Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
201712.3k citationsRamprasaath R. Selvaraju, Michael Cogswell et al.profile →
This map shows the geographic impact of Devi Parikh'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 Devi Parikh with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Devi Parikh more than expected).
This network shows the impact of papers produced by Devi Parikh. 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 Devi Parikh. The network helps show where Devi Parikh may publish in the future.
Co-authorship network of co-authors of Devi Parikh
This figure shows the co-authorship network connecting the top 25 collaborators of Devi Parikh.
A scholar is included among the top collaborators of Devi Parikh based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with Devi Parikh. Devi Parikh is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
All Works
20 of 20 papers shown
1.
Batra, Dhruv, et al.. (2020). Contrast and Classify: Alternate Training for Robust VQA.. arXiv (Cornell University).2 indexed citations
2.
Anderson, Peter, Ayush Shrivastava, Devi Parikh, Dhruv Batra, & Stefan Lee. (2019). Chasing Ghosts: Instruction Following as Bayesian State Tracking. arXiv (Cornell University). 32. 369–379.10 indexed citations
3.
Das, Abhishek, Satwik Kottur, Khushi Gupta, et al.. (2019). Visual Dialog. IEEE Transactions on Pattern Analysis and Machine Intelligence.12 indexed citations
4.
Yang, Jianwei, et al.. (2019). Cross-channel Communication Networks. Neural Information Processing Systems. 32. 1295–1304.10 indexed citations
Ke, Nan Rosemary, Amanpreet Singh, Abdelaziz Touati, et al.. (2018). Modeling the Long Term Future in Model-Based Reinforcement Learning. International Conference on Learning Representations.5 indexed citations
9.
Lu, Jiasen, Anitha Kannan, Jianwei Yang, Devi Parikh, & Dhruv Batra. (2017). Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model. Neural Information Processing Systems. 30. 314–324.37 indexed citations
10.
Das, Abhishek, Satwik Kottur, Khushi Gupta, et al.. (2017). Visual Dialog. Computer Vision and Pattern Recognition.213 indexed citations
11.
Selvaraju, Ramprasaath R., Michael Cogswell, Abhishek Das, et al.. (2017). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. 618–626.12321 indexed citations breakdown →
12.
Selvaraju, Ramprasaath R., Abhishek Das, Ramakrishna Vedantam, et al.. (2016). Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization. arXiv (Cornell University). 1.44 indexed citations
13.
Mostafazadeh, Nasrin, Nathanael Chambers, Xiaodong He, et al.. (2016). A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories. 839–849.340 indexed citations breakdown →
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.