gustation 发表于 2025-3-28 16:58:47

http://reply.papertrans.cn/24/2342/234125/234125_41.png

amphibian 发表于 2025-3-28 21:57:40

Gated Hierarchical Attention for Image Captioningring and neural machine translation, and significantly improves the performance. In this paper, we propose a bottom-up gated hierarchical attention (GHA) mechanism for image captioning. Our proposed model employs a CNN as the decoder which is able to learn different concepts at different layers, and

Lobotomy 发表于 2025-3-29 00:26:09

Dealing with Ambiguity in Robotic Grasping via Multiple Predictionsjects. However, the lack of such intuition in robots makes robotic grasping an exceptionally challenging task. There are often several equally viable options of grasping an object. However, this ambiguity is not modeled in conventional systems that estimate a single, optimal grasp position. We propo

OASIS 发表于 2025-3-29 05:13:00

http://reply.papertrans.cn/24/2342/234125/234125_44.png

Left-Atrium 发表于 2025-3-29 07:19:42

Solving Minimum Cost Lifted Multicut Problems by Node Agglomerationosition or multiple object tracking. Its solutions are decompositions of a graph into an optimal number of segments which are optimized w.r.t. a cost function defined on a superset of the edge set. While the currently available solvers for this problem provide high quality solutions in terms of the

使饥饿 发表于 2025-3-29 14:06:37

http://reply.papertrans.cn/24/2342/234125/234125_46.png

侧面左右 发表于 2025-3-29 19:00:13

http://reply.papertrans.cn/24/2342/234125/234125_47.png

同位素 发表于 2025-3-29 21:15:32

http://reply.papertrans.cn/24/2342/234125/234125_48.png

Anterior 发表于 2025-3-30 03:34:30

http://reply.papertrans.cn/24/2342/234125/234125_49.png

Moderate 发表于 2025-3-30 07:58:01

Continual Occlusion and Optical Flow Estimationames. The proposed ContinualFlow method estimates occlusions before flow, avoiding the use of flow corrupted by occlusions for their estimation. We show that providing occlusion masks as an additional input to flow estimation improves the standard performance metric by more than 25% on both KITTI an
页: 1 2 3 4 [5] 6 7
查看完整版本: Titlebook: Computer Vision – ACCV 2018; 14th Asian Conferenc C.V. Jawahar,Hongdong Li,Konrad Schindler Conference proceedings 2019 Springer Nature Swi