Zobrazeno 1 - 10
of 6 595
pro vyhledávání: '"Cohen, P S"'
Deception plays a crucial role in strategic interactions with incomplete information. Motivated by security applications, we study a class of two-player turn-based deterministic games with one-sided incomplete information, in which player 1 (P1) aims
Externí odkaz:
http://arxiv.org/abs/2407.14436
The flux ratios of strongly lensed quasars have previously been used to infer the properties of dark matter. In these analyses it is crucial to separate the effect of the main lensing galaxy and the low-mass dark matter halo population. In this work,
Externí odkaz:
http://arxiv.org/abs/2403.08895
Autor:
Perugachi-Diaz, Yura, Sautière, Guillaume, Abati, Davide, Yang, Yang, Habibian, Amirhossein, Cohen, Taco S
Humans do not perceive all parts of a scene with the same resolution, but rather focus on few regions of interest (ROIs). Traditional Object-Based codecs take advantage of this biological intuition, and are capable of non-uniform allocation of bits i
Externí odkaz:
http://arxiv.org/abs/2203.01978
Autor:
van Rozendaal, Ties, Brehmer, Johann, Zhang, Yunfan, Pourreza, Reza, Wiggers, Auke, Cohen, Taco S.
We introduce a video compression algorithm based on instance-adaptive learning. On each video sequence to be transmitted, we finetune a pretrained compression model. The optimal parameters are transmitted to the receiver along with the latent code. B
Externí odkaz:
http://arxiv.org/abs/2111.10302
We propose Skip-Convolutions to leverage the large amount of redundancies in video streams and save computations. Each video is represented as a series of changes across frames and network activations, denoted as residuals. We reformulate standard co
Externí odkaz:
http://arxiv.org/abs/2104.11487
Autor:
Singh, Ankitesh K., Egilmez, Hilmi E., Pourreza, Reza, Coban, Muhammed, Karczewicz, Marta, Cohen, Taco S.
Most of the existing deep learning based end-to-end video coding (DLEC) architectures are designed specifically for RGB color format, yet the video coding standards, including H.264/AVC, H.265/HEVC and H.266/VVC developed over past few decades, have
Externí odkaz:
http://arxiv.org/abs/2104.00807
Autor:
Pourreza, Reza, Cohen, Taco S
While most neural video codecs address P-frame coding (predicting each frame from past ones), in this paper we address B-frame compression (predicting frames using both past and future reference frames). Our B-frame solution is based on the existing
Externí odkaz:
http://arxiv.org/abs/2104.00531
Autor:
Egilmez, Hilmi E., Singh, Ankitesh K., Coban, Muhammed, Karczewicz, Marta, Zhu, Yinhao, Yang, Yang, Said, Amir, Cohen, Taco S.
Most of the existing deep learning based end-to-end image/video coding (DLEC) architectures are designed for non-subsampled RGB color format. However, in order to achieve a superior coding performance, many state-of-the-art block-based compression st
Externí odkaz:
http://arxiv.org/abs/2103.01760
We present PLONQ, a progressive neural image compression scheme which pushes the boundary of variable bitrate compression by allowing quality scalable coding with a single bitstream. In contrast to existing learned variable bitrate solutions which pr
Externí odkaz:
http://arxiv.org/abs/2102.02913
Neural data compression has been shown to outperform classical methods in terms of $RD$ performance, with results still improving rapidly. At a high level, neural compression is based on an autoencoder that tries to reconstruct the input instance fro
Externí odkaz:
http://arxiv.org/abs/2101.08687