5 papers
Blind Bitstream-corrupted Video Recovery via Metadata-guided Diffusion Model
Shuyun Wang, Hu Zhang, Xin Shen +2
Bitstream-corrupted video recovery aims to restore realistic content degraded during video storage or transmission. Existing methods typically assume that predefined masks of corru…
Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment
Chen Liu, Peike Li, Liying Yang +3
Accurately localizing audible objects based on audio-visual cues is the core objective of audio-visual segmentation. Most previous methods emphasize spatial or temporal multi-modal…
Dynamic Derivation and Elimination: Audio Visual Segmentation with Enhanced Audio Semantics
Chen Liu, Liying Yang, Peike Li +3
Sound-guided object segmentation has drawn considerable attention for its potential to enhance multimodal perception. Previous methods primarily focus on developing advanced archit…
7ABAW-Compound Expression Recognition via Curriculum Learning
Chen Liu, Feng Qiu, Wei Zhang +3
With the advent of deep learning, expression recognition has made significant advancements. However, due to the limited availability of annotated compound expression datasets and t…
Facial Expression Recognition with Controlled Privacy Preservation and Feature Compensation
Feng Xu, David Ahmedt-Aristizabal, Lars Petersson +2
Facial expression recognition (FER) systems raise significant privacy concerns due to the potential exposure of sensitive identity information. This paper presents a study on remov…