English
Related papers

Related papers: DRetHTR: Linear-Time Decoder-Only Retentive Networ…

200 papers

Real-time object detection has achieved substantial progress through meticulously designed architectures and optimization strategies. However, the pursuit of high-speed inference via lightweight network designs often leads to degraded…

Computer Vision and Pattern Recognition · Computer Science 2025-10-30 Zijun Liao , Yian Zhao , Xin Shan , Yu Yan , Chang Liu , Lei Lu , Xiangyang Ji , Jie Chen

Most existing audio-text retrieval (ATR) approaches typically rely on a single-level interaction to associate audio and text, limiting their ability to align different modalities and leading to suboptimal matches. In this work, we present a…

Sound · Computer Science 2025-05-06 Yifei Xin , Zhihong Zhu , Xuxin Cheng , Xusheng Yang , Yuexian Zou

This paper presents Nana-HDR, a new non-attentive non-autoregressive model with hybrid Transformer-based Dense-fuse encoder and RNN-based decoder for TTS. It mainly consists of three parts: Firstly, a novel Dense-fuse encoder with dense…

Computation and Language · Computer Science 2021-09-29 Shilun Lin , Wenchao Su , Li Meng , Fenglong Xie , Xinhui Li , Li Lu

Since context modeling is critical for estimating depth from a single image, researchers put tremendous effort into obtaining global context. Many global manipulations are designed for traditional CNN-based architectures to overcome the…

Computer Vision and Pattern Recognition · Computer Science 2022-05-02 Chang Shu , Ziming Chen , Lei Chen , Kuan Ma , Minghui Wang , Haibing Ren

Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision. However, Transformer training and inference in previous works…

Computer Vision and Pattern Recognition · Computer Science 2021-12-24 Zizheng Pan , Bohan Zhuang , Haoyu He , Jing Liu , Jianfei Cai

Large language models (LLMs) are increasingly employed for complex tasks that process multiple generation calls in a tree structure with shared prefixes of tokens, including few-shot prompting, multi-step reasoning, speculative decoding,…

Computation and Language · Computer Science 2025-03-10 Jinwei Yao , Kaiqi Chen , Kexun Zhang , Jiaxuan You , Binhang Yuan , Zeke Wang , Tao Lin

The recently proposed DEtection TRansformer (DETR) has established a fully end-to-end paradigm for object detection. However, DETR suffers from slow training convergence, which hinders its applicability to various detection tasks. We…

Computer Vision and Pattern Recognition · Computer Science 2023-02-07 Gongjie Zhang , Zhipeng Luo , Jiaxing Huang , Shijian Lu , Eric P. Xing

Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit…

Computer Vision and Pattern Recognition · Computer Science 2023-02-06 Jiale Zhang , Yulun Zhang , Jinjin Gu , Yongbing Zhang , Linghe Kong , Xin Yuan

Transformers process tokens in parallel but are temporally shallow: at position $t$, each layer attends to key-value pairs computed based on the previous layer, yielding a depth capped by the number of layers. Recurrent models offer…

Machine Learning · Computer Science 2026-04-24 Costin-Andrei Oncescu , Depen Morwani , Samy Jelassi , Alexandru Meterez , Mujin Kwun , Sham Kakade

DETR-like models have significantly boosted the performance of detectors and even outperformed classical convolutional models. However, all tokens are treated equally without discrimination brings a redundant computational burden in the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Dehua Zheng , Wenhui Dong , Hailin Hu , Xinghao Chen , Yunhe Wang

Decoder-only methods, such as GPT, have demonstrated superior performance in many areas compared to traditional encoder-decoder structure transformer methods. Over the years, end-to-end methods based on the traditional transformer…

Computer Vision and Pattern Recognition · Computer Science 2025-07-10 Liao Pan , Yang Feng , Zhao Wenhui , Yua Jinwen , Zhang Dingwen

Annotating bounding boxes for object detection is expensive, time-consuming, and error-prone. In this work, we propose a DETR based framework called ComplETR that is designed to explicitly complete missing annotations in partially annotated…

Computer Vision and Pattern Recognition · Computer Science 2022-09-14 Achin Jain , Kibok Lee , Gurumurthy Swaminathan , Hao Yang , Bernt Schiele , Avinash Ravichandran , Onkar Dabeer

Despite the recent progress in image dehazing, several problems remain largely unsolved such as robustness for varying scenes, the visual quality of reconstructed images, and effectiveness and flexibility for applications. To tackle these…

Computer Vision and Pattern Recognition · Computer Science 2017-12-05 Chongyi Li , Jichang Guo , Fatih Porikli , Chunle Guo , Huzhu Fu , Xi Li

Document-level Neural Machine Translation (DocNMT) has been proven crucial for handling discourse phenomena by introducing document-level context information. One of the most important directions is to input the whole document directly to…

Computation and Language · Computer Science 2023-09-26 Zihan Liu , Zewei Sun , Shanbo Cheng , Shujian Huang , Mingxuan Wang

Scene text recognition (STR) pre-training methods have achieved remarkable progress, primarily relying on synthetic datasets. However, the domain gap between synthetic and real images poses a challenge in acquiring feature representations…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Shuai Zhao , Yongkun Du , Zhineng Chen , Yu-Gang Jiang

Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices. We propose the low-rank transformer (LRT), a memory-efficient and fast neural…

Computation and Language · Computer Science 2020-02-17 Genta Indra Winata , Samuel Cahyawijaya , Zhaojiang Lin , Zihan Liu , Pascale Fung

Dot-product attention mechanism plays a crucial role in modern deep architectures (e.g., Transformer) for sequence modeling, however, na\"ive exact computation of this model incurs quadratic time and memory complexities in sequence length,…

Machine Learning · Computer Science 2023-06-30 Amir Zandieh , Insu Han , Majid Daliri , Amin Karbasi

Image Representation learning via input reconstruction is a common technique in machine learning for generating representations that can be effectively utilized by arbitrary downstream tasks. A well-established approach is using…

Neural and Evolutionary Computing · Computer Science 2025-06-10 Raoof HojatJalali , Edmondo Trentin

Many studies on (Offline) Handwritten Text Recognition (HTR) systems have focused on building state-of-the-art models for line recognition on small corpora. However, adding HTR capability to a large scale multilingual OCR system poses new…

Computer Vision and Pattern Recognition · Computer Science 2019-06-18 R. Reeve Ingle , Yasuhisa Fujii , Thomas Deselaers , Jonathan Baccash , Ashok C. Popat

We study on image super-resolution (SR), which aims to recover realistic textures from a low-resolution (LR) image. Recent progress has been made by taking high-resolution images as references (Ref), so that relevant textures can be…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Fuzhi Yang , Huan Yang , Jianlong Fu , Hongtao Lu , Baining Guo