Zane Durante
7 papers · 2022–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(18)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Computer Vision
(5)
Artificial Intelligence
(4)
Core AI
(4)
Deep Learning
(3)
Analysis
(3)
Processing
(3)
Machine Learning
(2)
Learning Types · Deep Learning
(2)
Natural Language Processing
(1)
Security & Privacy
(1)
Application Areas
(1)
Differential Privacy
(1)
Learning Paradigms
(1)
Learning Types · Machine Learning
(1)
Models
(1)
Keywords
video understanding
(3)
activity recognition
(2)
vision-language model
(2)
multimodal learning
(2)
video captioning
(1)
video classification
(1)
visual localization
(1)
egocentric vision
(1)
visual reasoning
(1)
video instance segmentation
(1)
object tracking
(1)
adversarial attack
(1)
gradient clipping
(1)
foundation model
(1)
privacy budget
(1)
temporal consistency
(1)
long-form video
(1)
video-language model
(1)
memory management
(1)
gradient-based attack
(1)
Papers
Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
ICLR 2025
LOMM: Latest Object Memory Management for Temporally Consistent Video Instance Segmentation
ICCV 2025
Re-thinking Temporal Search for Long-Form Video Understanding
CVPR 2025
Differentially Private Video Activity Recognition
WACV 2024
HourVideo: 1-Hour Video-Language Understanding
NeurIPS 2024
MindAgent: Emergent Gaming Interaction
NAACL 2024
MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing
NeurIPS 2022