Search Results for author: Cong Hu

Found 6 papers, 4 papers with code

Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment

1 code implementation25 Dec 2023 Rui Zhao, Liang Zhang, Biao Fu, Cong Hu, Jinsong Su, Yidong Chen

The first KL divergence optimizes the conditional variational autoencoder and regularizes the encoder outputs, while the second KL divergence performs a self-distillation from the posterior path to the prior path, ensuring the consistency of decoder outputs.

Sign Language Translation Translation

SDA-$x$Net: Selective Depth Attention Networks for Adaptive Multi-scale Feature Representation

1 code implementation21 Sep 2022 Qingbei Guo, Xiao-Jun Wu, Zhiquan Feng, Tianyang Xu, Cong Hu

To tackle this issue, we first introduce a new attention dimension, i. e., depth, in addition to existing attention dimensions such as channel, spatial, and branch, and present a novel selective depth attention network to symmetrically handle multi-scale objects in various vision tasks.

A Token-level Contrastive Framework for Sign Language Translation

1 code implementation11 Apr 2022 Biao Fu, PeiGen Ye, Liang Zhang, Pei Yu, Cong Hu, Yidong Chen, Xiaodong Shi

Sign Language Translation (SLT) is a promising technology to bridge the communication gap between the deaf and the hearing people.

Contrastive Learning Machine Translation +5

Dual Encoder-Decoder based Generative Adversarial Networks for Disentangled Facial Representation Learning

no code implementations19 Sep 2019 Cong Hu, Zhen-Hua Feng, Xiao-Jun Wu, Josef Kittler

To be more specific, the encoder-decoder structured generator is used to learn a pose disentangled face representation, and the encoder-decoder structured discriminator is tasked to perform real/fake classification, face reconstruction, determining identity and estimating face pose.

Benchmarking Face Generation +6

Combining Subgoal Graphs with Reinforcement Learning to Build a Rational Pathfinder

no code implementations5 Nov 2018 Junjie Zeng, Long Qin, Yue Hu, Cong Hu, Quanjun Yin

The first advantage of the proposed method is that SSG can solve the limitations of sparse reward and local minima trap for RL agents; thus, LSPI can be used to generate paths in complex environments.

Motion Planning Optimal Motion Planning +3

Cannot find the paper you are looking for? You can Submit a new open access paper.