English
Related papers

Related papers: Optical Context Compression Is Just (Bad) Autoenco…

200 papers

Vision-Language Models (VLMs) have shown strong promise on Optical Character Recognition (OCR), yet the sheer number of visual tokens required to encode dense documents incurs prohibitive inference cost. Existing pruning methods rely on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Zihan Tang , Leqi Shen , Hui Chen , Ao Wang , Ben Wan , Yan Feng , Ke Zhang , Sicheng Zhao , Tongxuan Liu , Guiguang Ding

Paper-intensive industries like insurance, law, and government have long leveraged optical character recognition (OCR) to automatically transcribe hordes of scanned documents into text strings for downstream processing. Even in 2019, there…

Computer Vision and Pattern Recognition · Computer Science 2020-01-17 W. Ronny Huang , Yike Qi , Qianqian Li , Jonathan Degange

We propose a new approach to the problem of optimizing autoencoders for lossy image compression. New media formats, changing hardware technology, as well as diverse requirements and content types create a need for compression algorithms…

Machine Learning · Statistics 2017-03-02 Lucas Theis , Wenzhe Shi , Andrew Cunningham , Ferenc Huszár

In recent years, image compression for high-level vision tasks has attracted considerable attention from researchers. Given that object information in images plays a far more crucial role in downstream tasks than background information,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-18 Chengjie Dai , Tiantian Song , Hui Tang , Fangdong Chen , Bowei Yang , Guanghua Song

Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine…

Information Retrieval · Computer Science 2023-10-24 George Zerveas , Navid Rekabsaz , Daniel Cohen , Carsten Eickhoff

Sentence embeddings can be decoded to give approximations of the original texts used to create them. We explore this effect in the context of text simplification, demonstrating that reconstructed text embeddings preserve complexity levels.…

Computation and Language · Computer Science 2025-10-29 Matthew Shardlow

Learned image compression methods have shown impressive performance but are often highly specialized for either human perception or specific machine vision tasks. This specialization limits their versatility and requires costly retraining…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Jinming Liu , Yuntao Wei , Junyan Lin , Shengyang Zhao , Heming Sun , Zhibo Chen , Wenjun Zeng , Xin Jin

Printed text recognition is an important problem for industrial OCR systems. Printed text is constructed in a standard procedural fashion in most settings. We develop a mathematical model for this process that can be applied to the backward…

Computer Vision and Pattern Recognition · Computer Science 2018-11-29 Wei Tang , John Corring , Ying Wu , Gang Hua

Image-text matching has been a hot research topic bridging the vision and language areas. It remains challenging because the current representation of image usually lacks global semantic concepts as in its corresponding text caption. To…

Computer Vision and Pattern Recognition · Computer Science 2019-09-09 Kunpeng Li , Yulun Zhang , Kai Li , Yuanyuan Li , Yun Fu

We introduce Perception Encoder (PE), a state-of-the-art vision encoder for image and video understanding trained via simple vision-language learning. Traditionally, vision encoders have relied on a variety of pretraining objectives, each…

Overfitted neural video codecs offer a decoding complexity orders of magnitude smaller than their autoencoder counterparts. Yet, this low complexity comes at the cost of limited compression efficiency, in part due to their difficulty…

Image and Video Processing · Electrical Eng. & Systems 2025-03-27 Thomas Leguay , Théo Ladune , Pierrick Philippe , Olivier Deforges

In recent years, with the development of deep neural networks, end-to-end optimized image compression has made significant progress and exceeded the classic methods in terms of rate-distortion performance. However, most learning-based image…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Meng Li , Shangyin Gao , Yihui Feng , Yibo Shi , Jing Wang

Modern visual generative models acquire rich visual knowledge through large-scale training, yet existing visual representations (such as pixels, latents, or tokens) remain external to the model and cannot directly exploit this knowledge for…

Machine Learning · Computer Science 2026-05-25 Zongyu Guo , Jiajun He , Zhaoyang Jia , Xiaoyi Zhang , Jiahao Li , Xiao Li , Bin Li , José Miguel Hernández-Lobato , Yan Lu

We address end-to-end learned video compression with a special focus on better learning and utilizing temporal contexts. For temporal context mining, we propose to store not only the previously reconstructed frames, but also the propagated…

Computer Vision and Pattern Recognition · Computer Science 2023-01-31 Xihua Sheng , Jiahao Li , Bin Li , Li Li , Dong Liu , Yan Lu

Most of the existing neural video compression methods adopt the predictive coding framework, which first generates the predicted frame and then encodes its residue with the current frame. However, as for compression ratio, predictive coding…

Image and Video Processing · Electrical Eng. & Systems 2021-12-15 Jiahao Li , Bin Li , Yan Lu

We introduce a simple recurrent variational auto-encoder architecture that significantly improves image modeling. The system represents the state-of-the-art in latent variable models for both the ImageNet and Omniglot datasets. We show that…

Machine Learning · Statistics 2016-05-02 Karol Gregor , Frederic Besse , Danilo Jimenez Rezende , Ivo Danihelka , Daan Wierstra

In the recent years, the dual-encoder vision-language models (\eg CLIP) have achieved remarkable text-to-image retrieval performance. However, we discover that these models usually results in very different retrievals for a pair of…

Computer Vision and Pattern Recognition · Computer Science 2024-05-07 Jiacheng Cheng , Hijung Valentina Shin , Nuno Vasconcelos , Bryan Russell , Fabian Caba Heilbron

Recent efforts to accelerate inference in Multimodal Large Language Models (MLLMs) have largely focused on visual token compression. The effectiveness of these methods is commonly evaluated by measuring the accuracy drop on existing MLLM…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Chenfei Liao , Wensong Wang , Zichen Wen , Xu Zheng , Yiyu Wang , Haocong He , Yuanhuiyi Lyu , Lutao Jiang , Xin Zou , Yuqian Fu , Bin Ren , Linfeng Zhang , Xuming Hu

In learning-based approaches to image compression, codecs are developed by optimizing a computational model to minimize a rate-distortion objective. Currently, the most effective learned image codecs take the form of an entropy-constrained…

Image and Video Processing · Electrical Eng. & Systems 2020-07-20 David Minnen , Saurabh Singh

Repository-level code intelligence tasks require large language models (LLMs) to process long, multi-file contexts. Such inputs introduce three challenges: crucial context can be obscured by noise, truncated due to limited windows, and…

Software Engineering · Computer Science 2026-04-16 Jia Feng , Zhanyue Qin , Cuiyun Gao , Ruiqi Wang , Chaozheng Wang , Yingwei Ma , Xiaoyuan Xie
‹ Prev 1 3 4 5 6 7 10 Next ›