Existing instance segmentation models learn task-specific information us...
Text-VQA aims at answering questions that require understanding the text...
We propose value retrieval with arbitrary queries for form-like document...
In the context of online privacy, many methods propose complex privacy a...
Despite great progress in object detection, most existing methods are li...
We propose a novel framework to evaluate the robustness of transformer-b...
We propose a novel framework to conduct field extraction from forms with...
Semi-supervised domain adaptation (SSDA) aims to adapt models from a lab...
Real-time 3D object detection is crucial for autonomous cars. Achieving
...
Online action detection in untrimmed videos aims to identify an action a...
Active learning (AL) integrates data labeling and model training to mini...
We propose weakly supervised language localization networks (WSLLN) to d...
Deep learning has driven great progress in natural and biological image
...
We formulate a new problem as Object Importance Estimation (OIE) in on-r...
We propose StartNet to address Online Detection of Action Start (ODAS) w...
Most work on temporal action detection is formulated in an offline manne...
To reduce the significant redundancy in deep Convolutional Neural Networ...
We introduce a count-guided weakly supervised localization (C-WSL) frame...
We introduce a generic framework that reduces the computational cost of
...