{"total":19,"rows":[{"id":"2105.13353","title":"Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering","created":"2021-05-27","cited_by_count":49,"area":null},{"id":"2111.03098","title":"Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Image","created":"2021-11-04","cited_by_count":20,"area":null},{"id":"2207.05306","title":"Contrastive Deep Supervision","created":"2022-07-12","cited_by_count":20,"area":null},{"id":"2206.15031","title":"Timestamp-Supervised Action Segmentation with Graph Convolutional Networks","created":"2022-06-30","cited_by_count":18,"area":null},{"id":"2305.19478","title":"Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment","created":"2023-05-31","cited_by_count":17,"area":null},{"id":"2208.06999","title":"HoW-3D: Holistic 3D Wireframe Perception from a Single Image","created":"2022-08-15","cited_by_count":12,"area":null},{"id":"2503.16832","title":"Joint Self-Supervised Video Alignment and Action Segmentation","created":"2025-03-21","cited_by_count":11,"area":null},{"id":"2207.02376","title":"A Comprehensive Review on Deep Supervision: Theories and Applications","created":"2022-07-06","cited_by_count":10,"area":null},{"id":"2104.03589","title":"PQA: Perceptual Question Answering","created":"2021-04-08","cited_by_count":6,"area":null},{"id":"2110.11636","title":"Occlusion-Robust Object Pose Estimation with Holistic Representation","created":"2021-10-22","cited_by_count":6,"area":null},{"id":"2309.06462","title":"Action Segmentation Using 2D Skeleton Heatmaps and Multi-Modality Fusion","created":"2023-09-12","cited_by_count":6,"area":null},{"id":"2104.06730","title":"Weakly But Deeply Supervised Occlusion-Reasoned Parametric Road Layouts","created":"2021-04-14","cited_by_count":3,"area":null},{"id":"2109.04153","title":"Single Image 3D Object Estimation with Primitive Graph Networks","created":"2021-09-09","cited_by_count":3,"area":null},{"id":"2403.19022","title":"WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusion","created":"2024-03-27","cited_by_count":3,"area":null},{"id":"2203.01449","title":"Object Pose Estimation using Mid-level Visual Representations","created":"2022-03-02","cited_by_count":2,"area":null},{"id":"2110.07118","title":"Nuisance-Label Supervision: Robustness Improvement by Free Labels","created":"2021-10-14","cited_by_count":1,"area":null},{"id":"2506.01414","title":"Self-supervised Latent Space Optimization with Nebula Variational Coding","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2103.09553","title":"Multi-channel Deep Supervision for Crowd Counting","created":"2021-03-17","cited_by_count":0,"area":null},{"id":"2210.06806","title":"OOOE: Only-One-Object-Exists Assumption to Find Very Small Objects in Chest Radiographs","created":"2022-10-13","cited_by_count":0,"area":null}],"next_cursor":null}