9.8k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Centre National de la Recherche ScientifiqueFR444 papers
- Institute for High Energy PhysicsES405 papers
- Stanford UniversityUS359 papers
- University of SouthamptonGB359 papers
- University College LondonGB358 papers
- University of MichiganUS356 papers
- Fermi National Accelerator LaboratoryUS350 papers
- University of ChicagoUS344 papers
- Ludwig-Maximilians-Universität MünchenDE323 papers
- University of Illinois Urbana-ChampaignUS315 papers
- Centro de Investigaciones Energéticas, Medioambientales y TecnológicasES312 papers
- The Ohio State UniversityUS305 papers
7 papers · 2 filters
Indiscapes: Instance Segmentation Networks for Layout Parsing of Historical Indic Manuscripts
Abhishek Prusty, Sowmya Aitha, Abhishek Trivedi +1
Historical palm-leaf manuscript and early paper documents from Indian subcontinent form an important part of the world's literary and cultural heritage. Despite their importance, l…
Exploring 3 R's of Long-term Tracking: Re-detection, Recovery and Reliability
Shyamgopal Karthik, Abhinav Moudgil, Vineet Gandhi
Recent works have proposed several long term tracking benchmarks and highlight the importance of moving towards long-duration tracking to bridge the gap with application requiremen…
Active Learning with Point Supervision for Cost-Effective Panicle Detection in Cereal Crops
Akshay L Chandra, Sai Vikas Desai, Vineeth N Balasubramanian +2
Panicle density of cereal crops such as wheat and sorghum is one of the main components for plant breeders and agronomists in understanding the yield of their crops. To phenotype t…
An Adaptive Supervision Framework for Active Learning in Object Detection
Sai Vikas Desai, Akshay L Chandra, Wei Guo +2
Active learning approaches in computer vision generally involve querying strong labels for data. However, previous works have shown that weak supervision can be effective in traini…
AdvGAN++ : Harnessing latent layers for adversary generation
Puneet Mangla, Surgan Jandial, Sakshi Varshney +1
Adversarial examples are fabricated examples, indistinguishable from the original image that mislead neural networks and drastically lower their performance. Recently proposed AdvG…
A Cost Efficient Approach to Correct OCR Errors in Large Document Collections
Deepayan Das, Jerin Philip, Minesh Mathew +1
Word error rate of an ocr is often higher than its character error rate. This is especially true when ocrs are designed by recognizing characters. High word accuracies are critical…
Borrow from Anywhere: Pseudo Multi-modal Object Detection in Thermal Imagery
Chaitanya Devaguptapu, Ninad Akolekar, Manuj M Sharma +1
Can we improve detection in the thermal domain by borrowing features from rich domains like visual RGB? In this paper, we propose a pseudo-multimodal object detector trained on nat…