{"total":16,"rows":[{"id":"2102.00463","title":"PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection","created":"2021-01-31","cited_by_count":232,"area":null},{"id":"2107.00420","title":"CBNet: A Composite Backbone Network Architecture for Object Detection","created":"2021-07-01","cited_by_count":77,"area":null},{"id":"2108.01684","title":"Vision Transformer with Progressive Sampling","created":"2021-08-03","cited_by_count":44,"area":null},{"id":"2211.15444","title":"DAMO-YOLO : A Report on Real-Time Object Detection Design","created":"2022-11-23","cited_by_count":38,"area":null},{"id":"2107.05790","title":"Visual Parser: Representing Part-whole Hierarchies with Transformers","created":"2021-07-13","cited_by_count":21,"area":null},{"id":"2202.04256","title":"GiraffeDet: A Heavy-Neck Paradigm for Object Detection","created":"2022-02-09","cited_by_count":17,"area":null},{"id":"2111.13336","title":"MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection","created":"2021-11-26","cited_by_count":16,"area":null},{"id":"2201.03176","title":"Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond","created":"2022-01-10","cited_by_count":8,"area":null},{"id":"2407.10200","title":"Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data","created":"2024-07-14","cited_by_count":8,"area":null},{"id":"2112.11290","title":"Review of Face Presentation Attack Detection Competitions","created":"2021-12-21","cited_by_count":3,"area":null},{"id":"2408.03030","title":"Nighttime Pedestrian Detection Based on Fore-Background Contrast Learning","created":"2024-08-06","cited_by_count":2,"area":null},{"id":"2107.11509","title":"Cycled Compositional Learning between Images and Text","created":"2021-07-24","cited_by_count":1,"area":null},{"id":"2310.16483","title":"Gramian Attention Heads are Strong yet Efficient Vision Learners","created":"2023-10-25","cited_by_count":1,"area":null},{"id":"2209.13661","title":"CEC-CNN: A Consecutive Expansion-Contraction Convolutional Network for Very Small Resolution Medical Image Classification","created":"2022-09-27","cited_by_count":0,"area":null},{"id":"2311.11974","title":"Evaluating Supervision Levels Trade-Offs for Infrared-Based People Counting","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2503.08321","title":"i-WiViG: Interpretable Window Vision GNN","created":"2025-03-11","cited_by_count":0,"area":null}],"next_cursor":null}