{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:55:59Z","timestamp":1759334159493,"version":"build-2065373602"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T00:00:00Z","timestamp":1753488000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T00:00:00Z","timestamp":1753488000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,26]]},"DOI":"10.23919\/mva65244.2025.11175122","type":"proceedings-article","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T17:35:13Z","timestamp":1758908113000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Boosting Small Object Tracking via Collaborative Detection Transformer"],"prefix":"10.23919","author":[{"given":"Bing-Cheng","family":"Chuang","sequence":"first","affiliation":[{"name":"National Tsing Hua University"}]},{"given":"Jia-Hua","family":"Lee","sequence":"additional","affiliation":[{"name":"National Tsing Hua University"}]},{"given":"Pin-Tseng","family":"Kuo","sequence":"additional","affiliation":[{"name":"National Tsing Hua University"}]},{"given":"I-Hsuan","family":"Chu","sequence":"additional","affiliation":[{"name":"National Tsing Hua University"}]},{"given":"Yi-Shein","family":"Hsiao","sequence":"additional","affiliation":[{"name":"National Tsing Hua University"}]},{"given":"Cheng-Han","family":"Wu","sequence":"additional","affiliation":[{"name":"National Tsing Hua University"}]},{"given":"Po-Yi","family":"Wu","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Jui-Chien","family":"Tsou","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Hsuan-Chi","family":"Liu","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Chun-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Yuan-Fu","family":"Yang","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University"}]}],"member":"263","reference":[{"issue":"15","key":"ref1","article-title":"convolutional one-stage: A comprehensive review","volume":"23","author":"Mirzaei","year":"2023","journal-title":"Sensors"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.23919\/MVA57639.2023.10215748"},{"key":"ref4","article-title":"Mo-CaE: Mixture of Calibrated Experts Significantly Improves Object Detection","author":"Oksuz","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"article-title":"D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement","volume-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025","author":"Peng","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_17"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-024-01531-5"},{"article-title":"Boosttrack++: using tracklet information to detect more objects in multiple object tracking","year":"2024","author":"Stanojevi\u0107","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00908"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897990"},{"article-title":"SAHI: A lightweight vision library for perform ing large scale object detection and instance segmentation","year":"2021","author":"Akyon","key":"ref14"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.23919\/MVA65244.2025.11175061","article-title":"Mva 2025 small multi-object tracking for spotting birds challenge: Dataset, methods, and results","volume-title":"2025 19th International Conference on Machine Vision and Applications (MVA)","author":"Kondo"},{"article-title":"YOLOX: Exceeding YOLO Series in 2021","year":"2021","author":"Ge","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00352"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"article-title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhang","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"International Conference on Learning Representations","author":"Liu","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"article-title":"Deformable detr: Deformable transformers for end-to-end object detection","year":"2021","author":"Zhu","key":"ref29"},{"key":"ref30","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00934"},{"article-title":"BoT-SORT: Robust Associations Multi-Pedestrian Tracking","year":"2022","author":"Aharon","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"year":"2021","key":"ref37","article-title":"Birds flying dataset"},{"author":"Brostr\u00f6m","key":"ref38","article-title":"BoxMOT: pluggable SOTA tracking modules for object detection, segmentation and pose estimation models"}],"event":{"name":"2025 19th International Conference on Machine Vision and Applications (MVA)","start":{"date-parts":[[2025,7,26]]},"location":"Kyoto, Japan","end":{"date-parts":[[2025,7,28]]}},"container-title":["2025 19th International Conference on Machine Vision and Applications (MVA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11174131\/11175049\/11175122.pdf?arnumber=11175122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T13:16:52Z","timestamp":1759238212000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11175122\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,26]]},"references-count":38,"URL":"https:\/\/doi.org\/10.23919\/mva65244.2025.11175122","relation":{},"subject":[],"published":{"date-parts":[[2025,7,26]]}}}