938 citations
- Centre National de la Recherche ScientifiqueFR52 papers
- University College LondonGB33 papers
- Max Planck Institute for Extraterrestrial PhysicsDE32 papers
- University of BristolGB32 papers
- University of CambridgeGB30 papers
- University of OxfordGB28 papers
- University of WarwickGB25 papers
- National Institute for AstrophysicsIT24 papers
- University of CopenhagenDK24 papers
- National Astronomical Observatory of JapanJP22 papers
- Space Telescope Science InstituteUS22 papers
- University of EdinburghGB22 papers
21 papers · 1 filter
YOLO with Kolmogorov-Arnold networks and vision-language foundation models for interpretable object detection with trustworthy multimodal AI in computer vision perception
Marios Impraimakis, Daniel Vazquez, Feiyu Zhou
The trustworthy object detection capabilities of a novel Kolmogorov-Arnold network framework are examined here. The approach addresses a key limitation in computer vision for vehic…
The Robust Semantic Segmentation UNCV2023 Challenge Results
Xuanlong Yu, Yi Zuo, Zitao Wang +34
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023. The challenge was centered around semantic segment…
Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild
Sindhu B Hegde, K R Prajwal, Rudrabha Mukhopadhyay +2
In this work, we address the problem of generating speech from silent lip videos for any speaker in the wild. In stark contrast to previous works, our method (i) is not restricted…
Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priors
Sindhu B Hegde, Rudrabha Mukhopadhyay, Vinay P Namboodiri +1
In this paper, we explore an interesting question of what can be obtained from an pixel video sequence. Surprisingly, it turns out to be quite a lot. We show that when w…
Parametric Reshaping of Portraits in Videos
Xiangjun Tang, Wenxin Sun, Yong-Liang Yang +1
Sharing short personalized videos to various social media networks has become quite popular in recent years. This raises the need for digital retouching of portraits in videos. How…
Disaster mapping from satellites: damage detection with crowdsourced point labels
Danil Kuzin, Olga Isupova, Brooke D. Simmons +1
High-resolution satellite imagery available immediately after disaster events is crucial for response planning as it facilitates broad situational awareness of critical infrastruct…