The proceedings contain 112 papers. The topics discussed include: conditional neural video coding with spatial-temporal super-resolution;LRCB: a comprehensive benchmark evaluation of reference-free lossless compressio...
ISBN:
(纸本)9798350385878
The proceedings contain 112 papers. The topics discussed include: conditional neural video coding with spatial-temporal super-resolution;LRCB: a comprehensive benchmark evaluation of reference-free lossless compression tools for genomics sequencing long reads data;an imperceptible adversarial attack against reconstruction for learned image compression;judging a video by its bitstream cover;faster wavelet tree queries;distortion-controlled dithering with reduced recompression rate;coding optimization for cloud gaming videos based on three-dimensional image warping;a non-reference just recognized distortion prediction framework for object detection task;variable-rate learned image compression with multi-objective optimization and quantization-reconstruction offsets;and UCVC: a unified contextual video compression framework with joint P-frame and B-frame coding.
The proceedings contain 62 papers. The topics discussed include: video transformer based video quality assessment with spatiotemporally adaptive token selection and assembly;gradient linear model for chroma intra pred...
ISBN:
(纸本)9798350347951
The proceedings contain 62 papers. The topics discussed include: video transformer based video quality assessment with spatiotemporally adaptive token selection and assembly;gradient linear model for chroma intra prediction;decoder-side chroma intra mode derivation in video coding;learned disentangled latent representations for scalable image coding for humans and machines;model compression for datacompression: neural network based lossless compressor made practical;bit-parallel (compressed) wavelet tree construction;a spatial-focal error concealment scheme for corrupted focal stack video;an adaptive intra-frame quantization parameter derivation model jointing with inter-frame analysis;practical construction of sensing matrices for a greedy sparse recovery algorithm over finite fields;and multiple description audio coding for wireless low-frequency sound zones.
The proceedings contain 72 papers. The topics discussed include: a predictive method for estimating the limits of lossless datacompression;irreversible compression of medical images with a rigorous error bound;an eff...
ISBN:
(纸本)9798331534714
The proceedings contain 72 papers. The topics discussed include: a predictive method for estimating the limits of lossless datacompression;irreversible compression of medical images with a rigorous error bound;an efficient lossless gradient compression technique for distributed training systems;accurate performance modeling and uncertainty analysis of lossy compression in scientific applications;neural image compression with multi-scale depthwise separable dilated convolution and multi-distribution mixture entropy model;dynamic temporal reference aggregation for neural video compression;optimization of datacompression parameters using genetic algorithms;scalable image compression based on diffusion models at ultra-low bitrates;and feature compression for machines with range-based channel truncation and frame packing.
The proceedings contain 86 papers. The topics discussed include: synergies between in-loop and out-of-loop mapping for HDR-PQ content;beyond keypoint coding: temporal evolution inference with compact feature represent...
ISBN:
(纸本)9781665478939
The proceedings contain 86 papers. The topics discussed include: synergies between in-loop and out-of-loop mapping for HDR-PQ content;beyond keypoint coding: temporal evolution inference with compact feature representation for talking face video compression;improved deep image compression with joint optimization of cross channel context model and generalized loop filter;a smart reference picture resampling approach for VVC;computing matching statistics on repetitive texts;compact representation of interval graphs of bounded degree and chromatic number;privacy-assured and multi-prior recovered compressed sensing for image compression-encryption applications;compressing cipher images by using semi-tensor product compressed sensing and pre-mapping;an edge aware motion modeling technique leveraging on the discrete cosine basis oriented motion model and frame super resolution;stochastic model of block segmentation based on improper quadtree and optimal code under the bayes criterion;and entropy modeling via gaussian process regression for learned image compression.
The proceedings contain 80 papers. The topics discussed include: backward weighted coding;multi-density convolutional neural network for in-loop filter in video coding;optimized adaptive loop filter in versatile video...
ISBN:
(纸本)9780738112275
The proceedings contain 80 papers. The topics discussed include: backward weighted coding;multi-density convolutional neural network for in-loop filter in video coding;optimized adaptive loop filter in versatile video coding;convolutional neural network for image compression with application to JPEG standard;super resolution for compressed screen content video;the twelvefold way of non-sequential lossless compression;on the choice of sampling rates in multi-rate sampling;low delay robust audio coding by noise shaping, fractional sampling, and source prediction;quad-tree based sample refinement filter for video coding;improving run length encoding by preprocessing;and On Elias-Fano for rank queries in FM-indexes.
The proceedings contain 66 papers. The topics discussed include: pattern search in grammar-compressed graphs;state-based multi-parameter probability estimation for context-based adaptive binary arithmetic coding;edge ...
ISBN:
(纸本)9781728164571
The proceedings contain 66 papers. The topics discussed include: pattern search in grammar-compressed graphs;state-based multi-parameter probability estimation for context-based adaptive binary arithmetic coding;edge minimization in de Bruijn graphs;low rate compression of video with dynamic backgrounds;denoising deep Boltzmann machines: compression for deep learning;convolutional neural network based fast intra mode prediction for H.266/FVC video coding;fast depth intra coding based on layer-classification and CNN for 3D-HEVC;and decompressing Lempel-Ziv compressed text.
Recent years witnessed the development in MPEG point cloud compression (PCC). However, the exploration of inter-frame coding may be impeded due to the lack of dynamic point clouds (point cloud sequences). To promote t...
详细信息
In this paper, we use the biological domain knowledge incorporated into stochastic models for ab initio RNA secondary-structure prediction to improve the state of the art in joint compression of RNA sequence and struc...
详细信息
ISBN:
(纸本)9798350347951
In this paper, we use the biological domain knowledge incorporated into stochastic models for ab initio RNA secondary-structure prediction to improve the state of the art in joint compression of RNA sequence and structure data (Liu et al., BMC Bioinformatics, 2008). Moreover, we show that, conversely, compression ratio can serve as a cheap and robust proxy for comparing the prediction quality of different stochastic models, which may help guide the search for better RNA structure prediction models. Our results build on expert stochastic context-free grammar models of RNA secondary structures (Dowell & Eddy, BMC Bioinformatics, 2004;Nebel & Scheid, Theory in Bio-sciences, 2011) combined with different (static and adaptive) models for rule probabilities and arithmetic coding. We provide a prototype implementation and an extensive empirical evaluation, where we illustrate how grammar features and probability models affect compression ratios.
Variable-rate learning excels in standard dynamic range (SDR) image compression, but extending it to high dynamic range (HDR) images is challenging. We propose an end-to-end Variable-Rate Learned HDR (VRLHDR) compress...
详细信息
CoordFlow is a pixel-wise Implicit Neural Representation (INR) framework for video compression, achieving state-of-the-art results among pixel-wise methods and rivaling both frame-wise and classic techniques. By segme...
详细信息
暂无评论