Xiaokun Feng
9 papers · 2023–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (3) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (12) π§ Keyword Pioneer
π
Cross-Pollinator
(14)
Conferences
NIPS (3)
AAAI (2)
ICCV (2)
ICML (2)
Top co-authors
Keywords
video generation
(3)
object tracking
(2)
vision-language tracking
(2)
video understanding
(2)
multi-modal learning
(2)
multimodal learning
(2)
semantic annotation
(1)
vision-language model
(1)
mixture of expert
(1)
benchmark dataset
(1)
semantic dependency
(1)
visual search
(1)
test-time scaling
(1)
prompt tuning
(1)
memory-based learning
(1)
adaptive memory
(1)
conditional generation
(1)
spatio-temporal reasoning
(1)
visual object tracking
(1)
human perception
(1)
Papers
Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation
AAAI 2026
ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints
AAAI 2026
ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking
ICCV 2025
VMBench: A Benchmark for Perception-Aligned Video Motion Generation
ICCV 2025
CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features
ICML 2025
Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness
ICML 2024
Beyond Accuracy: Tracking more like Human via Visual Search
NIPS 2024
MemVLT: Vision-Language Tracking with Adaptive Memory-based Prompts
NIPS 2024
A Multi-modal Global Instance Tracking Benchmark (MGIT): Better Locating Target in Complex Spatio-temporal and Causal Relationship
NIPS 2023