Xiaobin Zhu
12 papers · 2019–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Interdisciplinary Bridge π Conference Polyglot (4) π Academic Marathon (6) π Renaissance Researcher (6) πΊοΈ Taxonomy Completionist (40)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π
Conference Polyglot
(4)
π§¬
Topic Evolution
π€
Dynamic Duo
(10)
π
Century Club
(10)
π
Conference Pioneer
π₯
Unstoppable
(7)
ποΈ
Keyword Collector
(79)
Conferences
AAAI (6)
CVPR (3)
ICCV (2)
COLING (1)
Top co-authors
Keywords
recurrent neural network
(3)
text detection
(3)
graph convolutional network
(2)
optical flow estimation
(2)
feature extraction
(2)
image restoration
(2)
convolutional neural network
(2)
transfer learning
(1)
self-attention mechanism
(1)
metric learning
(1)
knowledge transfer
(1)
weakly supervised learning
(1)
temporal reasoning
(1)
question answering
(1)
video generation
(1)
computer vision
(1)
action recognition
(1)
semantic alignment
(1)
deep learning
(1)
scene text detection
(1)
Papers
VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation
AAAI 2026
Dual-Geometry Graph Network: Unifying Local and Global Priors for Few-Shot Learning
AAAI 2026
DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework
CVPR 2025
LayoutFormer: Hierarchical Text Detection Towards Scene Text Understanding
CVPR 2024
Recurrent Partial Kernel Network for Efficient Optical Flow Estimation
AAAI 2024
Arbitrary Time Information Modeling via Polynomial Approximation for Temporal Knowledge Graph Embedding
COLING 2024
Learning Correction Filter via Degradation-Adaptive Regression for Blind Single Image Super-Resolution
ICCV 2023
Learning Aligned Cross-Modal Representation for Generalized Zero-Shot Classification
AAAI 2022
Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection
ICCV 2021
Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection
CVPR 2020
Residual Invertible Spatio-Temporal Network for Video Super-Resolution
AAAI 2019
Learning Transferable Self-Attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision
AAAI 2019