47 citations · 98 across the 29 of their papers we have counts for
8 papers · 1 filter
Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions
Sosuke Suzuki, Yijin Wei, Koichiro Kamide +3
Skeleton-based emotion recognition from body motion remains challenging because emotional expressions are often characterized by subtle dynamic and relational motion cues, and hard…
Understanding Geometric Representations in Self-Supervised Vision Transformers via Subspace Intervention
Weichen Zhou, Yawen Zou, Chunzhi Gu +3
We introduce a controlled subspace intervention framework to investigate how self-supervised Vision Transformers (ViTs) encode dense geometric information. While linear probing is…
ECNet: Effective Controllable Text-to-Image Diffusion Models
Sicheng Li, Keqiang Sun, Zhixin Lai +5
The conditional text-to-image diffusion models have garnered significant attention in recent years. However, the precision of these models is often compromised mainly for two reaso…
AniFaceDrawing: Anime Portrait Exploration during Your Sketching
Zhengyu Huang, Haoran Xie, Tsukasa Fukusato +1
In this paper, we focus on how artificial intelligence (AI) can be used to assist users in the creation of anime portraits, that is, converting rough sketches into anime portraits…
DiffFaceSketch: High-Fidelity Face Image Synthesis with Sketch-Guided Latent Diffusion Model
Yichen Peng, Chunqi Zhao, Haoran Xie +2
Synthesizing face images from monochrome sketches is one of the most fundamental tasks in the field of image-to-image translation. However, it is still challenging to (1)~make mode…
Efficient Human-in-the-loop System for Guiding DNNs Attention
Yi He, Xi Yang, Chia-Ming Chang +2
Attention guidance is an approach to addressing dataset bias in deep learning, where the model relies on incorrect features to make decisions. Focusing on image classification task…
Interactive 3D Character Modeling from 2D Orthogonal Drawings with Annotations
Zhengyu Huang, Haoran Xie, Tsukasa Fukusato
We propose an interactive 3D character modeling approach from orthographic drawings (e.g., front and side views) based on 2D-space annotations. First, the system builds partial cor…
Image Deformation Estimation via Multi-Objective Optimization
Takumi Nakane, Haoran Xie, Chao Zhang
The free-form deformation model can represent a wide range of non-rigid deformations by manipulating a control point lattice over the image. However, due to a large number of param…