Aditya Aggarwal

TL;DR: The results from benchmarking the top performers of NTU-120 on Skeletics-152 reveal the challenges and domain gap induced by actions 'in the wild', and proposes new frontiers for human action recognition.

TL;DR: Skeleton-Mimetics-152 as discussed by the authors is a 3D pose-annotated subset of RGB videos sourced from Kinetics-700, a large-scale action dataset, and Metaphorics, a dataset with caption style annotated YouTube videos of the popular social game Dumb Charades and interpretative dance performances.

TL;DR: This paper presents a new system to obtain dense object reconstructions along with 6-DoF poses from a single image, and demonstrates that the approach—dubbed reconstruct, rasterize and backprop (RRB)—achieves significantly lower pose estimation errors compared to prior art, and is able to recover dense object shapes and poses from imagery.

TL;DR: This work presents a new SLAM framework in which they use monocular edge based SLAM, along with category level models, to localize objects in the scene as well as improve the camera trajectory, object poses along with its shape and 3D structure.

TL;DR: In this article, Li et al. presented a new system to obtain dense object reconstructions along with 6-DoF poses from a single image by leveraging recent advances in differentiable rendering (in particular, rasterization) to close the loop with 3D reconstruction in camera frame.