Search Results for author:
Found 7 papers, 2 papers with code
PanoSwin: a Pano-style Swin Transformer for Panorama Understanding
In panorama understanding, the widely used equirectangular projection (ERP) entails boundary discontinuity and spatial distortion.
Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction
Then, we conduct investigations and reveal the fact that: In contrast to humans, the representative state-of-the-art (SOTA) models in DocRE exhibit different decision rules.
Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network
In this paper, we present a Memory Prior Contrastive Network (MPCN) that can store shape prior knowledge in a few-shot learning based 3D reconstruction framework.
3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation
We enhance the performance of image-based methods for category-agnostic object pose estimation by exploiting 3D knowledge learned by a multi-modal method.
CaSS: A Channel-aware Self-supervised Representation Learning Framework for Multivariate Time Series Classification
Many previous works focus on the pretext task of self-supervised learning and usually neglect the complex problem of MTS encoding, leading to unpromising results.
Aerial-PASS: Panoramic Annular Scene Segmentation in Drone Videos
A lightweight panoramic annular semantic segmentation neural network model is designed to achieve high-accuracy and real-time scene parsing.
Ranked #69 on
Semantic Segmentation
on Cityscapes val
A Novel Apex-Time Network for Cross-Dataset Micro-Expression Recognition
As researchers working on such topics are moving to learn from the nature of micro-expression, the practice of using deep learning techniques has evolved from processing the entire video clip of micro-expression to the recognition on apex frame.
