Deep-view linguistic and inductive learning (DvLIL) based framework for Image Retrieval

Ahmed, Ikhlaq; Iltaf, Naima; Khan, Zafran; Zia, Usman

doi:10.1016/j.ins.2023.119641

Cited by 2 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even well-defined tracking systems, such as Weiming Hu et al 's SiamMask [48], can be improved with image retrieval techniques that process contextual and appearance variations. Using advanced image retrieval algorithms that integrate deep and semantic features (such as the DvLIL system by Ikhlaq Ahmed et al [62]), it is possible to develop an adaptive layer that adjusts the parameters of the tracking model in real time, based on features previously observed in similar situations. This not only improves the robustness of the tracking, but also reduces errors caused by abrupt changes in the scenario or the appearance of objects.…”

Section: Discussionmentioning

confidence: 99%

“…The method was validated on NBA blogs, demonstrating significant improvements in the accuracy and relevance of search results. Ahmed et al [62]: The article describes the development of the Deep-view Linguistic and Inductive Learning (DvLIL) framework, which stands out for combining visual and textual modalities to improve image retrieval. Using stateof-the-art techniques such as ResNet-50 and BERT, the system extracts detailed visual features and generates semantic and contextual representations of the text.…”

Section: Advances In Cbir and Overcoming The Semantic Gapmentioning

confidence: 99%

“…The integration of multimodalities and technological innovation, as seen in the work of Ikhlaq Ahmed et al [62] and Zafran Khan et al [68], exemplify how the combination of in-depth visual features and semantic textual representations can refine image retrieval. This approach not only improves accuracy, but also personalizes the image retrieval experience, adapting to the specific needs of users in a variety of contexts, from e-commerce to multimedia.…”

Section: B Image Retrievalmentioning

confidence: 99%

See 2 more Smart Citations

Enhancing Image Annotation With Object Tracking and Image Retrieval: A Systematic Review

Fernandes,

Pessoa,

Salgado

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Effective image and video annotation is a fundamental pillar in computer vision and artificial intelligence, crucial for the development of accurate machine learning models. Object tracking and image retrieval techniques are essential in this process, significantly improving the efficiency and accuracy of automatic annotation. This paper systematically investigates object tracking and image acquisition techniques. It explores how these technologies can collectively enhance the efficiency and accuracy of the annotation processes for image and video datasets. Object tracking is examined for its role in automating annotations by tracking objects across video sequences, while image retrieval is evaluated for its ability to suggest annotations for new images based on existing data. The review encompasses diverse methodologies, including advanced neural networks and machine learning techniques, highlighting their effectiveness in various contexts like medical analyses and urban monitoring. Despite notable advancements, challenges such as algorithm robustness and effective human-AI collaboration are identified. This review provides valuable insights into these technologies' current state and future potential in improving image annotation processes, even showing existing applications of these techniques and their full potential when combined.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Advances In Cbir and Overcoming The Semantic Gapmentioning

confidence: 99%