{"total":20,"rows":[{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2207.13085","title":"Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment","created":"2022-07-26","cited_by_count":98,"area":null},{"id":"2301.02508","title":"End-to-End 3D Dense Captioning with Vote2Cap-DETR","created":"2023-01-06","cited_by_count":78,"area":null},{"id":"2309.02999","title":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning","created":"2023-09-06","cited_by_count":39,"area":null},{"id":"2307.12612","title":"Less is More: Focus Attention for Efficient DETR","created":"2023-07-24","cited_by_count":38,"area":null},{"id":"2406.03459","title":"LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection","created":"2024-06-05","cited_by_count":36,"area":null},{"id":"2401.03989","title":"MS-DETR: Efficient DETR Training with Mixed Supervision","created":"2024-01-08","cited_by_count":35,"area":null},{"id":"2301.04019","title":"FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection","created":"2023-01-08","cited_by_count":30,"area":null},{"id":"2305.15377","title":"Uncovering and Quantifying Social Biases in Code Generation","created":"2023-05-24","cited_by_count":25,"area":null},{"id":"2305.16233","title":"Interactive Segment Anything NeRF with Feature Imitation","created":"2023-05-25","cited_by_count":24,"area":null},{"id":"2404.00653","title":"Dual DETRs for Multi-Label Temporal Action Detection","created":"2024-03-31","cited_by_count":20,"area":null},{"id":"2309.04902","title":"Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art","created":"2023-09-10","cited_by_count":15,"area":null},{"id":"2304.04978","title":"StageInteractor: Query-based Object Detector with Cross-stage Interaction","created":"2023-04-11","cited_by_count":8,"area":null},{"id":"2305.16253","title":"Uncovering and Categorizing Social Biases in Text-to-SQL","created":"2023-05-25","cited_by_count":5,"area":null},{"id":"2309.13600","title":"Multi-Dimensional Hyena for Spatial Inductive Bias","created":"2023-09-24","cited_by_count":5,"area":null},{"id":"2302.10707","title":"Parallel Sentence-Level Explanation Generation for Real-World Low-Resource Scenarios","created":"2023-02-21","cited_by_count":4,"area":null},{"id":"2303.10967","title":"Real-time 3D Semantic Scene Completion Via Feature Aggregation and Conditioned Prediction","created":"2023-03-20","cited_by_count":3,"area":null},{"id":"2405.04955","title":"Improving Long Text Understanding with Knowledge Distilled from Summarization Model","created":"2024-05-08","cited_by_count":3,"area":null},{"id":"2405.17677","title":"Understanding differences in applying DETR to natural and medical images","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2310.05290","title":"MSight: An Edge-Cloud Infrastructure-based Perception System for Connected Automated Vehicles","created":"2023-10-08","cited_by_count":1,"area":null}],"next_cursor":null}