167 citations · 237 across the 7 of their papers we have counts for
13 papers · 1 filter
Robust Online Video Instance Segmentation with Track Queries
Zitong Zhan, Daniel McKee, Svetlana Lazebnik
Recently, transformer-based methods have achieved impressive results on Video Instance Segmentation (VIS). However, most of these top-performing methods run in an offline manner by…
Transfer of Representations to Video Label Propagation: Implementation Factors Matter
Daniel McKee, Zitong Zhan, Bing Shuai +3
This work studies feature representations for dense label propagation in video, with a focus on recently proposed methods that learn video correspondence using self-supervised sign…
Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents
Shivansh Patel, Saim Wani, Unnat Jain +4
Communication between embodied AI agents has received increasing attention in recent years. Despite its use, it is still unclear whether the learned communication is interpretable…
Multi-Object Tracking with Hallucinated and Unlabeled Videos
Daniel McKee, Bing Shuai, Andrew Berneshawi +4
In this paper, we explore learning end-to-end deep neural trackers without tracking annotations. This is important as large-scale training data is essential for training deep neura…
GridToPix: Training Embodied Agents with Minimal Supervision
Unnat Jain, Iou-Jen Liu, Svetlana Lazebnik +3
While deep reinforcement learning (RL) promises freedom from hand-labeled data, great successes, especially for Embodied AI, require significant work to create supervision via care…
A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks
Unnat Jain, Luca Weihs, Eric Kolve +4
Autonomous agents must learn to collaborate. It is not scalable to develop a new centralized agent every time a task's difficulty outpaces a single agent's abilities. While multi-a…