新字
发表于 2025-3-30 12:13:42
http://reply.papertrans.cn/24/2343/234218/234218_51.png
CBC471
发表于 2025-3-30 13:18:51
PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments,proaches are mostly built on horizontal bounding box detectors by introducing an additional angle dimension optimized by a distance loss. However, as the distance loss only minimizes the angle error of the OBB and that it loosely correlates to the IoU, it is insensitive to objects with high aspect r
eardrum
发表于 2025-3-30 18:04:15
TENet: Triple Excitation Network for Video Salient Object Detection,n (VSOD) from three aspects, spatial, temporal, and online excitations. These excitation mechanisms are designed following the spirit of curriculum learning and aim to reduce learning ambiguities at the beginning of training by selectively exciting feature activations using ground truth. Then we gra
欢笑
发表于 2025-3-30 22:51:13
Deep Feedback Inverse Problem Solver, the forward process and learn an iterative update model. Specifically, at each iteration, the neural network takes the feedback as input and outputs an update on current estimation. Our approach does not have any restrictions on the forward process; it does not require any prior knowledge either. T
油膏
发表于 2025-3-31 02:45:34
http://reply.papertrans.cn/24/2343/234218/234218_55.png
RODE
发表于 2025-3-31 07:30:16
http://reply.papertrans.cn/24/2343/234218/234218_56.png
Pigeon
发表于 2025-3-31 10:51:00
DTVNet: Dynamic Time-Lapse Video Generation via Single Still Image,ingle landscape image, which are conditioned on normalized motion vectors. The proposed DTVNet consists of two submodules: . (OFE) and . (DVG). The OFE maps a sequence of optical flow maps to a . that encodes the motion information inside the generated video. The DVG contains motion and content stre
跟随
发表于 2025-3-31 15:03:33
http://reply.papertrans.cn/24/2343/234218/234218_58.png
Custodian
发表于 2025-3-31 20:06:12
http://reply.papertrans.cn/24/2343/234218/234218_59.png
agitate
发表于 2025-4-1 00:47:01
Stream Regulation in Great Britainiative alignment for leveraging part of the base data by aligning the novel training instances to the closely related ones in the base training set. This expands the size of the effective novel training set by adding extra “related base” instances to the few novel ones, thereby allowing a constructi