English
Related papers

Related papers: Enhancing DETRs Variants through Improved Content …

200 papers

Recently, the retrieval models based on dense representations have been gradually applied in the first stage of the document retrieval tasks, showing better performance than traditional sparse vector space models. To obtain high efficiency,…

Information Retrieval · Computer Science 2021-08-20 Hongyin Tang , Xingwu Sun , Beihong Jin , Jingang Wang , Fuzheng Zhang , Wei Wu

Recent self-supervised methods are mainly designed for representation learning with the base model, e.g., ResNets or ViTs. They cannot be easily transferred to DETR, with task-specific Transformer modules. In this work, we present Siamese…

Computer Vision and Pattern Recognition · Computer Science 2023-04-03 Zeren Chen , Gengshi Huang , Wei Li , Jianing Teng , Kun Wang , Jing Shao , Chen Change Loy , Lu Sheng

The recently proposed end-to-end transformer detectors, such as DETR and Deformable DETR, have a cascade structure of stacking 6 decoder layers to update object queries iteratively, without which their performance degrades seriously. In…

Computer Vision and Pattern Recognition · Computer Science 2021-04-06 Zhuyu Yao , Jiangbo Ai , Boxun Li , Chi Zhang

Multimodal encoders have pushed the boundaries of visual document retrieval, matching textual query tokens directly to image patches and achieving state-of-the-art performance on public benchmarks. Recent models relying on this paradigm…

Computation and Language · Computer Science 2026-04-08 Omri Uzan , Asaf Yehudai , Roi pony , Eyal Shnarch , Ariel Gera

Knowledge-Intensive Visual Question Answering (KI-VQA) refers to answering a question about an image whose answer does not lie in the image. This paper presents a new pipeline for KI-VQA tasks, consisting of a retriever and a reader. First,…

Computer Vision and Pattern Recognition · Computer Science 2023-04-27 Alireza Salemi , Juan Altmayer Pizzorno , Hamed Zamani

The dual-encoder has become the de facto architecture for dense retrieval. Typically, it computes the latent representations of the query and document independently, thus failing to fully capture the interactions between the query and…

Computation and Language · Computer Science 2023-10-31 Xingwei He , Yeyun Gong , A-Long Jin , Hang Zhang , Anlei Dong , Jian Jiao , Siu Ming Yiu , Nan Duan

Recently, video moment retrieval and highlight detection (MR/HD) are being spotlighted as the demand for video understanding is drastically increased. The key objective of MR/HD is to localize the moment and estimate clip-wise accordance…

Computer Vision and Pattern Recognition · Computer Science 2023-03-27 WonJun Moon , Sangeek Hyun , SangUk Park , Dongchan Park , Jae-Pil Heo

Composed Image Retrieval (CIR) requires both preserving the visual continuity of the reference image and faithfully executing the semantic variables specified in the modification text, which constitute the core challenge of the task.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Xingtian Pei , Yukun Song , Changwei Wang , Shunpeng Chen , Rongtao Xu , Shengpeng Xu , Shibiao Xu

Query reformulations have long been a key mechanism to alleviate the vocabulary-mismatch problem in information retrieval, for example by expanding the queries with related query terms or by generating paraphrases of the queries. In this…

Information Retrieval · Computer Science 2020-07-17 Xiao Wang , Craig Macdonald , Iadh Ounis

Image segmentation based on continual learning exhibits a critical drop of performance, mainly due to catastrophic forgetting and background shift, as they are required to incorporate new classes continually. In this paper, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2023-11-30 Weijia Wu , Yuzhong Zhao , Zhuang Li , Lianlei Shan , Hong Zhou , Mike Zheng Shou

The recent exploding growth in size of state-of-the-art machine learning models highlights a well-known issue where exponential parameter growth, which has grown to trillions as in the case of the Generative Pre-trained Transformer (GPT),…

Quantum Physics · Physics 2025-02-06 Ethan N. Evans , Matthew Cook , Zachary P. Bradshaw , Margarite L. LaBorde

Query auto-completion (QAC) has been widely studied in the context of web search, yet remains underexplored for in-document search, which we term DocQAC. DocQAC aims to enhance search productivity within long documents by helping users…

Information Retrieval · Computer Science 2026-04-21 Rahul Mehta , Kavin R , Indrajit Pal , Tushar Abhishek , Pawan Goyal , Manish Gupta

In incremental learning, enhancing the generality of knowledge is crucial for adapting to dynamic data inputs. It can develop generalized representations or more balanced decision boundaries, preventing the degradation of long-term…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Hongyang Chen , Shaoling Pu , Lingyu Zheng , Zhongwu Sun

One-to-one matching is a crucial design in DETR-like object detection frameworks. It enables the DETR to perform end-to-end detection. However, it also faces challenges of lacking positive sample supervision and slow convergence speed.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Rongyao Fang , Peng Gao , Aojun Zhou , Yingjie Cai , Si Liu , Jifeng Dai , Hongsheng Li

With the evergrowing sizes of pre-trained models (PTMs), it has been an emerging practice to only provide the inference APIs for users, namely model-as-a-service (MaaS) setting. To adapt PTMs with model parameters frozen, most current…

Computation and Language · Computer Science 2023-05-25 Ganqu Cui , Wentao Li , Ning Ding , Longtao Huang , Zhiyuan Liu , Maosong Sun

Long-context multiple-choice question answering tasks require robust reasoning over extensive text sources. Since most of the pre-trained transformer models are restricted to processing only a few hundred words at a time, successful…

Information Retrieval · Computer Science 2025-01-28 Manish Singh , Manish Shrivastava

DETR accomplishes end-to-end object detection through iteratively generating multiple object candidates based on image features and promoting one candidate for each ground-truth object. The traditional training procedure using one-to-one…

Computer Vision and Pattern Recognition · Computer Science 2024-01-09 Chuyang Zhao , Yifan Sun , Wenhao Wang , Qiang Chen , Errui Ding , Yi Yang , Jingdong Wang

The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement largely lies in the modeling of linguistic information by decoder. The decoder joint-optimized with an…

Computation and Language · Computer Science 2022-10-27 Xulong Zhang , Jianzong Wang , Ning Cheng , Mengyuan Zhao , Zhiyong Zhang , Jing Xiao

Information retrieval involves selecting artifacts from a corpus that are most relevant to a given search query. The flavor of retrieval typically used in classical applications can be termed as homogeneous and relaxed, where queries and…

Information Retrieval · Computer Science 2023-10-10 Anirudh Khatry , Yasharth Bajpai , Priyanshu Gupta , Sumit Gulwani , Ashish Tiwari

Video Moment Retrieval (MR) aims to localize moments within a video based on a given natural language query. Given the prevalent use of platforms like YouTube for information retrieval, the demand for MR techniques is significantly growing.…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Seojeong Park , Jiho Choi , Kyungjune Baek , Hyunjung Shim