Search Results for author:
Found 7 papers, 4 papers with code
Less Is More: Domain Adaptation with Lottery Ticket for Reading Comprehension
Then, we only fine-tune the lottery subnetwork, a small fraction of the whole parameters, on the annotated target domain data for adaptation.
SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models
Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications.
Distilled Dual-Encoder Model for Vision-Language Understanding
We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering.
HandAugment: A Simple Data Augmentation Method for Depth-Based 3D Hand Pose Estimation
Our method has two main parts: First, We propose a scheme of two-stage neural networks.
Ranked #2 on
Hand Pose Estimation
on HANDS 2019
Transforming Wikipedia into Augmented Data for Query-Focused Summarization
The limited size of existing query-focused summarization datasets renders training data-driven summarization models challenging.
Learning to Ask Unanswerable Questions for Machine Reading Comprehension
We also present a way to construct training data for our question generation models by leveraging the existing reading comprehension dataset.
Real-time Deep Video Deinterlacing
Interlacing is a widely used technique, for television broadcast and video recording, to double the perceived frame rate without increasing the bandwidth.
Ranked #11 on
Video Deinterlacing
on MSU Deinterlacer Benchmark
