English
Related papers

Related papers: Contrastive Learning for Cross-modal Artist Retrie…

200 papers

Discriminative representation is crucial for the association step in multi-object tracking. Recent work mainly utilizes features in single or neighboring frames for constructing metric loss and empowering networks to extract representation…

Computer Vision and Pattern Recognition · Computer Science 2022-04-06 En Yu , Zhuoling Li , Shoudong Han

Multi-modal contrastive learning as a self-supervised representation learning technique has achieved great success in foundation model training, such as CLIP~\citep{radford2021learning}. In this paper, we study the theoretical properties of…

Machine Learning · Statistics 2025-05-20 Yu Gui , Cong Ma , Zongming Ma

The burgeoning short video industry has accelerated the advancement of video-music retrieval technology, assisting content creators in selecting appropriate music for their videos. In self-supervised training for video-to-music retrieval,…

Multimedia · Computer Science 2024-07-30 Zeyu Chen , Pengfei Zhang , Kai Ye , Wei Dong , Xin Feng , Yana Zhang

In this work, we evaluate contrastive models for the task of image retrieval. We hypothesise that models that are learned to encode semantic similarity among instances via discriminative learning should perform well on the task of image…

Computer Vision and Pattern Recognition · Computer Science 2021-05-03 Tarun Krishna , Kevin McGuinness , Noel O'Connor

In the context of music information retrieval, similarity-based approaches are useful for a variety of tasks that benefit from a query-by-example scenario. Music however, naturally decomposes into a set of semantically meaningful factors of…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-03 Sebastian Ribecky , Jakob Abeßer , Hanna Lukashevich

Upscaled video detection is a helpful tool in multimedia forensics, but it is a challenging task that involves various upscaling and compression algorithms. There are many resolution-enhancement methods, including interpolation and…

Computer Vision and Pattern Recognition · Computer Science 2022-05-24 Viacheslav Meshchaninov , Ivan Molodetskikh , Dmitriy Vatolin

Dominant dual-encoder models enable efficient image-text retrieval but suffer from limited accuracy while the cross-encoder models offer higher accuracy at the expense of efficiency. Distilling cross-modality matching knowledge from…

Computer Vision and Pattern Recognition · Computer Science 2024-07-11 Yuxin Chen , Zongyang Ma , Ziqi Zhang , Zhongang Qi , Chunfeng Yuan , Bing Li , Junfu Pu , Ying Shan , Xiaojuan Qi , Weiming Hu

While static word embedding models are known to represent linguistic analogies as parallel lines in high-dimensional space, the underlying mechanism as to why they result in such geometric structures remains obscure. We find that an…

Computation and Language · Computer Science 2023-06-16 Narutatsu Ri , Fei-Tzin Lee , Nakul Verma

Background music (BGM) can enhance the video's emotion. However, selecting an appropriate BGM often requires domain knowledge. This has led to the development of video-music retrieval techniques. Most existing approaches utilize pretrained…

Multimedia · Computer Science 2023-09-19 Tianjun Mao , Shansong Liu , Yunxuan Zhang , Dian Li , Ying Shan

Multi-modal semantic understanding requires integrating information from different modalities to extract users' real intention behind words. Most previous work applies a dual-encoder structure to separately encode image and text, but fails…

Computation and Language · Computer Science 2024-03-12 Ming Zhang , Ke Chang , Yunfang Wu

Recommender systems and search are both indispensable in facilitating personalization and ease of browsing in online fashion platforms. However, the two tools often operate independently, failing to combine the strengths of recommender…

Information Retrieval · Computer Science 2022-07-26 Karin Sevegnani , Arjun Seshadri , Tian Wang , Anurag Beniwal , Julian McAuley , Alan Lu , Gerard Medioni

Generic sentence embeddings provide a coarse-grained approximation of semantic textual similarity but ignore specific aspects that make texts similar. Conversely, aspect-based sentence embeddings provide similarities between texts based on…

Computation and Language · Computer Science 2023-09-26 Tim Schopf , Emanuel Gerber , Malte Ostendorff , Florian Matthes

Learning scientific document representations can be substantially improved through contrastive learning objectives, where the challenge lies in creating positive and negative training samples that encode the desired similarity semantics.…

Computation and Language · Computer Science 2022-10-20 Malte Ostendorff , Nils Rethmeier , Isabelle Augenstein , Bela Gipp , Georg Rehm

Contrastive learning has shown remarkable results in recent self-supervised approaches for visual representation. By learning to contrast positive pairs' representation from the corresponding negatives pairs, one can train good visual…

Computer Vision and Pattern Recognition · Computer Science 2020-11-17 Sungnyun Kim , Gihun Lee , Sangmin Bae , Se-Young Yun

Given multiple source word embeddings learnt using diverse algorithms and lexical resources, meta word embedding learning methods attempt to learn more accurate and wide-coverage word embeddings. Prior work on meta-embedding has repeatedly…

Computation and Language · Computer Science 2022-04-27 Danushka Bollegala

Real-world decision-making often begins with identifying which modality contains the most relevant information for a given query. While recent multimodal models have made impressive progress in processing diverse inputs, it remains unclear…

Video search has become the main routine for users to discover videos relevant to a text query on large short-video sharing platforms. During training a query-video bi-encoder model using online search logs, we identify a modality bias…

Computer Vision and Pattern Recognition · Computer Science 2022-05-18 Xun Wang , Bingqing Ke , Xuanping Li , Fangyu Liu , Mingyu Zhang , Xiao Liang , Qiushi Xiao , Cheng Luo , Yue Yu

Contrastive learning is commonly used as a method of self-supervised learning with the "anchor" and "positive" being two random augmentations of a given input image, and the "negative" is the set of all other images. However, the…

Computer Vision and Pattern Recognition · Computer Science 2022-08-16 Rishab Balasubramanian , Kunal Rathore

With the advent of big data across multiple high-impact applications, we are often facing the challenge of complex heterogeneity. The newly collected data usually consist of multiple modalities and are characterized with multiple labels,…

Machine Learning · Computer Science 2022-07-27 Lecheng Zheng , Jinjun Xiong , Yada Zhu , Jingrui He

Composed image retrieval, a task involving the search for a target image using a reference image and a complementary text as the query, has witnessed significant advancements owing to the progress made in cross-modal modeling. Unlike the…

Computer Vision and Pattern Recognition · Computer Science 2024-02-01 Xintong Jiang , Yaxiong Wang , Yujiao Wu , Meng Wang , Xueming Qian
‹ Prev 1 8 9 10 Next ›