformer with High Resolution Inputs","created":"2024-03-18","cited_by_count":12,"area":null},{"id":"2312.10758","title":"SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation","created":"2023-12-17","cited_by_count":11,"area":null},{"id":"2404.10700","title":"Rawformer: Unpaired Raw-to-Raw Translation for Learnable Camera ISPs","created":"2024-04-16","cited_by_count":11,"area":null},{"id":"2204.10762","title":"Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation","created":"2022-04-22","cited_by_count":10,"area":null},{"id":"2205.15448","title":"FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER","created":"2022-05-30","cited_by_count":9,"area":null},{"id":"2311.05237","title":"Widely Applicable Strong Baseline for Sports Ball Detection and Tracking","created":"2023-11-09","cited_by_count":9,"area":null},{"id":"2108.11105","title":"Lightweight Monocular Depth with a Novel Neural Architecture Search Method","created":"2021-08-25","cited_by_count":7,"area":null},{"id":"2406.08896","title":"Blind Super-Resolution via Meta-learning and Markov Chain Monte Carlo Simulation","created":"2024-06-13","cited_by_count":7,"area":null},{"id":"2307.10267","title":"On the Real-Time Semantic Segmentation of Aphid Clusters in the Wild","created":"2023-07-17","cited_by_count":6,"area":null},{"id":"2407.10756","title":"GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation","created":"2024-07-15","cited_by_count":6,"area":null},{"id":"2408.15185","title":"Human-Centric Video Anomaly Detection Through Spatio-Temporal Pose Tokenization and Transformer","created":"2024-08-27","cited_by_count":6,"area":null},{"id":"2501.14302","title":"TD-RD: A Top-Down Benchmark with Real-Time Framework for Road Damage Detection","created":"2025-01-24","cited_by_count":6,"area":null},{"id":"2204.13096","title":"3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspective","created":"2022-04-27","cited_by_count":5,"area":null},{"id":"2207.13600","title":"Lightweight and Progressively-Scalable Networks for Semantic Segmentation","created":"2022-07-27","cited_by_count":4,"area":null},{"id":"2306.01452","title":"dugMatting: Decomposed-Uncertainty-Guided Matting","created":"2023-06-02","cited_by_count":4,"area":null},{"id":"2306.04225","title":"Efficient Vision Transformer for Human Pose Estimation via Patch Selection","created":"2023-06-07","cited_by_count":4,"area":null},{"id":"2308.06024","title":"Spatial-information Guided Adaptive Context-aware Network for Efficient RGB-D Semantic Segmentation","created":"2023-08-11","cited_by_count":4,"area":null},{"id":"2312.06797","title":"Improving the Robustness of 3D Human Pose Estimation: A Benchmark and Learning from Noisy Input","created":"2023-12-11","cited_by_count":4,"area":null},{"id":"2406.14367","title":"PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptions","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2407.13777","title":"DIR-BHRNet: A Lightweight Network for Real-time Vision-based Multi-person Pose Estimation on Smartphones","created":"2024-07-01","cited_by_count":4,"area":null},{"id":"2212.02163","title":"2D Human Pose Estimation with Explicit Anatomical Keypoints Structure Constraints","created":"2022-12-05","cited_by_count":3,"area":null},{"id":"2406.11743","title":"Domain Generalization for In-Orbit 6D Pose Estimation","created":"2024-06-17","cited_by_count":3,"area":null},{"id":"2409.07337","title":"Benchmarking 2D Egocentric Hand Pose Datasets","created":"2024-09-11","cited_by_count":3,"area":null},{"id":"2106.04400","title":"CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentation","created":"2021-06-08","cited_by_count":2,"area":null},{"id":"2206.08236","title":"Simple and Efficient Architectures for Semantic Segmentation","created":"2022-06-16","cited_by_count":2,"area":null},{"id":"2206.13577","title":"A View Independent Classification Framework for Yoga Postures","created":"2022-06-27","cited_by_count":2,"area":null},{"id":"2207.12648","title":"Efficient and Accurate Skeleton-Based Two-Person Interaction Recognition Using Inter- and Intra-body Graphs","created":"2022-07-26","cited_by_count":2,"area":null},{"id":"2208.11666","title":"Efficient Heterogeneous Video Segmentation at the Edge","created":"2022-08-24","cited_by_count":2,"area":null},{"id":"2307.01530","title":"Tomato Maturity Recognition with Convolutional Transformers","created":"2023-07-04","cited_by_count":2,"area":null},{"id":"2308.12133","title":"Lite-HRNet Plus: Fast and Accurate Facial Landmark Detection","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2404.10985","title":"Pixel-Wise Symbol Spotting via Progressive Points Location for Parsing CAD Images","created":"2024-04-17","cited_by_count":2,"area":null},{"id":"2404.14025","title":"DHRNet: A Dual-Path Hierarchical Relation Network for Multi-Person Pose Estimation","created":"2024-04-22","cited_by_count":2,"area":null},{"id":"2410.09312","title":"Towards Multi-Modal Animal Pose Estimation: A Survey and In-Depth Analysis","created":"2024-10-12","cited_by_count":2,"area":null},{"id":"2508.09650","title":"TOTNet: Occlusion-Aware Temporal Tracking for Robust Ball Detection in Sports Videos","created":"2025-08-13","cited_by_count":2,"area":null},{"id":"2107.03215","title":"FasterPose: A Faster Simple Baseline for Human Pose Estimation","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2310.08042","title":"X-HRNet: Towards Lightweight Human Pose Estimation with Spatially Unidimensional Self-Attention","created":"2023-10-12","cited_by_count":1,"area":null},{"id":"2403.13747","title":"Leveraging High-Resolution Features for Improved Deep Hashing-based Image Retrieval","created":"2024-03-20","cited_by_count":1,"area":null},{"id":"2507.11955","title":"Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentation","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2510.13740","title":"Multi-Scale High-Resolution Logarithmic Grapher Module for Efficient Vision GNNs","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2605.23178","title":"Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2111.00509","title":"DRBANET: A Lightweight Dual-Resolution Network for Semantic Segmentation with Boundary Auxiliary","created":"2021-10-31","cited_by_count":0,"area":null},{"id":"2203.01994","title":"Fast Neural Architecture Search for Lightweight Dense Prediction Networks","created":"2022-03-03","cited_by_count":0,"area":null},{"id":"2205.10611","title":"Lightweight Human Pose Estimation Using Heatmap-Weighting Loss","created":"2022-05-21","cited_by_count":0,"area":null},{"id":"2304.07072","title":"CornerFormer: Boosting Corner Representation for Fine-Grained Structured Reconstruction","created":"2023-04-14","cited_by_count":0,"area":null},{"id":"2307.07291","title":"Sampling-Priors-Augmented Deep Unfolding Network for Robust Video Compressive Sensing","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2308.09084","title":"MovePose: A High-performance Human Pose Estimation Algorithm on Mobile and Edge Devices","created":"2023-08-17","cited_by_count":0,"area":null},{"id":"2311.09653","title":"Improved TokenPose with Sparsity","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2311.13615","title":"HEViTPose: High-Efficiency Vision Transformer for Human Pose Estimation","created":"2023-11-22","cited_by_count":0,"area":null},{"id":"2405.10504","title":"Multi-scale Semantic Prior Features Guided Deep Neural Network for Urban Street-view Image","created":"2024-05-17","cited_by_count":0,"area":null},{"id":"2407.07389","title":"Greit-HRNet: Grouped Lightweight High-Resolution Network for Human Pose Estimation","created":"2024-07-10","cited_by_count":0,"area":null},{"id":"2410.03174","title":"Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2411.10334","title":"Y-MAP-Net: Real-time depth, normals, segmentation, multi-label captioning and 2D human pose in RGB images","created":"2024-11-15","cited_by_count":0,"area":null},{"id":"2411.15653","title":"OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUs","created":"2024-11-23","cited_by_count":0,"area":null},{"id":"2412.02197","title":"Cascaded Multi-Scale Attention for Enhanced Multi-Scale Feature Extraction and Interaction with Low-Resolution Images","created":"2024-12-03","cited_by_count":0,"area":null},{"id":"2503.00232","title":"Transformers with Joint Tokens and Local-Global Attention for Efficient Human Pose Estimation","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2503.13906","title":"HSOD-BIT-V2: A New Challenging Benchmarkfor Hyperspectral Salient Object Detection","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2506.04561","title":"LGM-Pose: A Lightweight Global Modeling Network for Real-time Human Pose Estimation","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2507.02519","title":"IMASHRIMP: Automatic White Shrimp (Penaeus vannamei) Biometrical Analysis from Laboratory Images Using Computer Vision and Deep Learning","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2510.12660","title":"On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimation","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2510.13250","title":"Real-Time Crowd Counting for Embedded Systems with Lightweight Architecture","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2512.16089","title":"LAPX: Lightweight Hourglass Network with Global Context","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2601.05747","title":"FlyPose: Towards Robust Human Pose Estimation From Aerial Views","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2603.08681","title":"ER-Pose: Rethinking Keypoint-Driven Representation Learning for Real-Time Human Pose Estimation","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2604.03590","title":"SBF: An Effective Representation to Augment Skeleton for Video-based Human Action Recognition","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2608.21837","title":"Towards Bitstream-corrupted Harsh Visual Understanding: Through Bitstream Language Modeling as Robust Semantic Priors","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2609.08038","title":"SAFER-Activities: A Dataset for Smart Assessment of Fall Events and Routine Activities","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.23974","title":"LEAP-NBV: Lightweight Edge Active-Perception for Foundation-Model Next-Best-View Planning","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.24537","title":"MIRAGE: Full-Body Bystander Privacy for Smart Glasses with Consent-Based Restoration","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}