activity
20182022
most citedHuman in the loop approaches in multi-modal conversational task guidance system development

1 citations · 1 across the 4 of their papers we have counts for

collaborators

5 papers

cs.CL20221 cited

Human in the loop approaches in multi-modal conversational task guidance system development

Ramesh Manuvinakurike, Sovan Biswas, Giuseppe Raffa +6

Development of task guidance systems for aiding humans in a situated task remains a challenging problem. The role of search (information retrieval) and conversational systems for t…

cs.CV2022

Distill and Collect for Semi-Supervised Temporal Action Segmentation

Sovan Biswas, Anthony Rhodes, Ramesh Manuvinakurike +2

Recent temporal action segmentation approaches need frame annotations during training to be effective. These annotations are very expensive and time-consuming to obtain. This limit…

cs.CV2021

Hierarchical Graph-RNNs for Action Detection of Multiple Activities

Sovan Biswas, Yaser Souri, Juergen Gall

In this paper, we propose an approach that spatially localizes the activities in a video frame where each person can perform multiple activities at the same time. Our approach take…

cs.CV2021

Discovering Multi-Label Actor-Action Association in a Weakly Supervised Setting

Sovan Biswas, Juergen Gall

Since collecting and annotating data for spatio-temporal action detection is very expensive, there is a need to learn approaches with less supervision. Weakly supervised approaches…

cs.CV2018

Structural Recurrent Neural Network (SRNN) for Group Activity Analysis

Sovan Biswas, Juergen Gall

A group of persons can be analyzed at various semantic levels such as individual actions, their interactions, and the activity of the entire group. In this paper, we propose a stru…