English
Related papers

Related papers: Beat: Bi-directional One-to-Many Embedding Alignme…

200 papers

With the explosive growth of web videos and emerging large-scale vision-language pre-training models, e.g., CLIP, retrieving videos of interest with text instructions has attracted increasing attention. A common practice is to transfer…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Bo Fang , Wenhao Wu , Chang Liu , Yu Zhou , Yuxin Song , Weiping Wang , Xiangbo Shu , Xiangyang Ji , Jingdong Wang

Recent information retrieval (IR) models are pre-trained and instruction-tuned on massive datasets and tasks, enabling them to perform well on a wide range of tasks and potentially generalize to unseen tasks with instructions. However,…

Information Retrieval · Computer Science 2024-10-15 Weiwei Sun , Zhengliang Shi , Jiulong Wu , Lingyong Yan , Xinyu Ma , Yiding Liu , Min Cao , Dawei Yin , Zhaochun Ren

We introduce a model for bidirectional retrieval of images and sentences through a multi-modal embedding of visual and natural language data. Unlike previous models that directly map images or sentences into a common embedding space, our…

Computer Vision and Pattern Recognition · Computer Science 2014-06-24 Andrej Karpathy , Armand Joulin , Li Fei-Fei

Effectively adapting powerful pretrained foundation models to diverse tasks remains a key challenge in AI deployment. Current approaches primarily follow two paradigms:discrete optimization of text prompts through prompt engineering, or…

Computation and Language · Computer Science 2025-08-06 Xiaoming Hou , Jiquan Zhang , Zibin Lin , DaCheng Tao , Shengli Zhang

Most existing person re-identification (re-id) models focus on matching still person images across disjoint camera views. Since only limited information can be exploited from still images, it is hard (if not impossible) to overcome the…

Computer Vision and Pattern Recognition · Computer Science 2016-07-08 Jinjie You , Ancong Wu , Xiang Li , Wei-Shi Zheng

Text-based Pedestrian Retrieval (TPR) deals with retrieving specific target pedestrians in visual scenes according to natural language descriptions. Although existing methods have achieved progress under constrained settings, interactive…

Computer Vision and Pattern Recognition · Computer Science 2025-12-18 Zengli Luo , Canlong Zhang , Xiaochun Lu , Zhixin Li

In this work, we focus on text-based person retrieval, which identifies individuals based on textual descriptions. Despite advancements enabled by synthetic data for pretraining, a significant domain gap, due to variations in lighting,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Shuyu Yang , Yaxiong Wang , Yongrui Li , Li Zhu , Zhedong Zheng

Most existing person re-identification (ReID) methods rely only on the spatial appearance information from either one or multiple person images, whilst ignore the space-time cues readily available in video or image-sequence data. Moreover,…

Computer Vision and Pattern Recognition · Computer Science 2016-11-29 Xiaolong Ma , Xiatian Zhu , Shaogang Gong , Xudong Xie , Jianming Hu , Kin-Man Lam , Yisheng Zhong

LLMs confront inherent limitations in terms of its knowledge, memory, and action. The retrieval augmentation stands as a vital mechanism to address these limitations, which brings in useful information from external sources to augment the…

Information Retrieval · Computer Science 2026-01-06 Peitian Zhang , Shitao Xiao , Zheng Liu , Zhicheng Dou , Jian-Yun Nie

Text embeddings are commonly evaluated on a small set of datasets from a single task not covering their possible applications to other tasks. It is unclear whether state-of-the-art embeddings on semantic textual similarity (STS) can be…

Computation and Language · Computer Science 2023-03-21 Niklas Muennighoff , Nouamane Tazi , Loïc Magne , Nils Reimers

In this paper, we investigate a new approach to Population, Intervention and Outcome (PIO) element detection, a common task in Evidence Based Medicine (EBM). The purpose of this study is two-fold: to build a training dataset for PIO element…

Computation and Language · Computer Science 2019-06-27 Hichem Mezaoui , Aleksandr Gontcharov , Isuru Gunasekara

Person re-identification is challenging due to the large variations of pose, illumination, occlusion and camera view. Owing to these variations, the pedestrian data is distributed as highly-curved manifolds in the feature space, despite the…

Computer Vision and Pattern Recognition · Computer Science 2016-11-02 Hailin Shi , Yang Yang , Xiangyu Zhu , Shengcai Liao , Zhen Lei , Weishi Zheng , Stan Z. Li

Text embedding models play a cornerstone role in AI applications, such as retrieval-augmented generation (RAG). While general-purpose text embedding models demonstrate strong performance on generic retrieval benchmarks, their effectiveness…

Information Retrieval · Computer Science 2025-10-22 Yubai Wei , Jiale Han , Yi Yang

Multi-person human mesh recovery from a single image is a challenging task, hindered by the scarcity of in-the-wild training data. Prevailing in-the-wild human mesh pseudo-ground-truth (pGT) generation pipelines are single-person-centric,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-21 Kaiwen Wang , Kaili Zheng , Yiming Shi , Chenyi Guo , Ji Wu

Retrieval-Augmented Generation (RAG) has emerged as a promising technique to enhance the quality and relevance of responses generated by large language models. While recent advancements have mainly focused on improving RAG for text-based…

Computation and Language · Computer Science 2025-09-30 Ainulla Khan , Yamada Moyuru , Srinidhi Akella

Entity resolution is a widely studied problem with several proposals to match records across relations. Matching textual content is a widespread task in many applications, such as question answering and search. While recent methods achieve…

Databases · Computer Science 2021-12-17 Naser Ahmadi , Hansjorg Sand , Paolo Papotti

GRAP-MOT is a new approach for solving the person MOT problem dedicated to videos of closed areas with overlapping multi-camera views, where person occlusion frequently occurs. Our novel graph-weighted solution updates a person's…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Marek Socha , Michał Marczyk , Aleksander Kempski , Michał Cogiel , Paweł Foszner , Radosław Zawiski , Michał Staniszewski

Multi-object tracking (MOT) is a fundamental problem in computer vision with numerous applications, such as intelligent surveillance and automated driving. Despite the significant progress made in MOT, pedestrian attributes, such as gender,…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Yunhao Li , Zhen Xiao , Lin Yang , Dan Meng , Xin Zhou , Heng Fan , Libo Zhang

Text-based person search, employing free-form text queries to identify individuals within a vast image collection, presents a unique challenge in aligning visual and textual representations, particularly at the human part level. Existing…

Computer Vision and Pattern Recognition · Computer Science 2024-09-23 Jicheol Park , Dongwon Kim , Boseung Jeong , Suha Kwak

We simplify space binding by focusing on two core components, a single encoder per modality and high-quality data; enabling training state-of-the-art models on a single GPU in a few hours as opposed to multiple days. We present EBind, an…

Machine Learning · Computer Science 2025-11-19 Jim Broadbent , Felix Cohen , Frederik Hvilshøj , Eric Landau , Eren Sasoglu