diathermy 发表于 2025-3-30 09:16:39
http://reply.papertrans.cn/24/2343/234209/234209_51.png值得 发表于 2025-3-30 15:55:32
http://reply.papertrans.cn/24/2343/234209/234209_52.png食道 发表于 2025-3-30 18:37:01
Object Detection with a Unified Label Space from Multiple Datasets,abel spaces. The practical benefits of such an object detector are obvious and significant—application-relevant categories can be picked and merged form arbitrary existing datasets. However, naïve merging of datasets is not possible in this case, due to inconsistent object annotations. Consider an oAccord 发表于 2025-3-30 21:29:03
http://reply.papertrans.cn/24/2343/234209/234209_54.png提名 发表于 2025-3-31 04:08:23
http://reply.papertrans.cn/24/2343/234209/234209_55.pngblithe 发表于 2025-3-31 05:04:41
http://reply.papertrans.cn/24/2343/234209/234209_56.png爱国者 发表于 2025-3-31 09:29:38
http://reply.papertrans.cn/24/2343/234209/234209_57.pngfertilizer 发表于 2025-3-31 15:23:29
http://reply.papertrans.cn/24/2343/234209/234209_58.png模范 发表于 2025-3-31 18:15:16
Adversarial Background-Aware Loss for Weakly-Supervised Temporal Activity Localization,eakly-supervised temporal activity localization struggle to recognize when an activity is not occurring. To address this issue, we propose a novel method named A2CL-PT. Two triplets of the feature space are considered in our approach: one triplet is used to learn discriminative features for each actgain631 发表于 2025-4-1 00:31:38
http://reply.papertrans.cn/24/2343/234209/234209_60.png