中文
相关论文

相关论文: Cross-modal Contrastive Learning with Asymmetric C…

200 篇论文

Given a collection of untrimmed and unsegmented videos, video corpus moment retrieval (VCMR) is to retrieve a temporal moment (i.e., a fraction of a video) that semantically corresponds to a given text query. As video and text are from two…

计算与语言 · 计算机科学 2021-05-14 Hao Zhang , Aixin Sun , Wei Jing , Guoshun Nan , Liangli Zhen , Joey Tianyi Zhou , Rick Siow Mong Goh

The image-text retrieval task aims to retrieve relevant information from a given image or text. The main challenge is to unify multimodal representation and distinguish fine-grained differences across modalities, thereby finding similar…

多媒体 · 计算机科学 2024-05-20 Ziyu Gong , Chengcheng Mai , Yihua Huang

Contrastive learning has been widely used to train transformer-based vision-language models for video-text alignment and multi-modal representation learning. This paper presents a new algorithm called Token-Aware Cascade contrastive…

计算机视觉与模式识别 · 计算机科学 2021-08-24 Jianwei Yang , Yonatan Bisk , Jianfeng Gao

Video moment retrieval targets at retrieving a moment in a video for a given language query. The challenges of this task include 1) the requirement of localizing the relevant moment in an untrimmed video, and 2) bridging the semantic gap…

计算机视觉与模式识别 · 计算机科学 2023-04-06 Haoyu Tang , Jihua Zhu , Meng Liu , Zan Gao , Zhiyong Cheng

Cross-modal attention mechanisms have been widely applied to the image-text matching task and have achieved remarkable improvements thanks to its capability of learning fine-grained relevance across different modalities. However, the…

计算机视觉与模式识别 · 计算机科学 2022-10-05 Yuxiao Chen , Jianbo Yuan , Long Zhao , Tianlang Chen , Rui Luo , Larry Davis , Dimitris N. Metaxas

Multi-channel video-language retrieval require models to understand information from different channels (e.g. video$+$question, video$+$speech) to correctly link a video with a textual response or query. Fortunately, contrastive multimodal…

计算机视觉与模式识别 · 计算机科学 2023-04-12 Xudong Lin , Simran Tiwari , Shiyuan Huang , Manling Li , Mike Zheng Shou , Heng Ji , Shih-Fu Chang

We present CLIP2Video network to transfer the image-language pre-training model to video-text retrieval in an end-to-end manner. Leading approaches in the domain of video-and-language learning try to distill the spatio-temporal video…

计算机视觉与模式识别 · 计算机科学 2021-06-22 Han Fang , Pengfei Xiong , Luhui Xu , Yu Chen

Temporal grounding, which localizes video moments related to a natural language query, is a core problem of vision-language learning and video understanding. To encode video moments of varying lengths, recent methods employ a multi-level…

计算机视觉与模式识别 · 计算机科学 2026-04-28 Thong Thanh Nguyen , Yi Bin , Xiaobao Wu , Zhiyuan Hu , Cong-Duy T Nguyen , See-Kiong Ng , Anh Tuan Luu

This paper addresses the challenging task of weakly-supervised video temporal grounding. Existing approaches are generally based on the moment proposal selection framework that utilizes contrastive learning and reconstruction paradigm for…

计算机视觉与模式识别 · 计算机科学 2026-05-27 Xiang Fang , Zeyu Xiong , Wanlong Fang , Xiaoye Qu , Chen Chen , Jianfeng Dong , Keke Tang , Pan Zhou , Yu Cheng , Daizong Liu

Video salient object detection aims to find the most visually distinctive objects in a video. To explore the temporal dependencies, existing methods usually resort to recurrent neural networks or optical flow. However, these approaches…

计算机视觉与模式识别 · 计算机科学 2021-11-04 Yi-Wen Chen , Xiaojie Jin , Xiaohui Shen , Ming-Hsuan Yang

Long-form video understanding requires designing approaches that are able to temporally localize activities or language. End-to-end training for such tasks is limited by the compute device memory constraints and lack of temporal annotations…

计算机视觉与模式识别 · 计算机科学 2022-04-27 Mengmeng Xu , Erhan Gundogdu , Maksim Lapin , Bernard Ghanem , Michael Donoser , Loris Bazzani

Unsupervised object-centric learning from videos is a promising approach to extract structured representations from large, unlabeled collections of videos. To support downstream tasks like autonomous control, these representations must be…

计算机视觉与模式识别 · 计算机科学 2025-03-19 Anna Manasyan , Maximilian Seitzer , Filip Radovic , Georg Martius , Andrii Zadaianchuk

Video-text retrieval has been a crucial and fundamental task in multi-modal research. The development of video-text retrieval has been considerably promoted by large-scale multi-modal contrastive pre-training, which primarily focuses on…

计算机视觉与模式识别 · 计算机科学 2022-09-23 Yiwei Ma , Guohai Xu , Xiaoshuai Sun , Ming Yan , Ji Zhang , Rongrong Ji

We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy…

计算机视觉与模式识别 · 计算机科学 2021-04-28 Xin Yuan , Zhe Lin , Jason Kuen , Jianming Zhang , Yilin Wang , Michael Maire , Ajinkya Kale , Baldo Faieta

Large-scale single-stream pre-training has shown dramatic performance in image-text retrieval. Regrettably, it faces low inference efficiency due to heavy attention layers. Recently, two-stream methods like CLIP and ALIGN with high…

计算机视觉与模式识别 · 计算机科学 2022-05-23 Haoyu Lu , Nanyi Fei , Yuqi Huo , Yizhao Gao , Zhiwu Lu , Ji-Rong Wen

The extraction of text information in videos serves as a critical step towards semantic understanding of videos. It usually involved in two steps: (1) text recognition and (2) text classification. To localize texts in videos, we can resort…

计算机视觉与模式识别 · 计算机科学 2022-06-07 Ye Liu , Changchong Lu , Chen Lin , Di Yin , Bo Ren

In recent years, the explosion of web videos makes text-video retrieval increasingly essential and popular for video filtering, recommendation, and search. Text-video retrieval aims to rank relevant text/video higher than irrelevant ones.…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Chen Jiang , Hong Liu , Xuzheng Yu , Qing Wang , Yuan Cheng , Jia Xu , Zhongyi Liu , Qingpei Guo , Wei Chu , Ming Yang , Yuan Qi

Pose-estimation methods enable extracting human motion from common videos in the structured form of 3D skeleton sequences. Despite great application opportunities, effective content-based access to such spatio-temporal motion data is a…

计算机视觉与模式识别 · 计算机科学 2024-07-03 Nicola Messina , Jan Sedmidubsky , Fabrizio Falchi , Tomáš Rebok

Despite recent progress in video and language representation learning, the weak or sparse correspondence between the two modalities remains a bottleneck in the area. Most video-language models are trained via pair-level loss to predict…

机器学习 · 计算机科学 2022-10-12 Zixu Wang , Yujie Zhong , Yishu Miao , Lin Ma , Lucia Specia

Video topic segmentation unveils the coarse-grained semantic structure underlying videos and is essential for other video understanding tasks. Given the recent surge in multi-modal, relying solely on a single modality is arguably…

‹ 上一页 1 2 3 10 下一页 ›