17 citations · 39 across the 26 of their papers we have counts for
8 papers · 2 filters
Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions
Jihoon Kwon, Kyle Min, Jy-yong Sohn
Despite recent advances, vision-language models trained with standard contrastive objectives still struggle with compositional reasoning -- the ability to understand structured rel…
ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning
Jongseo Lee, Kyungho Bae, Kyle Min +2
In this work, we tackle the problem of video classincremental learning (VCIL). Many existing VCIL methods mitigate catastrophic forgetting by rehearsal training with a few temporal…
FLAIR: Frequency- and Locality-Aware Implicit Neural Representations
Sukhun Ko, Seokhyun Youn, Dahyeon Kye +3
Implicit Neural Representations (INRs) leverage neural networks to map coordinates to corresponding signals, enabling continuous and compact representations. This paradigm has driv…
EASG-Bench: Video Q&A Benchmark with Egocentric Action Scene Graphs
Ivan Rodin, Tz-Ying Wu, Kyle Min +4
We introduce EASG-Bench, a question-answering benchmark for egocentric videos where the question-answering pairs are created from spatio-temporally grounded dynamic scene graphs ca…
Keystep Recognition using Graph Neural Networks
Julia Lee Romero, Kyle Min, Subarna Tripathi +1
We pose keystep recognition as a node classification task, and propose a flexible graph-learning framework for fine-grained keystep recognition that is able to effectively leverage…
Reinforcement Learning meets Masked Video Modeling : Trajectory-Guided Adaptive Token Selection
Ayush K. Rai, Kyle Min, Tarun Krishna +3
Masked video modeling~(MVM) has emerged as a highly effective pre-training strategy for visual foundation models, whereby the model reconstructs masked spatiotemporal tokens using…
DecompDreamer: A Composition-Aware Curriculum for Structured 3D Asset Generation
Utkarsh Nath, Rajeev Goel, Rahul Khurana +5
Current text-to-3D methods excel at generating single objects but falter on compositional prompts. We argue this failure is fundamental to their optimization schedules, as simultan…
Graph-Based Multimodal and Multi-view Alignment for Keystep Recognition
Julia Lee Romero, Kyle Min, Subarna Tripathi +1
Egocentric videos capture scenes from a wearer's viewpoint, resulting in dynamic backgrounds, frequent motion, and occlusions, posing challenges to accurate keystep recognition. We…