Pandeng Li
9 papers · 2022–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (5) π Renaissance Researcher (7) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (16) π§ Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
ECCV (3)
AAAI (2)
ICCV (2)
CVPR (1)
NIPS (1)
Top co-authors
Keywords
video understanding
(2)
video moment retrieval
(2)
embedding learning
(1)
self-supervised learning
(1)
text representation
(1)
cross-modal learning
(1)
video retrieval
(1)
instruction tuning
(1)
generative model
(1)
diffusion model
(1)
cross-modal alignment
(1)
vision-language model
(1)
multimodal large language model
(1)
visual token
(1)
prototype matching
(1)
open-vocabulary semantic segmentation
(1)
semantic modeling
(1)
structure embedding
(1)
token compression
(1)
temporal localization
(1)
Papers
CLIP-Adapted Region-to-Text Learning for Generative Open-Vocabulary Semantic Segmentation
ICCV 2025
Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models
CVPR 2025
AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation
ECCV 2024
Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval
AAAI 2024
FuseTeacher: Modality-fused Encoders are Strong Vision Supervisors
ECCV 2024
MomentDiff: Generative Video Moment Retrieval from Random to Real
NIPS 2023
Progressive Spatio-Temporal Prototype Matching for Text-Video Retrieval
ICCV 2023
Neighborhood-Adaptive Structure Augmented Metric Learning
AAAI 2022
Dual-Stream Knowledge-Preserving Hashing for Unsupervised Video Retrieval
ECCV 2022