19 citations · 59 across the 18 of their papers we have counts for
5 papers · 1 filter
Temporally Aligned Audio for Video with Autoregression
Ilpo Viertola, Vladimir Iashin, Esa Rahtu
We introduce V-AURA, the first autoregressive model to achieve high temporal alignment and relevance in video-to-audio generation. V-AURA uses a high-framerate visual feature extra…
UDGS-SLAM : UniDepth Assisted Gaussian Splatting for Monocular SLAM
Mostafa Mansour, Ahmed Abdelsalam, Ari Happonen +2
Recent advancements in monocular neural depth estimation, particularly those achieved by the UniDepth network, have prompted the investigation of integrating UniDepth within a Gaus…
Synchformer: Efficient Synchronization from Sparse Cues
Vladimir Iashin, Weidi Xie, Esa Rahtu +1
Our objective is audio-visual synchronization with a focus on 'in-the-wild' videos, such as those on YouTube, where synchronization cues can be sparse. Our contributions include a…
NN-VVC: Versatile Video Coding boosted by self-supervisedly learned image coding for machines
Jukka I. Ahonen, Nam Le, Honglei Zhang +5
The recent progress in artificial intelligence has led to an ever-increasing usage of images and videos by machine analysis algorithms, mainly neural networks. Nonetheless, compres…
Bridging the gap between image coding for machines and humans
Nam Le, Honglei Zhang, Francesco Cricri +5
Image coding for machines (ICM) aims at reducing the bitrate required to represent an image while minimizing the drop in machine vision analysis accuracy. In many use cases, such a…