L
Longwen Gao
Researcher at Fudan University
Publications - 12
Citations - 142
Longwen Gao is an academic researcher from Fudan University. The author has contributed to research in topics: Data compression & Sparse approximation. The author has an hindex of 4, co-authored 10 publications receiving 87 citations.
Papers
More filters
Proceedings ArticleDOI
Non-Local ConvLSTM for Video Compression Artifact Reduction
TL;DR: An approximate non-local strategy is introduced in NL-ConvLSTM to capture global motion patterns and trace the spatiotemporal dependency in a video sequence to recover high-quality videos from low-quality compressed videos.
Journal ArticleDOI
Effectively classifying short texts by structured sparse representation with dictionary filtering
TL;DR: This work introduces a structured sparse representation classifier to effectively classify short texts, and develops an effective approach called convex hull vertices selection to reduce data correlation and redundancy of the dictionary?(the set of training texts), which thus substantially boosts STC efficiency and performance.
Posted Content
Non-Local ConvLSTM for Video Compression Artifact Reduction
TL;DR: Zhang et al. as mentioned in this paper proposed an end-to-end deep neural network called non-local ConvLSTM (NL-ConvLSTMs) that exploits multiple consecutive frames.
Proceedings ArticleDOI
Boosting the Performance of Video Compression Artifact Reduction with Reference Frame Proposals and Frequency Domain Information
TL;DR: Wang et al. as mentioned in this paper proposed an effective reference frame proposal strategy to boost the performance of the existing multi-frame approaches and introduced a loss based on fast Fourier transformation (FFT) to further improve the effectiveness of restoration.
Proceedings Article
GIF Thumbnails: Attract More Clicks to Your Videos
TL;DR: Zhang et al. as mentioned in this paper proposed a generative variational dual-encoder (GEVADEN) model to generate GIF thumbnails for videos and boost their Click-Through-Rate (CTR).