Tinea-Capitis 发表于 2025-3-30 09:49:33

,Learning Camouflaged Object Detection from Noisy Pseudo Label,-intensive. Although weakly supervised methods offer higher annotation efficiency, their performance is far behind due to the unclear visual demarcations between foreground and background in camouflaged images. In this paper, we explore the potential of using boxes as prompts in camouflaged scenes a

Missile 发表于 2025-3-30 14:38:23

,Weakly Supervised 3D Object Detection via Multi-level Visual Guidance, few accurate 3D annotations, we propose a framework to study how to leverage constraints between 2D and 3D domains without requiring any 3D labels. Specifically, we employ visual data from three perspectives to establish connections between 2D and 3D domains. First, we design a feature-level constr

美食家 发表于 2025-3-30 20:00:18

,Deblur ,-NeRF: NeRF from Motion-Blurred Events under High-speed or Low-light Conditions,s underperform. However, event cameras also suffer from motion blur, especially under these challenging conditions, contrary to what most think. This is due to the limited bandwidth of the event sensor pixel, which is mostly proportional to the light intensity. Thus, to ensure event cameras can trul

Insatiable 发表于 2025-3-31 00:10:55

http://reply.papertrans.cn/25/2424/242354/242354_54.png

Abutment 发表于 2025-3-31 02:08:36

http://reply.papertrans.cn/25/2424/242354/242354_55.png

子女 发表于 2025-3-31 05:23:09

http://reply.papertrans.cn/25/2424/242354/242354_56.png

半球 发表于 2025-3-31 09:16:26

,Motion Mamba: Efficient and Long Sequence Motion Generation,emains challenging. Recent advancements in state space models (SSMs), notably Mamba, have showcased considerable promise in long sequence modeling with an efficient hardware-aware design, which appears to be a significant direction upon building motion generation model. Nevertheless, adapting SSMs t

Range-Of-Motion 发表于 2025-3-31 17:22:10

http://reply.papertrans.cn/25/2424/242354/242354_58.png

nauseate 发表于 2025-3-31 19:27:18

http://reply.papertrans.cn/25/2424/242354/242354_59.png

Odyssey 发表于 2025-4-1 01:15:13

http://reply.papertrans.cn/25/2424/242354/242354_60.png
页: 1 2 3 4 5 [6] 7
查看完整版本: Titlebook: Computer Vision – ECCV 2024; 18th European Confer Aleš Leonardis,Elisa Ricci,Gül Varol Conference proceedings 2025 The Editor(s) (if applic