22 citations · 66 across the 11 of their papers we have counts for
5 papers · 1 filter
More Is Better: A MoE-Based Emotion Recognition Framework with Human Preference Alignment
Jun Xie, Yingjian Zhu, Feng Chen +9
In this paper, we present our solution for the semi-supervised learning track (MER-SEMI) in MER2025. We propose a comprehensive framework, grounded in the principle that "more is b…
PCIE_Interaction Solution for Ego4D Social Interaction Challenge
Kanokphan Lertniphonphan, Feng Chen, Junda Xu +4
This report presents our team's PCIE_Interaction solution for the Ego4D Social Interaction Challenge at CVPR 2025, addressing both Looking At Me (LAM) and Talking To Me (TTM) tasks…
ReIDTrack: Multi-Object Track and Segmentation Without Motion
Kaer Huang, Bingchuan Sun, Feng Chen +5
In recent years, dominant Multi-object tracking (MOT) and segmentation (MOTS) methods mainly follow the tracking-by-detection paradigm. Transformer-based end-to-end (E2E) solutions…
Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation
Inkyu Shin, Dahun Kim, Qihang Yu +6
Video Panoptic Segmentation (VPS) aims to achieve comprehensive pixel-level scene understanding by segmenting all pixels and associating objects in a video. Current solutions can b…
Improving Deep Image Matting via Local Smoothness Assumption
Rui Wang, Jun Xie, Jiacheng Han +1
Natural image matting is a fundamental and challenging computer vision task. Conventionally, the problem is formulated as an underconstrained problem. Since the problem is ill-pose…