Rongkun Zheng
5 papers · 2023–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(3)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(11)
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
ICCV (2)
NIPS (2)
ECCV (1)
Top co-authors
Keywords
video instance segmentation
(2)
temporal reasoning
(1)
video understanding
(1)
object localization
(1)
token efficiency
(1)
multi-object tracking
(1)
multimodal large language model
(1)
temporal coherence
(1)
visual token
(1)
transformer decoder
(1)
multi-dataset training
(1)
joint training
(1)
instance tracking
(1)
large language model
(1)
video reasoning segmentation
(1)
semantic distinction
(1)
synchronized modeling
(1)
video-level query
(1)
frame-level query
(1)
taxonomy-aware learning
(1)
Papers
DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs
ICCV 2025
ViLLa: Video Reasoning Segmentation with Large Language Model
ICCV 2025
SyncVIS: Synchronized Video Instance Segmentation
NIPS 2024
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
ECCV 2024
TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation
NIPS 2023