Light-programmed system projects 28-layer 3D images in single shot

Researchers at the UCLA Samueli School of Engineering and CNSI (California NanoSystems Institute), led by Professor Aydogan ...
GitHub

Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder

Outperforms advanced methods in terms of rate-distortion-perception performance. Delivers exceptional encoding efficiency for 35.8 FPS@1080P Maintains competitive decoding speed compared to existing ...
IEEE

AdapNet: Adaptability Decomposing Encoder–Decoder Network for Weakly Supervised Action Recognition and Localization

Abstract: The point process is a solid framework to model sequential data, such as videos, by exploring the underlying relevance. As a challenging problem for high-level video understanding, weakly ...
GitHub

SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation

We propose an encoder-decoder for open-vocabulary semantic segmentation comprising a hierarchical encoder-based cost map generation and a gradual fusion decoder. We introduce a category early ...