中文
相关论文

相关论文: STEP-EZ: Syntax Tree guided semantic ExPlanation f…

200 篇论文

In zero-shot learning (ZSL) community, it is generally recognized that transductive learning performs better than inductive one as the unseen-class samples are also used in its training stage. How to generate pseudo labels for unseen-class…

计算机视觉与模式识别 · 计算机科学 2022-03-31 Bo Liu , Lihua Hu , Qiulei Dong , Zhanyi Hu

Given the semantic descriptions of classes, Zero-Shot Learning (ZSL) aims to recognize unseen classes without labeled training data by exploiting semantic information, which contains knowledge between seen and unseen classes. Existing ZSL…

计算机视觉与模式识别 · 计算机科学 2021-03-31 Vivek Chalumuri , Bac Nguyen

This study investigates explainable machine learning algorithms for identifying depression from speech. Grounded in evidence from speech production that depression affects motor control and vowel generation, pre-trained vowel-based…

机器学习 · 计算机科学 2024-10-25 Kexin Feng , Theodora Chaspari

Early detection of depression from social media data offers a valuable opportunity for timely intervention. However, this task poses significant challenges, requiring both professional medical knowledge and the development of accurate and…

计算与语言 · 计算机科学 2025-03-20 Xiangyong Chen , Xiaochuan Lin

Accurate and interpretable detection of depressive language in social media is useful for early interventions of mental health conditions, and has important implications for both clinical practice and broader public health efforts. In this…

计算与语言 · 计算机科学 2025-06-10 Samuel Kim , Oghenemaro Imieye , Yunting Yin

Zero-shot learning (ZSL) aims to recognize instances of unseen classes solely based on the semantic descriptions of the classes. Existing algorithms usually formulate it as a semantic-visual correspondence problem, by learning mappings from…

计算机视觉与模式识别 · 计算机科学 2019-11-28 Kai Li , Martin Renqiang Min , Yun Fu

Zero-shot Learning (ZSL) is a transfer learning technique which aims at transferring knowledge from seen classes to unseen classes. This knowledge transfer is possible because of underlying semantic space which is common to seen and unseen…

计算机视觉与模式识别 · 计算机科学 2020-05-12 Omkar Gune , Mainak Pal , Preeti Mukherjee , Biplab Banerjee , Subhasis Chaudhuri

Zero-shot learning (ZSL) can be formulated as a cross-domain matching problem: after being projected into a joint embedding space, a visual sample will match against all candidate class-level semantic descriptions and be assigned to the…

计算机视觉与模式识别 · 计算机科学 2018-12-12 Lei Zhang , Peng Wang , Lingqiao Liu , Chunhua Shen , Wei Wei , Yannning Zhang , Anton Van Den Hengel

Zero-shot stance detection (ZSSD) seeks to determine the stance of text toward previously unseen targets, a task critical for analyzing dynamic and polarized online discourse with limited labeled data. While large language models (LLMs)…

计算与语言 · 计算机科学 2026-01-27 Bowen Zhang , Jun Ma , Fuqiang Niu , Li Dong , Jinzhou Cao , Genan Dai

Zero-shot detection (ZSD) is a challenging task where we aim to recognize and localize objects simultaneously, even when our model has not been trained with visual samples of a few target ("unseen") classes. Recently, methods employing…

计算机视觉与模式识别 · 计算机科学 2022-12-13 Sandipan Sarma , Sushil Kumar , Arijit Sur

Zero-Shot Learning (ZSL) has rapidly advanced in recent years. Towards overcoming the annotation bottleneck in the Sign Language Recognition (SLR), we explore the idea of Zero-Shot Sign Language Recognition (ZS-SLR) with no annotated visual…

计算机视觉与模式识别 · 计算机科学 2021-09-06 Razieh Rastgoo , Kourosh Kiani , Sergio Escalera , Mohammad Sabokrou

Zero-shot learning aims to recognize instances of unseen classes, for which no visual instance is available during training, by learning multimodal relations between samples from seen classes and corresponding class semantic…

计算机视觉与模式识别 · 计算机科学 2020-10-08 Yannick Le Cacheux , Hervé Le Borgne , Michel Crucianu

As an important and challenging problem in computer vision, zero-shot learning (ZSL) aims at automatically recognizing the instances from unseen object classes without training data. To address this problem, ZSL is usually carried out in…

计算机视觉与模式识别 · 计算机科学 2017-03-28 Yunlong Yu , Zhong Ji , Xi Li , Jichang Guo , Zhongfei Zhang , Haibin Ling , Fei Wu

This work aims to understand how scaling improves language models, specifically in terms of training dynamics. We find that language models undergo loss deceleration early in training; an abrupt slowdown in the rate of loss improvement,…

Due to the lack of properly annotated medical data, exploring the generalization capability of the deep model is becoming a public concern. Zero-shot learning (ZSL) has emerged in recent years to equip the deep model with the ability to…

计算机视觉与模式识别 · 计算机科学 2022-03-22 Cheng Bian , Chenglang Yuan , Kai Ma , Shuang Yu , Dong Wei , Yefeng Zheng

Zero-shot learning (ZSL) is a popular research problem that aims at predicting for those classes that have never appeared in the training stage by utilizing the inter-class relationship with some side information. In this study, we propose…

人工智能 · 计算机科学 2020-07-01 Jiaoyan Chen , Freddy Lecue , Yuxia Geng , Jeff Z. Pan , Huajun Chen

Early detection of depression from online social media posts holds promise for providing timely mental health interventions. In this work, we present a high-quality, expert-annotated dataset of 1,017 social media posts labeled with…

计算与语言 · 计算机科学 2025-07-29 Prajval Bolegave , Pushpak Bhattacharya

Zero-shot learning (ZSL) aims to recognize unseen classes by generalizing the relation between visual features and semantic attributes learned from the seen classes. A recent paradigm called transductive zero-shot learning further leverages…

计算机视觉与模式识别 · 计算机科学 2023-03-20 Zhengbo Wang , Jian Liang , Zilei Wang , Tieniu Tan

Depression is one of the leading causes of disability worldwide, posing a severe burden on individuals, healthcare systems, and society at large. Recent advancements in Large Language Models (LLMs) have shown promise in addressing mental…

计算与语言 · 计算机科学 2025-02-11 Shiyu Teng , Jiaqing Liu , Rahul Kumar Jain , Shurong Chai , Ruibo Hou , Tomoko Tateyama , Lanfen Lin , Yen-wei Chen

Zero-Shot Learning (ZSL) promises to scale visual recognition by bypassing the conventional model training requirement of annotated examples for every category. This is achieved by establishing a mapping connecting low-level features and a…

计算机视觉与模式识别 · 计算机科学 2016-11-29 Xun Xu , Timothy M. Hospedales , Shaogang Gong