Guillaume Berger's scientific contributions
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (8)
Real-time rendering for video games has become increasingly challenging due to the need for higher resolutions, framerates and photorealism. Supersampling has emerged as an effective solution to address this challenge. Our work introduces a novel neural algorithm for supersampling rendered content that is 4 times more efficient than existing method...
End-to-end learning has taken hold of many computer vision tasks, in particular, related to still images, with task-specific optimization yielding very strong performance. Nevertheless, human-centric action recognition is still largely dominated by hand-crafted pipelines, and only individual components are replaced by neural networks that typically...
In this work, we present QuickSRNet, an efficient super-resolution architecture for real-time applications on mobile platforms. Super-resolution clarifies, sharpens, and upscales an image to higher resolution. Applications such as gaming and video playback along with the ever-improving display capabilities of TVs, smartphones, and VR headsets are d...
We describe a DNN for fine-grained action classification and video captioning. It gives state-of-the-art performance on the challenging Something-Something dataset, with over 220, 000 videos and 174 fine-grained actions. Classification and captioning on this dataset are challenging because of the subtle differences between actions, the use of thous...
Gatys et al. (2015) showed that pair-wise products of features in a convolutional network are a very effective representation of image textures. We propose a simple modification to that representation which makes it possible to incorporate long-range structure into image generation, and to render images that satisfy various symmetry constraints. We...
Citations
... Among them, the EgoGesture [47] dataset is a large-scale gesture recognition dataset, including 2,081 long videos recorded by head-mounted cameras, and each video contains approximately ten gestures. The Jester [48] dataset is a large third-party gesture recognition dataset with 148,092 videos collected in 27 categories. The Something-Something V2 [49] dataset is a large-scale action recognition dataset, including 174 common human actions, divided into 168,913 training samples. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/278412313808899-1443390076316_Q64/Roland-Memisevic-2.jpg)
... Subsequent algorithms have sought to address these shortcomings. Berger and Memisevic [14] improved upon Gatys' method by incorporating Markov structures into high-level features, enabling the generation of images that exhibit long-term consistency, suitable for generating textures with global symmetry and transforming image seasons. Risser et al. [15] discovered that the instability of Gram matrices primarily arises from their inability to capture the distribution information of image features. ...
