S
Subarna Tripathi
Researcher at Intel
Publications - 58
Citations - 1541
Subarna Tripathi is an academic researcher from Intel. The author has contributed to research in topics: Object detection & Convolutional neural network. The author has an hindex of 18, co-authored 58 publications receiving 1189 citations. Previous affiliations of Subarna Tripathi include University of California & STMicroelectronics.
Papers
More filters
Proceedings ArticleDOI
PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding
TL;DR: PartNet as discussed by the authors is a large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information, consisting of 573,585 part instances over 26,671 3D models.
Posted Content
Precise Recovery of Latent Vectors from Generative Adversarial Networks
TL;DR: In this paper, a simple gradient-based technique called stochastic clipping is proposed to recover the latent vector pre-images of images generated by GANs. But this method is not robust to noise.
Posted Content
PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding
TL;DR: This work presents PartNet, a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information, and proposes a baseline method for part instance segmentation that is superior performance over existing methods.
Proceedings ArticleDOI
Real-time sign language fingerspelling recognition using convolutional neural networks from depth map
TL;DR: In this article, the authors used CNNs for the classification of 31 alphabets and numbers using a subset of collected depth data from multiple subjects, and achieved 99.99% accuracy for observed signers and 83.58% to 85.49% accuracies for new signers.
Patent
Advance video coding with perceptual quality scalability for regions of interest
TL;DR: In this paper, a video compression framework based on parametric object and background compression is proposed, where an object is detected and frames are segmented into regions corresponding to the foreground object and the background.