{"total":45,"rows":[{"id":"2303.17912","title":"CIRCLE: Capture In Rich Contextual Environments","created":"2023-03-31","cited_by_count":79,"area":null},{"id":"2203.16051","title":"Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction","created":"2022-03-30","cited_by_count":66,"area":null},{"id":"2207.13362","title":"Camouflaged Object Detection via Context-aware Cross-level Fusion","created":"2022-07-27","cited_by_count":32,"area":null},{"id":"2404.15383","title":"WANDR: Intention-guided Human Motion Generation","created":"2024-04-23","cited_by_count":26,"area":null},{"id":"2405.02077","title":"MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition","created":"2024-05-03","cited_by_count":25,"area":null},{"id":"2203.13530","title":"Multimodal Pre-training Based on Graph Attention Network for Document Understanding","created":"2022-03-25","cited_by_count":24,"area":null},{"id":"2112.10992","title":"Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognition","created":"2021-12-21","cited_by_count":23,"area":null},{"id":"2108.04603","title":"Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition","created":"2021-08-10","cited_by_count":19,"area":null},{"id":"2302.02316","title":"Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognition","created":"2023-02-05","cited_by_count":17,"area":null},{"id":"2404.08347","title":"Learning to Rebalance Multi-Modal Optimization by Adaptively Masking Subnetworks","created":"2024-04-12","cited_by_count":16,"area":null},{"id":"2211.11220","title":"STGlow: A Flow-based Generative Framework with Dual Graphormer for Pedestrian Trajectory Prediction","created":"2022-11-21","cited_by_count":14,"area":null},{"id":"2109.01664","title":"Exploring Separable Attention for Multi-Contrast MR Image Super-Resolution","created":"2021-09-03","cited_by_count":13,"area":null},{"id":"2207.11759","title":"Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edges","created":"2022-07-24","cited_by_count":12,"area":null},{"id":"2212.07592","title":"Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaboration","created":"2022-12-15","cited_by_count":11,"area":null},{"id":"2302.02327","title":"Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action Recognition","created":"2023-02-05","cited_by_count":11,"area":null},{"id":"2311.17408","title":"Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Prediction","created":"2023-11-29","cited_by_count":11,"area":null},{"id":"2112.00396","title":"Dyadic Human Motion Prediction","created":"2021-12-01","cited_by_count":9,"area":null},{"id":"2201.09271","title":"Wavelet-Attention CNN for Image Classification","created":"2022-01-23","cited_by_count":8,"area":null},{"id":"2204.01297","title":"Learning Constrained Dynamic Correlations in Spatiotemporal Graphs for Motion Prediction","created":"2022-04-04","cited_by_count":7,"area":null},{"id":"2105.07673","title":"EA-Net: Edge-Aware Network for Flow-based Video Frame Interpolation","created":"2021-05-17","cited_by_count":6,"area":null},{"id":"2112.00281","title":"FDA-GAN: Flow-based Dual Attention GAN for Human Pose Transfer","created":"2021-12-01","cited_by_count":5,"area":null},{"id":"2306.11046","title":"FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation","created":"2023-06-19","cited_by_count":5,"area":null},{"id":"2602.18043","title":"Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition","created":"2026-02-20","cited_by_count":4,"area":null},{"id":"2208.13414","title":"PV-RCNN++: Semantical Point-Voxel Feature Interaction for 3D Object Detection","created":"2022-08-29","cited_by_count":3,"area":null},{"id":"2503.22869","title":"SIGHT: Synthesizing Image-Text Conditioned and Geometry-Guided 3D Hand-Object Trajectories","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2508.10897","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","created":"2025-08-14","cited_by_count":3,"area":null},{"id":"2510.12385","title":"Learning to Recognize Correctly Completed Procedure Steps in Egocentric Assembly Videos through Spatio-Temporal Modeling","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2104.05015","title":"Temporal Consistency Two-Stream CNN for Human Motion Prediction","created":"2021-04-11","cited_by_count":2,"area":null},{"id":"2109.09692","title":"Modeling Regime Shifts in Multiple Time Series","created":"2021-09-20","cited_by_count":2,"area":null},{"id":"2201.06304","title":"Action Keypoint Network for Efficient Video Recognition","created":"2022-01-17","cited_by_count":2,"area":null},{"id":"2304.06411","title":"Meta-Auxiliary Learning for Adaptive Human Pose Prediction","created":"2023-04-13","cited_by_count":2,"area":null},{"id":"2306.11990","title":"Physics-constrained Attack against Convolution-based Human Motion Prediction","created":"2023-06-21","cited_by_count":2,"area":null},{"id":"2204.11751","title":"Adversarial Attention for Human Motion Synthesis","created":"2022-04-25","cited_by_count":1,"area":null},{"id":"2207.05249","title":"Efficient Human Vision Inspired Action Recognition using Adaptive Spatiotemporal Sampling","created":"2022-07-12","cited_by_count":1,"area":null},{"id":"2304.04023","title":"Attack-Augmentation Mixing-Contrastive Skeletal Representation Learning","created":"2023-04-08","cited_by_count":1,"area":null},{"id":"2312.06184","title":"Recent Advances in Deterministic Human Motion Prediction: A Review","created":"2023-12-11","cited_by_count":1,"area":null},{"id":"2506.18193","title":"DeInfoReg: A Decoupled Learning Framework for Better Training Throughput","created":"2025-06-22","cited_by_count":1,"area":null},{"id":"2506.20583","title":"Dense Video Captioning using Graph-based Sentence Summarization","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2512.11941","title":"DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognition","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2304.14502","title":"Deep state-space modeling for explainable representation, analysis, and generation of professional human poses","created":"2023-04-13","cited_by_count":0,"area":null},{"id":"2312.03798","title":"Single Image Reflection Removal with Patch Reflectance Prior","created":"2023-12-06","cited_by_count":0,"area":null},{"id":"2409.17951","title":"Spatial Hierarchy and Temporal Attention Guided Cross Masking for Self-supervised Skeleton-based Action Recognition","created":"2024-09-26","cited_by_count":0,"area":null},{"id":"2510.08305","title":"LTCA: Long-range Temporal Context Attention for Referring Video Object Segmentation","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2609.08636","title":"From Where to How: Continuous 4D Interaction Forecasting from Egocentric Video","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2610.16624","title":"Adaptive Interaction Network for Human Motion Prediction During Human-Robot Collaboration","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}