11 citations · 27 across the 8 of their papers we have counts for
8 papers
Unlocking Deterministic Robustness Certification on ImageNet
Kai Hu, Andy Zou, Zifan Wang +2
Despite the promise of Lipschitz-based methods for provably-robust deep learning with deterministic guarantees, current state-of-the-art results are limited to feed-forward Convolu…
Enhanced Training of Query-Based Object Detection via Selective Query Recollection
Fangyi Chen, Han Zhang, Kai Hu +3
This paper investigates a phenomenon where query-based object detectors mispredict at the last decoding stage while predicting correctly at an intermediate stage. We review the tra…
Contextual Expressive Text-to-Speech
Jianhong Tu, Zeyu Cui, Xiaohuan Zhou +4
The goal of expressive Text-to-speech (TTS) is to synthesize natural speech with desired content, prosody, emotion, or timbre, in high expressiveness. Most of previous studies atte…
ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents
Weihong Lin, Qifang Gao, Lei Sun +4
Recent grid-based document representations like BERTgrid allow the simultaneous encoding of the textual and layout information of a document in a 2D feature map so that state-of-th…
Text to Image Generation with Semantic-Spatial Aware GAN
Kai Hu, Wentong Liao, Michael Ying Yang +1
Text-to-image synthesis (T2I) aims to generate photo-realistic images which are semantically consistent with the text descriptions. Existing methods are usually built upon conditio…
Meta Feature Modulator for Long-tailed Recognition
Renzhen Wang, Kaiqin Hu, Yanwen Zhu +3
Deep neural networks often degrade significantly when training data suffer from class imbalance problems. Existing approaches, e.g., re-sampling and re-weighting, commonly address…
RotationOut as a Regularization Method for Neural Network
Kai Hu, Barnabas Poczos
In this paper, we propose a novel regularization method, RotationOut, for neural networks. Different from Dropout that handles each neuron/channel independently, RotationOut regard…
Qiniu Submission to ActivityNet Challenge 2018
Xiaoteng Zhang, Yixin Bao, Feiyun Zhang +7
In this paper, we introduce our submissions for the tasks of trimmed activity recognition (Kinetics) and trimmed event recognition (Moments in Time) for Activitynet Challenge 2018.…