中文
相关论文

相关论文: When a Zero-Shooter Cheats: Improving Age Estimati…

200 篇论文

Unobtrusive sensor-based recognition of Activities of Daily Living (ADLs) in smart homes by processing data collected from IoT sensing devices supports applications such as healthcare, safety, and energy management. Recent zero-shot methods…

计算机视觉与模式识别 · 计算机科学 2026-01-14 Michele Fiori , Gabriele Civitarese , Marco Colussi , Claudio Bettini

Large language models (LLMs) are very proficient text generators. We leverage this capability of LLMs to generate task-specific data via zero-shot prompting and promote cross-lingual transfer for low-resource target languages. Given…

计算与语言 · 计算机科学 2024-07-16 Barah Fazili , Ashish Sunil Agrawal , Preethi Jyothi

Model editing aims to correct outdated or erroneous knowledge in large models without costly retraining. Recent research discovered that the mid-layer representation of the subject's final token in a prompt has a strong influence on factual…

计算机视觉与模式识别 · 计算机科学 2025-01-24 Qizhou Chen , Taolin Zhang , Chengyu Wang , Xiaofeng He , Dakan Wang , Tingting Liu

The widespread use of cameras in our society has created an overwhelming amount of video data, far exceeding the capacity for human monitoring. This presents a critical challenge for public safety and security, as the timely detection of…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Pascal Benschop , Cristian Meo , Justin Dauwels , Jelte P. Mense

Multiple Choice Question Answering (MCQA) benchmarks are an established standard for measuring Vision Language Model (VLM) performance in driving tasks. However, we observe the known phenomenon that synthetically generated MCQAs are highly…

机器学习 · 计算机科学 2026-02-23 Sutej Kulgod , Sean Ye , Sanchit Tanwar , Christoffer Heckman

Grammar competency estimation is essential for assessing linguistic proficiency in both written and spoken language; however, the spoken modality presents additional challenges due to its spontaneous, unstructured, and disfluent nature.…

计算与语言 · 计算机科学 2025-11-18 Sourya Dipta Das , Shubham Kumar , Kuldeep Yadav

Detecting anomalous hazards in visual data, particularly in video streams, is a critical challenge in autonomous driving. Existing models often struggle with unpredictable, out-of-label hazards due to their reliance on predefined object…

计算机视觉与模式识别 · 计算机科学 2025-04-21 Shashank Shriram , Srinivasa Perisetla , Aryan Keskar , Harsha Krishnaswamy , Tonko Emil Westerhof Bossen , Andreas Møgelmose , Ross Greer

The most existing studies in the facial age estimation assume training and test images are captured under similar shooting conditions. However, this is rarely valid in real-world applications, where training and test sets usually have…

计算机视觉与模式识别 · 计算机科学 2020-10-28 Ali Akbari , Muhammad Awais , Zhen-Hua Feng , Ammarah Farooq , Josef Kittler

Vision-Language Models (VLMs) show promise as zero-shot goal-conditioned value functions, but their frozen pre-trained representations limit generalization and temporal reasoning. We introduce VITA, a zero-shot value function learning…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Christos Ziakas , Alessandra Russo

Although Large Vision-Language Models (LVLMs) have demonstrated remarkable performance on downstream tasks, they frequently produce contents that deviate from visual information, leading to object hallucination. To tackle this, recent works…

计算机视觉与模式识别 · 计算机科学 2026-05-07 Qiming Li , Zekai Ye , Xiaocheng Feng , Weihong Zhong , Libo Qin , Ruihan Chen , Lei Huang , Baohang Li , Kui Jiang , Yaowei Wang , Ting Liu , Bing Qin

Multimodal Large Language Models (MLLMs) have recently achieved promising zero-shot accuracy on visual question answering (VQA) -- a fundamental task affecting various downstream applications and domains. Given the great potential for the…

计算机视觉与模式识别 · 计算机科学 2024-02-13 Jiarui Zhang , Mahyar Khayatkhoei , Prateek Chhikara , Filip Ilievski

Age estimation has attracted attention for its various medical applications. There are many studies on human age estimation from biomedical images. However, there is no research done on mammograms for age estimation, as far as we know. The…

计算机视觉与模式识别 · 计算机科学 2022-07-14 Charitha Dissanayake Lekamlage , Fabia Afzal , Erik Westerberg , Abbas Cheddad

Estimating age from a single speech is a classic and challenging topic. Although Label Distribution Learning (LDL) can represent adjacent indistinguishable ages well, the uncertainty of the age estimate for each utterance varies from person…

声音 · 计算机科学 2022-11-17 Zuheng Kang , Jianzong Wang , Junqing Peng , Jing Xiao

Large language models (LLMs) can sometimes detect when they are being evaluated and adjust their behavior to appear more aligned, compromising the reliability of safety evaluations. In this paper, we show that adding a steering vector to an…

计算与语言 · 计算机科学 2026-03-03 Tim Tian Hua , Andrew Qin , Samuel Marks , Neel Nanda

Autonomous driving systems often infer pedestrian yielding behavior from geometric and kinematic cues alone, limiting their ability to reason about visual scene context and age-dependent behavioral variability. This limitation can produce…

系统与控制 · 电气工程与系统科学 2026-04-28 Qingwen Pu , Kun Xie , Yuxiang Liu

Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. In the cross-modal setting, tokens in the sentence are masked at random, and the model predicts the masked tokens given the image and the text. In…

计算与语言 · 计算机科学 2021-09-07 Yonatan Bitton , Gabriel Stanovsky , Michael Elhadad , Roy Schwartz

As large language models (LLMs) become ubiquitous in our daily tasks and digital interactions, associated privacy risks are increasingly in focus. While LLM privacy research has primarily focused on the leakage of model training data, it…

人工智能 · 计算机科学 2024-11-05 Batuhan Tömekçe , Mark Vero , Robin Staab , Martin Vechev

Swift response to the detection of endangered minors is an ongoing concern for law enforcement. Many child-focused investigations hinge on digital evidence discovery and analysis. Automated age estimation techniques are needed to aid in…

计算机视觉与模式识别 · 计算机科学 2020-12-03 Felix Anda , Brett A. Becker , David Lillis , Nhien-An Le-Khac , Mark Scanlon

Recent research on Vision Language Models (VLMs) suggests that they rely on inherent biases learned during training to respond to questions about visual properties of an image. These biases are exacerbated when VLMs are asked highly…

计算机视觉与模式识别 · 计算机科学 2025-09-11 Saurav Sengupta , Nazanin Moradinasab , Jiebei Liu , Donald E. Brown

Recent Vision-based Large Language Models~(VisionLLMs) for autonomous driving have seen rapid advancements. However, such promotion is extremely dependent on large-scale high-quality annotated data, which is costly and labor-intensive. To…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Chaoqun Wang , Jie Yang , Xiaobin Hong , Ruimao Zhang