撕裂皮肉 发表于 2025-3-26 21:56:39

: Learning General Trees for Structured Grid Layout Generationy when the datasets contain a small number of samples. We also demonstrate that the structured layout space constructed by our method enables structure blending between structured layouts. We will release our code upon the acceptance of the paper.

NIL 发表于 2025-3-27 01:33:15

Silhouette-Based 6D Object Pose Estimationto perform pose estimation through search, rendering, and comparison in a reduced-dimensional space efficiently and accurately. Experimental results demonstrate the high precision and generalization of the proposed method. Our code is available at ..

poliosis 发表于 2025-3-27 07:05:21

Robust Light Field Depth Estimation over Occluded and Specular Regionsency, we propose a voting method to select the un-occluded pixels to obtain the initial depth of the occluded point. We use a method to determine the specular region based on similar features of color and texture in the superpixel region and then present an optimization energy function to obtain the

玩忽职守 发表于 2025-3-27 10:38:56

Foreground and Background Separate Adaptive Equilibrium Gradients Loss for Long-Tail Object Detectioategories to weight different classes, then adaptively leverage the suppression of head classes according to the logit value of the network output. Meanwhile, dynamically adjusting the suppression gradient of the background classes to protect the head and common classes while improving the detection

occult 发表于 2025-3-27 15:44:04

http://reply.papertrans.cn/24/2333/233216/233216_35.png

谎言 发表于 2025-3-27 21:18:19

http://reply.papertrans.cn/24/2333/233216/233216_36.png

富足女人 发表于 2025-3-27 22:35:56

http://reply.papertrans.cn/24/2333/233216/233216_37.png

FOVEA 发表于 2025-3-28 02:40:08

Denoised Dual-Level Contrastive Network for Weakly-Supervised Temporal Sentence Groundingintra-video and inter-video loss. Moreover, a ranking weight strategy is presented to select high-quality positive and negative pairs during training. Afterward, an effective pseudo-label denoised process is introduced to alleviate the noisy activations caused by the video-level annotations, thereby

GLADE 发表于 2025-3-28 10:17:44

http://reply.papertrans.cn/24/2333/233216/233216_39.png

aristocracy 发表于 2025-3-28 12:49:34

http://reply.papertrans.cn/24/2333/233216/233216_40.png
页: 1 2 3 [4] 5
查看完整版本: Titlebook: Computational Visual Media; 12th International C Fang-Lue Zhang,Andrei Sharf Conference proceedings 2024 The Editor(s) (if applicable) and