Kyle Min
13 papers · 2018–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Interdisciplinary Bridge π Academic Marathon (7) π Conference Polyglot (4) π Renaissance Researcher (5) πΊοΈ Taxonomy Completionist (33)
π£
Hot Topic Early Bird
π
Renaissance Researcher
(5)
π
Interdisciplinary Bridge
π₯
Unstoppable
(8)
ποΈ
Keyword Collector
(66)
π
Century Club
(13)
Conferences
CVPR (5)
ECCV (3)
WACV (3)
ICCV (2)
Top co-authors
Keywords
video understanding
(3)
egocentric video
(2)
diffusion model
(2)
catastrophic forgetting
(1)
action recognition
(1)
model fingerprinting
(1)
few-shot learning
(1)
object recognition
(1)
hierarchical classification
(1)
curriculum learning
(1)
object detection
(1)
video classification
(1)
attention mechanism
(1)
temporal reasoning
(1)
egocentric vision
(1)
confidence calibration
(1)
transfer learning
(1)
class-incremental learning
(1)
scene graph generation
(1)
zero-shot learning
(1)
Papers
ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning
ICCV 2025
Ego-VPA: Egocentric Video Understanding with Parameter-Efficient Adaptation
WACV 2025
Deep Geometric Moments Promote Shape Consistency in Text-to-3D Generation
WACV 2025
R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model
ECCV 2024
WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models
CVPR 2024
Action Scene Graphs for Long-Form Understanding of Egocentric Videos
CVPR 2024
Unbiased Scene Graph Generation in Videos
CVPR 2023
SViTT: Temporal Learning of Sparse Video-Text Transformers
CVPR 2023
Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection
ECCV 2022
Integrating Human Gaze Into Attention for Egocentric Activity Recognition
WACV 2021
Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization
ECCV 2020
TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection
ICCV 2019
Hierarchical Novelty Detection for Visual Object Recognition
CVPR 2018