Awesome Computer Vision
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Jingkuan Song — most-cited papers & profile · Computer Vision
← authors
·
overview
Jingkuan Song
22
papers ·
193
citations ·
58
h-index
Tongji University · University of Electronic Science and Technology of China
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
From Pixels to Objects: Cubic Visual Attention for Visual Question Answering
2022 · 12 citations
Localizing Unseen Activities in Video via Image Query
2019 · 7 citations
Support-set based Multi-modal Representation Enhancement for Video Captioning
2022 · 3 citations
Part-Aware Transformer for Generalizable Person Re-identification
2023 · 3 citations
Open-Ended Long-Form Video Question Answering via Hierarchical Convolutional Self-Attention Networks
2019 · 1 citations
Training-Free Semantic Video Composition via Pre-trained Diffusion Model
2024 · 1 citations
Exploiting Scene Graphs for Human-Object Interaction Detection
2021
Learning Dual-Fused Modality-Aware Representations for RGBD Tracking
2022
CageViT: Convolutional Activation Guided Efficient Vision Transformer
2023
Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detection
2023
Top co-authors
Lianli Gao
· 5
Heng Tao Shen
· 3
Pengpeng Zeng
· 2
Yuan-Fang Li
· 2
Zhijie Lin
· 2
Zhou Zhao
· 2
Zhu Zhang
· 2
Ales Leonardis
· 1
Deng Cai
· 1
Feng Zheng
· 1
Feng Zheng
· 1
Hao Ni
· 1
Topics
Object Detection
Video Understanding
Image Generation
Visual Language
3D Vision
Segmentation
Tracking
cs.AI
cs.IR