activity
20172022
most citedSketchParse : Towards Rich Descriptions for Poorly Drawn Sketches using Multi-Task Hierarchical Deep Networks

8 citations · 11 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CV20222 cited

DRAMA: Joint Risk Localization and Captioning in Driving

Srikanth Malla, Chiho Choi, Isht Dwivedi +2

Considering the functionality of situational awareness in safety-critical automation systems, the perception of risk in driving scenes and its explainability is of particular impor…

cs.CV20221 cited

Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos

Reza Ghoddoosian, Isht Dwivedi, Nakul Agarwal +2

This paper addresses a new problem of weakly-supervised online action segmentation in instructional videos. We present a framework to segment streaming videos online at test time u…

cs.CV2020

SSP: Single Shot Future Trajectory Prediction

Isht Dwivedi, Srikanth Malla, Behzad Dariush +1

We propose a robust solution to future trajectory forecast, which can be practically applicable to autonomous agents in highly crowded environments. For this, three aspects are par…

cs.CV2019

Dynamic Traffic Scene Classification with Space-Time Coherence

Athma Narayanan, Isht Dwivedi, Behzad Dariush

This paper examines the problem of dynamic traffic scene classification under space-time variations in viewpoint that arise from video captured on-board a moving vehicle. Solutions…

cs.LG2018

High Quality Prediction of Protein Q8 Secondary Structure by Diverse Neural Network Architectures

Iddo Drori, Isht Dwivedi, Pranav Shrestha +13

We tackle the problem of protein secondary structure prediction using a common task framework. This lead to the introduction of multiple ideas for neural architectures based on sta…

cs.CV20178 cited

SketchParse : Towards Rich Descriptions for Poorly Drawn Sketches using Multi-Task Hierarchical Deep Networks

Ravi Kiran Sarvadevabhatla, Isht Dwivedi, Abhijat Biswas +2

The ability to semantically interpret hand-drawn line sketches, although very challenging, can pave way for novel applications in multimedia. We propose SketchParse, the first deep…