中文
相关论文

相关论文: Optimal Transport Adapter Tuning for Bridging Moda…

200 篇论文

Few-shot object detection (FSOD) has garnered significant research attention in the field of remote sensing due to its ability to reduce the dependency on large amounts of annotated data. However, two challenges persist in this area: (1)…

计算机视觉与模式识别 · 计算机科学 2024-03-21 Jiawei Zhou , Wuzhou Li , Yi Cao , Hongtao Cai , Xiang Li

Semantic segmentation of multichannel images is a fundamental task for many applications. Selecting an appropriate channel combination from the original multichannel image can improve the accuracy of semantic segmentation and reduce the…

计算机视觉与模式识别 · 计算机科学 2023-05-09 Yuanzhi Cai , Jagannath Aryal , Yuan Fang , Hong Huang , Lei Fan

This study introduces a novel approach for estimating plane-wave coefficients in sound field reconstruction, specifically addressing challenges posed by error-in-variable phase perturbations. Such systematic errors typically arise from…

信号处理 · 电气工程与系统科学 2026-02-06 Yuyang Liu , Johan Karlsson , Filip Elvander

The nonlinear filtering problem is concerned with finding the conditional probability distribution (posterior) of the state of a stochastic dynamical system, given a history of partial and noisy observations. This paper presents a…

最优化与控制 · 数学 2024-03-26 Mohammad Al-Jarrah , Bamdad Hosseini , Amirhossein Taghvaei

Corpus Aware Training (CAT) leverages valuable corpus metadata during training by injecting corpus information into each training example, and has been found effective in the literature, commonly known as the "tagging" approach. Models…

机器学习 · 计算机科学 2025-08-08 Yi-Hsiu Liao , Cheng Shen , Brenda , Yang

In this paper, we propose an Omni-perception Pre-Trainer (OPT) for cross-modal understanding and generation, by jointly modeling visual, text and audio resources. OPT is constructed in an encoder-decoder framework, including three…

计算机视觉与模式识别 · 计算机科学 2021-07-07 Jing Liu , Xinxin Zhu , Fei Liu , Longteng Guo , Zijia Zhao , Mingzhen Sun , Weining Wang , Hanqing Lu , Shiyu Zhou , Jiajun Zhang , Jinqiao Wang

The interaction data used by recommender systems (RSs) inevitably include noises resulting from mistaken or exploratory clicks, especially under implicit feedbacks. Without proper denoising, RS models cannot effectively capture users'…

信息检索 · 计算机科学 2022-04-20 Yanchao Tan , Carl Yang Member , Xiangyu Wei , Ziyue Wu , Xiaolin Zheng

Current multi-object tracking (MOT) algorithms typically overlook issues inherent in low-quality videos, leading to significant degradation in tracking performance when confronted with real-world image deterioration. Therefore, advancing…

计算机视觉与模式识别 · 计算机科学 2025-09-18 Jun Du , Weiwei Xing , Ming Li , Fei Richard Yu

Variational Auto-Encoders enforce their learned intermediate latent-space data distribution to be a simple distribution, such as an isotropic Gaussian. However, this causes the posterior collapse problem and loses manifold structure which…

机器学习 · 计算机科学 2018-09-18 Huidong Liu , Yang Guo , Na Lei , Zhixin Shu , Shing-Tung Yau , Dimitris Samaras , Xianfeng Gu

In online incremental learning, data continuously arrives with substantial distributional shifts, creating a significant challenge because previous samples have limited replay value when learning a new task. Prior research has typically…

机器学习 · 计算机科学 2026-04-17 Quyen Tran , Hai Nguyen , Hoang Phan , Quan Dao , Linh Ngo , Khoat Than , Dinh Phung , Dimitris Metaxas , Trung Le

As a key research direction in the field of multi-object tracking (MOT), UAV-based multi-object tracking has significant application value in the analysis and understanding of urban intelligent transportation systems. However, in complex…

计算机视觉与模式识别 · 计算机科学 2025-09-03 Wenguang Tao , Xiaotian Wang , Tian Yan , Jie Yan , Guodong Li , Kun Bai

Test-time adaptive (TTA) semantic segmentation adapts a source pre-trained image semantic segmentation model to unlabeled batches of target domain test images, different from real-world, where samples arrive one-by-one in an online fashion.…

计算机视觉与模式识别 · 计算机科学 2023-03-01 Debasmit Das , Shubhankar Borse , Hyojin Park , Kambiz Azarian , Hong Cai , Risheek Garrepalli , Fatih Porikli

Understanding open-world semantics is critical for robotic planning and control, particularly in unstructured outdoor environments. Existing vision-language mapping approaches typically rely on object-centric segmentation priors, which…

机器人学 · 计算机科学 2025-09-23 Simon Schwaiger , Stefan Thalhammer , Wilfried Wöber , Gerald Steinbauer-Wagner

Multimarginal optimal transport (MOT) is a powerful framework for modeling interactions between multiple distributions, yet its applicability is bottlenecked by a high computational overhead. Entropic regularization provides computational…

机器学习 · 计算机科学 2025-06-03 Dor Tsur , Ziv Goldfeld , Kristjan Greenewald , Haim Permuter

With the discovery of Wasserstein GANs, Optimal Transport (OT) has become a powerful tool for large-scale generative modeling tasks. In these tasks, OT cost is typically used as the loss for training GANs. In contrast to this approach, we…

机器学习 · 计算机科学 2022-03-08 Litu Rout , Alexander Korotin , Evgeny Burnaev

Multi-modal large language models (MLLMs) achieve strong visual-language reasoning but suffer from high inference cost due to redundant visual tokens. Recent work explores visual token pruning to accelerate inference, while existing pruning…

计算机视觉与模式识别 · 计算机科学 2026-04-02 Xiwen Chen , Wenhui Zhu , Gen Li , Xuanzhao Dong , Yujian Xiong , Hao Wang , Peijie Qiu , Qingquan Song , Zhipeng Wang , Shao Tang , Yalin Wang , Abolfazl Razi

Personalizing diffusion models using limited data presents significant challenges, including overfitting, loss of prior knowledge, and degradation of text alignment. Overfitting leads to shifts in the noise prediction distribution,…

计算机视觉与模式识别 · 计算机科学 2025-07-04 JungWoo Chae , Jiyoon Kim , JaeWoong Choi , Kyungyul Kim , Sangheum Hwang

In the dynamic and uncertain environments where reinforcement learning (RL) operates, risk management becomes a crucial factor in ensuring reliable decision-making. Traditional RL approaches, while effective in reward optimization, often…

机器学习 · 计算机科学 2023-09-13 Ali Baheri

Over-the-air (OTA) emulation of diverse sensing target characteristics in a controlled laboratory environment is pivotal for advancing integrated sensing and communication (ISAC) technology, as it facilitates the non-invasive performance…

信号处理 · 电气工程与系统科学 2026-03-12 Chunhui Li , Hao Sun , Wei Fan

Salient object detection (SOD) aims to segment visually prominent regions in images and serves as a foundational task for various computer vision applications. We posit that SOD can now reach near-supervised accuracy without a single…

计算机视觉与模式识别 · 计算机科学 2025-10-21 Muhammad Umer Ramzan , Ali Zia , Abdelwahed Khamis , Noman Ali , Usman Ali , Wei Xiang
‹ 上一页 1 8 9 10 下一页 ›