α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Xiaojie Jin
Xiaojie Jin
17
papers
1,226
total citations
papers (17)
Conflict-Averse Gradient Descent for Multi-task learning
NEURIPS 2021
arXiv
454
citations
All Tokens Matter: Token Labeling for Training Better Vision Transformers
NEURIPS 2021
arXiv
238
citations
PixelLM: Pixel Reasoning with Large Multimodal Model
CVPR 2024
arXiv
197
citations
HR-NAS: Searching Efficient High-Resolution Neural Architectures With Lightweight Transformers
CVPR 2021
arXiv
74
citations
VISTA-LLAMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens
CVPR 2024
arXiv
73
citations
Neural Architecture Search for Lightweight Non-Local Networks
CVPR 2020
arXiv
55
citations
Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling
ICCV 2023
arXiv
50
citations
VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
CVPR 2025
arXiv
33
citations
AutoTransition: Learning to Recommend Video Transition Effects
ECCV 2022
arXiv
14
citations
Flash-VStream: Efficient Real-Time Understanding for Long Video Streams
ICCV 2025
arXiv
11
citations
AutoSpace: Neural Architecture Search With Less Human Interference
ICCV 2021
arXiv
10
citations
Video Recognition in Portrait Mode
CVPR 2024
arXiv
7
citations
MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval
CVPR 2024
arXiv
7
citations
PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling
NEURIPS 2025
arXiv
2
citations
A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis
NEURIPS 2025
arXiv
1
citations
Exploring Domain Incremental Video Highlights Detection with the LiveFood Benchmark
AAAI 2024
arXiv
0
citations
Stitching Segments and Sentences towards Generalization in Video-Text Pre-training
AAAI 2024
0
citations
