Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization2017 · 13.0k citations
What are hit papers?
Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if any of the following hold:
it has ≥500 total citations;
it reaches ≥1.5× the top-1% citation threshold for papers in the same subfield and year (the
threshold is the minimum needed to enter the top 1%, not the average within it);
it reaches the top citation threshold in at least one of its specific research topics.
2017Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Countries citing papers authored by Ramakrishna Vedantam
Since Specialization
Citations
This map shows the geographic impact of Ramakrishna Vedantam's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Ramakrishna Vedantam with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Ramakrishna Vedantam more than expected).
Fields of papers citing papers by Ramakrishna Vedantam
This network shows the impact of papers produced by Ramakrishna Vedantam. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Ramakrishna Vedantam. The network helps show where Ramakrishna Vedantam may publish in the future.
Co-authors
The 22 scholars most cited alongside Ramakrishna Vedantam, linked wherever they
have co-authored with each other. Click a name or a connecting line to browse the papers
they share.
Border = papers with Ramakrishna VedantamLine = papers co-authored togetherRamakrishna Vedantam links everyone, so they are left out of the graph.
All Works
10 of 10 papers shown
#
Work
1
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Ramakrishna Vedantam is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence, Infectious Diseases, Organic Chemistry and Surgery, having authored 10 papers that have together received 16.0k indexed citations. Recurring topics across this work include Multimodal Machine Learning Applications (8 papers), Domain Adaptation and Few-Shot Learning (7 papers), Advanced Image and Video Retrieval Techniques (2 papers), Topic Modeling (2 papers), Human Pose and Action Recognition (2 papers), Explainable Artificial Intelligence (XAI) (2 papers), Visual Attention and Saliency Detection (1 paper) and Natural Language Processing Techniques (1 paper). The work is most often cited by research in Computer Vision and Pattern Recognition (7.4k citations), Health Informatics (387 citations), Artificial Intelligence (6.8k citations), Radiology, Nuclear Medicine and Imaging (2.3k citations) and Media Technology (690 citations). Ramakrishna Vedantam has collaborated with scholars based in United States, Israel and France. Frequent co-authors include Devi Parikh, Dhruv Batra, Michael Cogswell, Abhishek Das, Ramprasaath R. Selvaraju, C. Lawrence Zitnick, Gal Chechik, Kevin Murphy, Samy Bengio and Xiao Lin. Their work appears in journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, PubMed and arXiv (Cornell University).
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.