Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Ghazala Rafiq et al.
Summary: Video description is about understanding visual content and converting it into automatic textual narration. By combining computer vision and natural language processing, it has practical applications in real-time scenarios. Deep learning-based approaches have shown better results than conventional methods. This paper focuses on deep learning-enabled automatic caption generation, specifically on the sequence to sequence techniques.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Chemistry, Analytical
Xuefei Huang et al.
Summary: In this paper, a fusion model that integrates both visual and audio features in the video for captioning is proposed. The model combines the Transformer framework, multi-head attention, and a Common Pool to handle variations in sequence lengths and filter information. LSTM is used as a decoder to generate description sentences, reducing network memory size. Experimental results demonstrate the competitiveness of the method on the ActivityNet Captions dataset.
Article
Computer Science, Information Systems
Yubin Wu et al.
Summary: Traditional intelligent transportation systems can only track objects through fixed surveillance cameras, but with the advent of the Internet of Things, object tracking has become more challenging. To address this issue, we propose a hybrid motion model to improve the tracking accuracy on mobile devices.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Software Engineering
Wei Zhang et al.
Summary: In this paper, a novel network called LF-CFANet is proposed to improve LF super-resolution by dynamically learning the complementary information in LF views. This network utilizes a residual complementary-view spatial and channel attention module (RCSCAM) to effectively interact with the complementary information between views. The proposed LF-CFANet outperforms state-of-the-art methods in terms of reconstruction performance and SR accuracy on both synthetic and real-world datasets.
COMPUTATIONAL VISUAL MEDIA
(2023)
Article
Engineering, Electrical & Electronic
Jincan Deng et al.
Summary: In this paper, a syntax-guided hierarchical attention network (SHAN) is proposed to generate video captions by integrating visual and sentence-context features. Experimental results demonstrate that the proposed method achieves comparable performance with current methods.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Zhi Chang et al.
Summary: The study aims to generate event proposals using visual-audio cues, enhance event-level representations, capture relationships between events, and fuse multi-modal information through an attention-gating mechanism, proposing an event-centric multi-modal fusion approach for dense video captioning. Experimental results demonstrate significant progress on the ActivityNet Caption and YouCook2 datasets.
Article
Engineering, Electrical & Electronic
Bowen Li et al.
Summary: Perceptual quality assessment of videos acquired in the wild is crucial for ensuring the quality of video services. This study proposes a model-based transfer learning approach that combines image quality assessment and action recognition to effectively evaluate target video databases.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Wangyu Choi et al.
Summary: In this paper, a parallel pathway dense video captioning framework is proposed, which can localize and describe events simultaneously without depending on the output of preceding modules. By introducing a representation organization network and an event localizer at the branching point of the parallel pathway, and considering the fluency and coherence of sentences during sentence generation, the proposed method outperforms existing algorithms.
Article
Computer Science, Artificial Intelligence
Shuai Wang et al.
Summary: This paper introduces an extendable multiple nodes tracking framework and proposes a general recurrent tracking unit for scoring track proposals. Additionally, a method for generating simulated tracking data is presented. Experimental results show that these methods achieve state-of-the-art performance in multiple-object tracking tasks, and the recurrent tracking unit also brings significant improvements in other trackers.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Review
Chemistry, Analytical
Bogdan Ilie Sighencea et al.
Summary: Pedestrian trajectory prediction is a key task in areas such as self-driving auto vehicles and mobile robots, with state-of-the-art methods benefiting from advancements in sensors and signal processing technologies. This paper reviews recent deep learning-based solutions for the problem and provides an overview of datasets, performance metrics, and practical applications. Furthermore, the study highlights research gaps and potential new directions for future work.
Article
Engineering, Electrical & Electronic
Weixia Zhang et al.
Summary: The main challenges of the emerging vision-and-language navigation (VLN) problem arise from the combination of language instructions and visual environments, as well as the discrepancy in action selection between training and inference.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Teng Wang et al.
Summary: Dense video captioning aims to generate multiple associated captions with their temporal locations from the video. The proposed framework PDVC formulates the dense caption generation as a set prediction task, showing better results than traditional methods in experiments.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Information Systems
Ka-Hou Chan et al.
2020 IEEE/ACM 13TH INTERNATIONAL CONFERENCE ON UTILITY AND CLOUD COMPUTING (UCC 2020)
(2020)
Article
Computer Science, Artificial Intelligence
Bin Zhao et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Tanzila Rahman et al.
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Jonghwan Mun et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Jingwen Wang et al.
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhiqiang Shen et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Ranjay Krishna et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Joao Carreira et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Review
Multidisciplinary Sciences
Yann LeCun et al.
Proceedings Paper
Computer Science, Artificial Intelligence
Du Tran et al.
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2015)
Article
Computer Science, Artificial Intelligence
Alon Lavie et al.
MACHINE TRANSLATION
(2009)
Article
Computer Science, Artificial Intelligence
Yaron Caspi et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2006)
