English
Related papers

Related papers: A request for clarity over the End of Sequence tok…

200 papers

Extremely low-light text images are common in natural scenes, making scene text detection and recognition challenging. One solution is to enhance these images using low-light image enhancement methods before text extraction. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Che-Tsung Lin , Chun Chet Ng , Zhi Qin Tan , Wan Jun Nah , Xinyu Wang , Jie Long Kew , Pohao Hsu , Shang Hong Lai , Chee Seng Chan , Christopher Zach

Effectively aligning with human judgment when evaluating machine-generated image captions represents a complex yet intriguing challenge. Existing evaluation metrics like CIDEr or CLIP-Score fall short in this regard as they do not take into…

Computer Vision and Pattern Recognition · Computer Science 2024-07-31 Sara Sarto , Marcella Cornia , Lorenzo Baraldi , Rita Cucchiara

Automatically describing the content of an image is a fundamental problem in artificial intelligence that connects computer vision and natural language processing. In this paper, we present a generative model based on a deep recurrent…

Computer Vision and Pattern Recognition · Computer Science 2016-09-22 Oriol Vinyals , Alexander Toshev , Samy Bengio , Dumitru Erhan

End-to-end (E2E) spoken language understanding (SLU) is constrained by the cost of collecting speech-semantics pairs, especially when label domains change. Hence, we explore \textit{zero-shot} E2E SLU, which learns E2E SLU without…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-06 Jianfeng He , Julian Salazar , Kaisheng Yao , Haoqi Li , Jinglun Cai

Trusted execution environments (TEEs) provide an environment for running workloads in the cloud without having to trust cloud service providers, by offering additional hardware-assisted security guarantees. However, main memory encryption…

Cryptography and Security · Computer Science 2023-09-25 Jan Wichelmann , Anna Pätschke , Luca Wilke , Thomas Eisenbarth

Conventional optical character recognition (OCR) techniques segmented each character and then recognized. This made them prone to error in character segmentation, and devoid of context to exploit language models. Advances in sequence to…

Computer Vision and Pattern Recognition · Computer Science 2025-09-01 Shashank Vempati , Nishit Anand , Gaurav Talebailkar , Arpan Garai , Chetan Arora

Cloud occlusion severely degrades the semantic integrity of optical remote sensing imagery. While incorporating Synthetic Aperture Radar (SAR) provides complementary observations, achieving efficient global modeling and reliable cross-modal…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Chenxing Meng , Wuzhou Quan , Yingjie Cai , Liqun Cao , Liyan Zhang , Mingqiang Wei

Image paragraph captioning aims to describe a given image with a sequence of coherent sentences. Most existing methods model the coherence through the topic transition that dynamically infers a topic vector from preceding sentences.…

Computer Vision and Pattern Recognition · Computer Science 2022-06-22 Qi Zheng , Chaoyue Wang , Dadong Wang

Text-only training provides an attractive approach to address data scarcity challenges in zero-shot image captioning (ZIC), avoiding the expense of collecting paired image-text annotations. However, although these approaches perform well…

Computer Vision and Pattern Recognition · Computer Science 2025-11-13 Zimao Lu , Hui Xu , Bing Liu , Ke Wang

Nowadays, most methods in end-to-end contextual speech recognition bias the recognition process towards contextual knowledge. Since all-neural contextual biasing methods rely on phrase-level contextual modeling and attention-based relevance…

Computation and Language · Computer Science 2022-03-03 Minglun Han , Linhao Dong , Zhenlin Liang , Meng Cai , Shiyu Zhou , Zejun Ma , Bo Xu

Complex narrative contexts often challenge language models' ability to follow instructions, and existing benchmarks fail to capture these difficulties. To address this, we propose Concise-SAE, a training-free framework that improves…

Computation and Language · Computer Science 2025-05-23 Runcong Zhao , Chengyu Cao , Qinglin Zhu , Xiucheng Lv , Shun Shao , Lin Gui , Ruifeng Xu , Yulan He

Image captioning, a fundamental task in vision-language understanding, seeks to generate accurate natural language descriptions for provided images. Current image captioning approaches heavily rely on high-quality image-caption pairs, which…

Computer Vision and Pattern Recognition · Computer Science 2023-11-03 Chuanyang Jin

Existing image captioning models are usually trained by cross-entropy (XE) loss and reinforcement learning (RL), which set ground-truth words as hard targets and force the captioning model to learn from them. However, the widely adopted…

Computer Vision and Pattern Recognition · Computer Science 2022-08-08 Yiqing Huang , Jiansheng Chen

The incremental sequence labeling task involves continuously learning new classes over time while retaining knowledge of the previous ones. Our investigation identifies two significant semantic shifts: E2O (where the model mislabels an old…

Computation and Language · Computer Science 2024-05-28 Shengjie Qiu , Junhao Zheng , Zhen Liu , Yicheng Luo , Qianli Ma

Tremendous progress has been made in recent years in developing better image captioning models, yet most of them rely on a separate object detector to extract regional features. Recent vision-language studies are shifting towards the…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Zhiyuan Fang , Jianfeng Wang , Xiaowei Hu , Lin Liang , Zhe Gan , Lijuan Wang , Yezhou Yang , Zicheng Liu

To solve the Grammatical Error Correction (GEC) problem , a mapping between a source sequence and a target one is needed, where the two differ only on few spans. For this reason, the attention has been shifted to the non-autoregressive or…

Computation and Language · Computer Science 2024-10-23 Kamal Al-Sabahi , Kang Yang , Wangwang Liu , Guanyu Jiang , Xian Li , Ming Yang

Efficient distillation is a key pathway for converting expensive reasoning capability into deployable efficiency, yet in the frontier regime where the student already has strong reasoning ability, naive continual distillation often yields…

Computation and Language · Computer Science 2026-05-22 Zhanming Shen , Jiaqi Hu , Zeyu Qin , Hao Chen , Wentao Ye , Zenan Huang , Yihong Zhuang , Guoshan Lu , Junlin Zhou , Junbo Zhao

Scene text spotting aims to detect and recognize the entire word or sentence with multiple characters in natural images. It is still challenging because ambiguity often occurs when the spacing between characters is large or the characters…

Computer Vision and Pattern Recognition · Computer Science 2021-07-07 Wenhai Wang , Xuebo Liu , Xiaozhong Ji , Enze Xie , Ding Liang , Zhibo Yang , Tong Lu , Chunhua Shen , Ping Luo

In this paper, we have worked on interpretability, trust, and understanding of the decisions made by models in the form of classification tasks. The task is divided into 3 subtasks. The first task consists of determining Binary Sexism…

Computation and Language · Computer Science 2023-04-11 Debashish Roy , Manish Shrivastava

Pseudo-label learning is widely used in semantic segmentation, particularly in label-scarce scenarios such as unsupervised domain adaptation (UDA) and semisupervised learning (SSL). Despite its success, this paradigm can generate erroneous…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Wangkai Li , Rui Sun , Zhaoyang Li , Tianzhu Zhang