28 citations · 56 across the 14 of their papers we have counts for
14 papers · 1 filter
Seed Feature Maps-based CNN Models for LEO Satellite Remote Sensing Services
Zhichao Lu, Chuntao Ding, Shangguang Wang +3
Deploying high-performance convolutional neural network (CNN) models on low-earth orbit (LEO) satellites for rapid remote sensing image processing has attracted significant interes…
Accelerating Vision-Language Pretraining with Free Language Modeling
Teng Wang, Yixiao Ge, Feng Zheng +4
The state of the arts in vision-language pretraining (VLP) achieves exemplary performance but suffers from high training costs resulting from slow convergence and long training tim…
Surrogate-assisted Multi-objective Neural Architecture Search for Real-time Semantic Segmentation
Zhichao Lu, Ran Cheng, Shihua Huang +3
The architectural advancements in deep neural networks have led to remarkable leap-forwards across a broad array of computer vision tasks. Instead of relying on human expertise, ne…
VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix
Teng Wang, Wenhao Jiang, Zhichao Lu +4
Existing vision-language pre-training (VLP) methods primarily rely on paired image-text datasets, which are either annotated by enormous human labors, or crawled from the internet…
S3E-GNN: Sparse Spatial Scene Embedding with Graph Neural Networks for Camera Relocalization
Ran Cheng, Xinyu Jiang, Yuan Chen +2
Camera relocalization is the key component of simultaneous localization and mapping (SLAM) systems. This paper proposes a learning-based approach, named Sparse Spatial Scene Embedd…
Spotlights: Probing Shapes from Spherical Viewpoints
Jiaxin Wei, Lige Liu, Ran Cheng +6
Recent years have witnessed the surge of learned representations that directly build upon point clouds. Though becoming increasingly expressive, most existing representations still…
Semantic-Aware Pretraining for Dense Video Captioning
Teng Wang, Zhu Liu, Feng Zheng +3
This report describes the details of our approach for the event dense-captioning task in ActivityNet Challenge 2021. We present a semantic-aware pretraining method for dense video…
GP-S3Net: Graph-based Panoptic Sparse Semantic Segmentation Network
Ryan Razani, Ran Cheng, Enxu Li +3
Panoptic segmentation as an integrated task of both static environmental understanding and dynamic object identification, has recently begun to receive broad research interest. In…
FaPN: Feature-aligned Pyramid Network for Dense Image Prediction
Shihua Huang, Zhichao Lu, Ran Cheng +1
Recent advancements in deep neural networks have made remarkable leap-forwards in dense image prediction. However, the issue of feature alignment remains as neglected by most exist…
End-to-End Dense Video Captioning with Parallel Decoding
Teng Wang, Ruimao Zhang, Zhichao Lu +3
Dense video captioning aims to generate multiple associated captions with their temporal locations from the video. Previous methods follow a sophisticated "localize-then-describe"…
Lite-HDSeg: LiDAR Semantic Segmentation Using Lite Harmonic Dense Convolutions
Ryan Razani, Ran Cheng, Ehsan Taghavi +1
Autonomous driving vehicles and robotic systems rely on accurate perception of their surroundings. Scene understanding is one of the crucial components of perception modules. Among…
S3Net: 3D LiDAR Sparse Semantic Segmentation Network
Ran Cheng, Ryan Razani, Yuan Ren +1
Semantic Segmentation is a crucial component in the perception systems of many applications, such as robotics and autonomous driving that rely on accurate environmental perception…
(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network
Ran Cheng, Ryan Razani, Ehsan Taghavi +2
Autonomous robotic systems and self driving cars rely on accurate perception of their surroundings as the safety of the passengers and pedestrians is the top priority. Semantic seg…
S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds
Ran Cheng, Christopher Agia, Yuan Ren +2
With the increasing reliance of self-driving and similar robotic systems on robust 3D vision, the processing of LiDAR scans with deep convolutional neural networks has become a tre…