Related papers: Predicting Chroma from Luma in AV1

This paper introduces FlowMAC, a novel neural audio codec for high-quality general audio compression at low bit rates based on conditional flow matching (CFM). FlowMAC jointly learns a mel spectrogram encoder, quantizer and decoder. At…

[Abridged] The Coma cluster luminosity function (LF) from ultraviolet (2000 AA) to the near-infrared (H band) is summarized. In the UV the LF is very steep, much steeper than in the optical. The steep Coma UV LF implies that faint and…

Prior to encoding color images for RGB full-color, Bayer color filter array (CFA), and digital time delay integration (DTDI) CFA images, performing chroma subsampling on their converted chroma images is necessary and important. In this…

Temporal feature extraction is an important issue in video-based action recognition. Optical flow is a popular method to extract temporal feature, which produces excellent performance thanks to its capacity of capturing pixel-level…

Pre-training has been proven to be effective in boosting the performance of Isolated Sign Language Recognition (ISLR). Existing pre-training methods solely focus on the compact pose data, which eliminates background perturbation but…

This work examines whether decoder-only Transformers such as LLaMA, which were originally designed for large language models (LLMs), can be adapted to the computer vision field. We first "LLaMAfy" a standard ViT step-by-step to align with…

We introduce here a predictive coding based model that aims to generate accurate and sharp future frames. Inspired by the predictive coding hypothesis and related works, the total model is updated through a combination of bottom-up and…

Despite the remarkable performance of vision language models (VLMs) such as Contrastive Language Image Pre-training (CLIP), the large size of these models is a considerable obstacle to their use in federated learning (FL) systems where the…

We present the first clustering results of X-ray selected AGN at z~3. Using Chandra X-ray imaging and UVR optical colors from MUSYC photometry in the ECDF-S field, we selected a sample of 58 z~3 AGN candidates. From the optical data we also…

CFHTLS optical photometry has been used to study the galaxy luminosity functions of 14 X-ray selected clusters from the XMM-LSS survey. These are mostly groups and poor clusters, with masses (M_{500}) in the range 0.6 to 19x10 ^{13} M_solar…

We constructed the composite Luminosity Function (LF) of cluster galaxies in the g,r and i bands from the photometry of a mixed (Abell and X-ray selected) sample of the cores of 65 clusters, ranging in redshift from 0.05 to 0.25. The…

Continual learning with vision-language models like CLIP offers a pathway toward scalable machine learning systems by leveraging its transferable representations. Existing CLIP-based methods adapt the pre-trained image encoder by adding…

In recent years, large-scale vision-language models (VLMs) have demonstrated remarkable performance on multimodal understanding and reasoning tasks. However, handling high-dimensional visual features often incurs substantial computational…

HEVC includes a Coding Unit (CU) level luminance-based perceptual quantization technique known as AdaptiveQP. AdaptiveQP perceptually adjusts the Quantization Parameter (QP) at the CU level based on the spatial activity of raw input video…

Most sRGB-based LLIE methods suffer from entangled luminance and color, while the HSV color space offers insufficient decoupling at the cost of introducing significant red and black noise artifacts. Recently, the HVI color space has been…

The color - stellar mass-to-light ratio relation (CMLR) is a widely accepted tool to estimate the stellar mass (M*) of a galaxy. However, an individual CMLR tends to give distinct M* for a same galaxy when it is applied in different bands.…

Semantic location prediction from multimodal social media posts is a critical task with applications in personalized services and human mobility analysis. This paper introduces \textit{Contextualized Vision-Language Alignment (CoVLA)}, a…

Reliable estimation of illuminant chromaticity is crucial for simulating color constancy and for white balancing digital images. However, estimating illuminant chromaticity from a single image is an ill-posed task, in general, and existing…

Visual-Language Alignment (VLA) has gained a lot of attention since CLIP's groundbreaking work. Although CLIP performs well, the typical direct latent feature alignment lacks clarity in its representation and similarity scores. On the other…

Graph contrastive learning (GCL) is the most representative and prevalent self-supervised learning approach for graph-structured data. Despite its remarkable success, existing GCL methods highly rely on an augmentation scheme to learn the…