Tartar
发表于 2025-3-28 18:38:20
http://reply.papertrans.cn/29/2848/284723/284723_41.png
exceed
发表于 2025-3-28 20:14:32
http://reply.papertrans.cn/29/2848/284723/284723_42.png
forecast
发表于 2025-3-28 23:09:48
http://reply.papertrans.cn/29/2848/284723/284723_43.png
prolate
发表于 2025-3-29 06:14:12
ULIC: Ultra Lightweight Image Coder on Wearable Devices is still computationally-expensive and power-exhaustive, which is hardly affordable by most low-power and general-purpose Micro Controller Units (MCUs). This paper thus proposes the ULIC - a pixel-based, ultra-lightweight lossy image coder to fulfill the purpose. The proposed ULIC is extended subst
Jingoism
发表于 2025-3-29 09:54:51
http://reply.papertrans.cn/29/2848/284723/284723_45.png
vocation
发表于 2025-3-29 12:10:17
Resolution-Agnostic Neural Compression for High-Fidelity Portrait Video Conferencing via Implicit Ranferencing applications. Most pioneering methods rely on classic video compression codec without high-level feature embedding and thus can not reach the extremely low bandwidth. Recent works instead employ model-based neural compression to acquire ultra-low bitrates using sparse representations of e
cravat
发表于 2025-3-29 17:01:42
Fast QTMT Decision for H.266/VVC via Jointly Leveraging Neural Network and Machine Learning Modelsy technologies in H.266/VVC is the QuadTree with nested Multi-type Tree (QTMT), which enhances the coding performance at the cost of increased time complexity. To accelerate the QTMT partitioning process while mitigating performance degradation, this paper models the Coding Unit (CU) partition as a
草率女
发表于 2025-3-29 22:50:26
End-to-End Image Compression Through Machine Semanticss paper, we propose a novel end-to-end machine semantic information compression method. To better align machine semantics with tasks, we jointly optimize the entire process of semantic extraction, compression, and inference. Additionally, we introduce a dedicated activation function called StairReLU
我正派
发表于 2025-3-30 02:40:04
http://reply.papertrans.cn/29/2848/284723/284723_49.png
LEERY
发表于 2025-3-30 06:58:34
Human-Centered Financial Signal Processing: A Case Study on Stock Chart Analysisock price chart plus stock volume chart. We first construct the stock chart with professional stock traders’ visual attention (SPSTV) dataset, which contains 150 stock charts images associated with eye-movement data from 10 professional stock traders. Based on the SPSTV dataset, the transfer learnin