English
Related papers

Related papers: Dual-Latent Collaborative Decoding for Fidelity-Pe…

200 papers

Supported by powerful generative models, low-bitrate learned image compression (LIC) models utilizing perceptual metrics have become feasible. Some of the most advanced models achieve high compression rates and superior perceptual quality…

Image and Video Processing · Electrical Eng. & Systems 2024-11-21 Shimon Murai , Heming Sun , Jiro Katto

Entropy coding is widely used in typical learned image compression (LIC) that converts latents into a compact bitstream. However, entropy coding is typically sequential and becomes the coding latency bottleneck. To overcome it, we present…

Image and Video Processing · Electrical Eng. & Systems 2026-05-25 Hao Cao , Wenqi Guo , Zhijin Qin , Jungong Han

Denoising diffusion models achieved impressive results on several image generation tasks often outperforming GAN based models. Recently, the generative capabilities of diffusion models have been employed for perceptual image compression,…

Image and Video Processing · Electrical Eng. & Systems 2025-05-20 Jonas Brenig , Radu Timofte

Variational Autoencoders for multimodal data hold promise for many tasks in data analysis, such as representation learning, conditional generation, and imputation. Current architectures either share the encoder output, decoder input, or…

Recent advances in generative recommenders adopt a two-stage paradigm: items are first tokenized into semantic IDs using a pretrained tokenizer, and then large language models (LLMs) are trained to generate the next item via…

Information Retrieval · Computer Science 2026-05-05 Yifan Liu , Yaokun Liu , Zelin Li , Zhenrui Yue , Gyuseok Lee , Ruichen Yao , Yang Zhang , Dong Wang

Image-Text Retrieval (ITR) is challenging in bridging visual and lingual modalities. Contrastive learning has been adopted by most prior arts. Except for limited amount of negative image-text pairs, the capability of constrastive learning…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Haoran Wang , Dongliang He , Wenhao Wu , Boyang Xia , Min Yang , Fu Li , Yunlong Yu , Zhong Ji , Errui Ding , Jingdong Wang

While recent neural codecs achieve strong performance at low bitrates when optimized for perceptual quality, their effectiveness deteriorates significantly under ultra-low bitrate conditions. To mitigate this, generative compression methods…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Chuqin Zhou , Xiaoyue Ling , Yunuo Chen , Jincheng Dai , Guo Lu , Wenjun Zhang

In semantic image synthesis the state of the art is dominated by methods that use customized variants of the SPatially-Adaptive DE-normalization (SPADE) layers, which allow for good visual generation quality and editing versatility. By…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Tomaso Fontanini , Claudio Ferrari , Giuseppe Lisanti , Massimo Bertozzi , Andrea Prati

Over the past several years, we have witnessed impressive progress in the field of learned image compression. Recent learned image codecs are commonly based on autoencoders, that first encode an image into low-dimensional latent…

Computer Vision and Pattern Recognition · Computer Science 2021-11-02 Zongyu Guo , Zhizheng Zhang , Runsen Feng , Zhibo Chen

Vector quantization is a fundamental tool for compressing high-dimensional embeddings, yet existing multi-codebook methods rely on static codebooks that limit expressiveness under heterogeneous data geometry. While recent dynamic quantizers…

Machine Learning · Computer Science 2026-05-15 Zhengjia Zhong , Shuyan Ke , Zaizhou Lin , Jiaqi Song , Hongyi Lan , Hui Li

The explosion of data has resulted in more and more associated text being transmitted along with images. Inspired by from distributed source coding, many works utilize image side information to enhance image compression. However, existing…

Computer Vision and Pattern Recognition · Computer Science 2023-11-29 Shiyu Qin , Bin Chen , Yujun Huang , Baoyi An , Tao Dai , Shu-Tao Xia

Passage retrieval aims to retrieve relevant passages from large collections of the open-domain corpus. Contextual Masked Auto-Encoding has been proven effective in representation bottleneck pre-training of a monolithic dual-encoder for…

Computation and Language · Computer Science 2023-04-21 Guangyuan Ma , Xing Wu , Peng Wang , Songlin Hu

Large-scale multimodal contrastive learning has recently achieved impressive success in learning rich and transferable representations, yet it remains fundamentally limited by the uniform treatment of feature dimensions and the neglect of…

Machine Learning · Computer Science 2026-02-11 Jinjin Guo , Yexin Li , Zhichao Huang , Jun Fang , Zhiyuan Liu , Chao Liu , Pengzhang Liu , Qixia Jiang

Learned image compression has recently shown the potential to outperform the standard codecs. State-of-the-art rate-distortion (R-D) performance has been achieved by context-adaptive entropy coding approaches in which hyperprior and…

Image and Video Processing · Electrical Eng. & Systems 2021-01-01 Mohammad Akbari , Jie Liang , Jingning Han , Chengjie Tu

We investigate a reinforcement approach for distributed sensing based on the latent space derived from multi-modal deep generative models. Our contribution provides insights to the following benefits: Detections can be exchanged effectively…

Machine Learning · Computer Science 2018-09-13 Timo Korthals , Jürgen Leitner , Ulrich Rückert

Masked image modeling (MIM) has been recognized as a strong self-supervised pre-training approach in the vision domain. However, the mechanism and properties of the learned representations by such a scheme, as well as how to further enhance…

Computer Vision and Pattern Recognition · Computer Science 2024-04-10 Kevin Zhang , Zhiqiang Shen

Multi-modal affective computing aims to automatically recognize and interpret human attitudes from diverse data sources such as images and text, thereby enhancing human-computer interaction and emotion understanding. Existing approaches…

Computation and Language · Computer Science 2025-06-10 Yuanhe Tian , Pengsen Cheng , Guoqing Jin , Lei Zhang , Yan Song

Mixture of Experts (MoE) has become a key architectural paradigm for efficiently scaling Large Language Models (LLMs) by selectively activating a subset of parameters for each input token. However, standard MoE architectures face…

Machine Learning · Computer Science 2025-05-27 Zehua Liu , Han Wu , Ruifeng She , Xiaojin Fu , Xiongwei Han , Tao Zhong , Mingxuan Yuan

Representation Autoencoders (RAEs) leverage frozen vision foundation models (VFMs) as tokenizer encoders, providing robust high-level representations that facilitate fast convergence and high-quality generation in latent diffusion models.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Tianhang Wang , Yitong Chen , Wei Song , Zuxuan Wu , Min Li , Jiaqi Wang

In disentangled representation learning, a model is asked to tease apart a dataset's underlying sources of variation and represent them independently of one another. Since the model is provided with no ground truth information about these…

Machine Learning · Computer Science 2023-10-24 Kyle Hsu , Will Dorrell , James C. R. Whittington , Jiajun Wu , Chelsea Finn