109 citations · 293 across the 16 of their papers we have counts for
18 papers
Enhancing conversational quality in language learning chatbots: An evaluation of GPT4 for ASR error correction
Long Mai, Julie Carson-Berndsen
The integration of natural language processing (NLP) technologies into educational applications has shown promising results, particularly in the language learning domain. Recently,…
Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?
Thang M. Pham, Trung Bui, Long Mai +1
A principle behind dozens of attribution methods is to take the prediction difference between before-and-after an input feature (here, a token) is removed as its attribution. A pop…
Compositional Sketch Search
Alexander Black, Tu Bui, Long Mai +2
We present an algorithm for searching image collections using free-hand sketches that describe the appearance and relative positions of multiple objects. Sketch based image retriev…
APES: Audiovisual Person Search in Untrimmed Video
Juan Leon Alcazar, Long Mai, Federico Perazzi +4
Humans are arguably one of the most important subjects in video streams, many real-world applications such as video summarization or video editing workflows often require the autom…
Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging
S. Mahdi H. Miangoleh, Sebastian Dille, Long Mai +2
Neural networks have shown great abilities in estimating depth from a single image. However, the inferred depth maps are well below one-megapixel resolution and often lack fine-gra…
Learning to Recover 3D Scene Shape from a Single Image
Wei Yin, Jianming Zhang, Oliver Wang +4
Despite significant progress in monocular depth estimation in the wild, recent state-of-the-art methods cannot be used to recover accurate 3D scene shape due to an unknown depth sh…
Out of Order: How Important Is The Sequential Order of Words in a Sentence in Natural Language Understanding Tasks?
Thang M. Pham, Trung Bui, Long Mai +1
Do state-of-the-art natural language understanding models care about word order - one of the most important characteristics of a sequence? Not always! We found 75% to 90% of the co…
Revisiting Adaptive Convolutions for Video Frame Interpolation
Simon Niklaus, Long Mai, Oliver Wang
Video frame interpolation, the synthesis of novel views in time, is an increasingly popular research direction with many new papers further advancing the state of the art. But as e…
Active Speakers in Context
Juan Leon Alcazar, Fabian Caba Heilbron, Long Mai +4
Current methods for active speak er detection focus on modeling short-term audiovisual information from a single speaker. Although this strategy can be enough for addressing single…
Context-Aware Group Captioning via Self-Attention and Contrastive Features
Zhuowan Li, Quan Tran, Long Mai +2
While image captioning has progressed rapidly, existing works focus mainly on describing single images. In this paper, we introduce a new task, context-aware group captioning, whic…
BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images
Thu Nguyen-Phuoc, Christian Richardt, Long Mai +2
We present BlockGAN, an image generative model that learns object-aware 3D scene representations directly from unlabelled 2D images. Current work on scene representation learning e…
A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings
Qi Li, Long Mai, Michael A. Alcorn +1
Large, pre-trained generative models have been increasingly popular and useful to both the research and wider communities. Specifically, BigGANs a class-conditional Generative Adve…
An Internal Learning Approach to Video Inpainting
Haotian Zhang, Long Mai, Ning Xu +3
We propose a novel video inpainting algorithm that simultaneously hallucinates missing appearance and motion (optical flow) information, building upon the recent 'Deep Image Prior'…
3D Ken Burns Effect from a Single Image
Simon Niklaus, Long Mai, Jimei Yang +1
The Ken Burns effect allows animating still images with a virtual camera scan and zoom. Adding parallax, which results in the 3D Ken Burns effect, enables significantly more compel…
M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning
Peng Zhou, Long Mai, Jianming Zhang +3
Incremental learning targets at achieving good performance on new categories without forgetting old ones. Knowledge distillation has been shown critical in preserving the performan…
Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects
Michael A. Alcorn, Qi Li, Zhitao Gong +4
Despite excellent performance on stationary test sets, deep neural networks (DNNs) can fail to generalize to out-of-distribution (OoD) inputs, including natural, non-adversarial on…
Video Frame Interpolation via Adaptive Separable Convolution
Simon Niklaus, Long Mai, Feng Liu
Standard video frame interpolation methods first estimate optical flow between input frames and then synthesize an intermediate frame guided by motion. Recent approaches merge thes…
Video Frame Interpolation via Adaptive Convolution
Simon Niklaus, Long Mai, Feng Liu
Video frame interpolation typically involves two steps: motion estimation and pixel synthesis. Such a two-step approach heavily depends on the quality of motion estimation. This pa…